You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2020/09/27 22:35:21 UTC
[incubator-tvm-site] branch asf-site updated: Build at Sun Sep 27
15:35:09 PDT 2020
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/incubator-tvm-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 3335a1e Build at Sun Sep 27 15:35:09 PDT 2020
3335a1e is described below
commit 3335a1e4ef4569e5d737fa529338721705b7f729
Author: tqchen <tq...@octoml.ai>
AuthorDate: Sun Sep 27 15:35:09 2020 -0700
Build at Sun Sep 27 15:35:09 PDT 2020
---
.gitignore | 1 +
2017/08/17/tvm-release-announcement.html | 276 +-
...s-with-TVM-A-Depthwise-Convolution-Example.html | 404 ++-
2017/10/06/nnvm-compiler-announcement.html | 276 +-
...s-to-TVM-Stack-and-NNVM-Compiler-with-ROCm.html | 318 +-
2017/11/08/android-rpc-introduction.html | 360 ++-
2018/01/16/opt-mali-gpu.html | 400 ++-
2018/03/12/webgl.html | 276 +-
2018/03/23/nmt-transformer-optimize.html | 300 +-
2018/07/12/vta-release-announcement.html | 276 +-
2018/08/10/DLPack-Bridge.html | 324 +--
2018/10/03/auto-opt-all.html | 282 +-
2018/10/09/ml-in-tees.html | 276 +-
2018/12/18/lowprecision-conv.html | 296 +-
2019/01/19/Golang.html | 292 +-
2019/03/18/tvm-apache-announcement.html | 324 +--
2019/04/29/opt-cuda-quantized.html | 318 +-
2019/05/30/pytorch-frontend.html | 290 +-
...machine-learning-to-webassembly-and-webgpu.html | 276 +-
2020/05/20/bring-your-own-datatypes.html | 370 ++-
2020/06/04/tinyml-how-tvm-is-taming-tiny.html | 342 ++-
2020/07/14/bert-pytorch-tvm.html | 544 ++--
.../15/how-to-bring-your-own-codegen-to-tvm.html | 370 ++-
404.html | 73 +-
about.html | 226 +-
asf.html | 324 +--
assets/images/Flexibility.svg | 3 +
assets/images/about-image.svg | 91 +
assets/images/about-responsive-image.svg | 413 +++
assets/images/banner-bg.jpg | Bin 0 -> 327674 bytes
assets/images/close-icon.svg | 3 +
assets/images/communitybg.svg | 315 ++
assets/images/dropdown-icon.svg | 3 +
assets/images/favicon.ico | Bin 0 -> 15406 bytes
assets/images/flexbg.svg | 138 +
assets/images/leftslide.svg | 3 +
assets/images/logo.svg | 9 +
assets/images/menu-icon.svg | 5 +
assets/images/modal-close-icon.svg | 3 +
assets/images/pattern.png | Bin 0 -> 84215 bytes
assets/images/performance.svg | 206 ++
assets/images/right.svg | 3 +
assets/images/run.svg | 3 +
assets/images/runbg.svg | 212 ++
assets/images/speed.svg | 7 +
assets/images/use.svg | 3 +
assets/images/usebg.svg | 216 ++
assets/js/custome.js | 27 +
assets/js/slick.js | 3037 ++++++++++++++++++++
.../bootstrap/css/bootstrap.2.2.2.min.css | 782 -----
.../bootstrap/img/glyphicons-halflings-white.png | Bin 8777 -> 0 bytes
.../bootstrap/img/glyphicons-halflings.png | Bin 12799 -> 0 bytes
.../themes/custom-twitter/css/1.4.0/bootstrap.css | 356 ---
assets/themes/custom-twitter/css/style.css | 428 ---
atom.xml | 944 +++---
blog.html | 276 +-
categories.html | 288 +-
community.html | 286 +-
css/custom.css | 581 ++++
css/custom.css.map | 12 +
css/slick-theme.css | 186 ++
css/slick.css | 119 +
css/variables.scss | 3 +
download.html | 326 ++-
feed.xml | 2190 ++++++++++++++
images/community/alicloud.png | Bin 20301 -> 3461 bytes
images/community/amd.png | Bin 8823 -> 1287 bytes
images/community/arm.png | Bin 2050 -> 1401 bytes
images/community/aws.png | Bin 32934 -> 3365 bytes
images/community/edgecortix.png | Bin 94207 -> 3824 bytes
images/community/facebookopen.png | Bin 0 -> 6853 bytes
images/community/huawei.png | Bin 7913 -> 4222 bytes
images/community/intel.png | Bin 4489 -> 2843 bytes
images/community/itri_tw.png | Bin 0 -> 77552 bytes
images/community/microsoft.png | Bin 24164 -> 2158 bytes
images/community/nvidia.png | Bin 48816 -> 2408 bytes
images/community/oasislabs.png | Bin 37771 -> 3652 bytes
images/community/octoml.png | Bin 0 -> 2705 bytes
images/community/qualcommic.png | Bin 32799 -> 4370 bytes
images/community/ucberkeley.png | Bin 32071 -> 4101 bytes
images/community/ucla.png | Bin 45279 -> 26748 bytes
images/community/uwcse.png | Bin 19344 -> 4791 bytes
images/community/xilinx.png | Bin 12702 -> 2071 bytes
index.html | 533 +++-
rss.xml | 946 +++---
sitemap.txt | 6 +-
tags.html | 288 +-
vta.html | 288 +-
88 files changed, 13618 insertions(+), 7734 deletions(-)
diff --git a/.gitignore b/.gitignore
index 7aaaff4..cf6401d 100644
--- a/.gitignore
+++ b/.gitignore
@@ -5,3 +5,4 @@ website.tgz
*.bak
.jekyll-cache
docs.tgz
+Gemfile.lock
diff --git a/2017/08/17/tvm-release-announcement.html b/2017/08/17/tvm-release-announcement.html
index 2271f91..10bf6ca 100644
--- a/2017/08/17/tvm-release-announcement.html
+++ b/2017/08/17/tvm-release-announcement.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>TVM: An End to End IR Stack for Deploying Deep Learning Workloads on Hardware Platforms</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -284,37 +274,41 @@ that adopts the standard, such as MXNet, PyTorch, Caffe2 and tiny-dnn.</li>
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2017/08/22/Optimize-Deep-Learning-GPU-Operators-with-TVM-A-Depthwise-Convolution-Example.html b/2017/08/22/Optimize-Deep-Learning-GPU-Operators-with-TVM-A-Depthwise-Convolution-Example.html
index 0848819..ff81b88 100644
--- a/2017/08/22/Optimize-Deep-Learning-GPU-Operators-with-TVM-A-Depthwise-Convolution-Example.html
+++ b/2017/08/22/Optimize-Deep-Learning-GPU-Operators-with-TVM-A-Depthwise-Convolution-Example.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Optimize Deep Learning GPU Operators with TVM: A Depthwise Convolution Example</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -186,18 +176,18 @@ It’s an effective method to reduce the computation complexity of deep neural n
<p>In TVM, depthwise convolution can be declared as:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="c1"># padding stage
-</span><span class="n">PaddedInput</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">compute</span><span class="p">(</span>
+</span><span class="n">PaddedInput</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">compute</span><span class="p">(</span>
<span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="n">in_channel</span><span class="p">,</span> <span class="n">height_after_pad</span><span class="p">,</span> <span class="n">width_after_pad</span><span class="p">),</span>
- <span class="k">lambda</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">:</span> <span class="n">tvm</span><span class="o">.</span><span class="n">select</span><span class="p">(</span>
- <span class="n">tvm</span><span class="o">.</span><span class="nb">all</span><span class="p">(</span><span class="n">i</span> <span class="o">>=</span> <span class="n">pad_top</span><span class="p">,</span> <span class="n">i</span> <span class="o">-</span> <span class="n">pad_top</span> <span class="o"><</span> <span class="n">in_height</span><span class="p">,</span> <span class="n">j</span> <span class="o">>=</span> <span class="n">pad_left</span><span class="p">,</span [...]
- <span class="n">Input</span><span class="p">[</span><span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">i</span> <span class="o">-</span> <span class="n">pad_top</span><span class="p">,</span> <span class="n">j</span> <span class="o">-</span> <span class="n">pad_left</span><span class="p">],</span> <span class="n">tvm</span><span class="o">.</span><span class="n">const</span><span class="p">(</span><span class="mf">0.0 [...]
+ <span class="k">lambda</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">:</span> <span class="n">tvm</span><span class="p">.</span><span class="n">select</span><span class="p">(</span>
+ <span class="n">tvm</span><span class="p">.</span><span class="nb">all</span><span class="p">(</span><span class="n">i</span> <span class="o">>=</span> <span class="n">pad_top</span><span class="p">,</span> <span class="n">i</span> <span class="o">-</span> <span class="n">pad_top</span> <span class="o"><</span> <span class="n">in_height</span><span class="p">,</span> <span class="n">j</span> <span class="o">>=</span> <span class="n">pad_left</span><span class="p">,</span [...]
+ <span class="n">Input</span><span class="p">[</span><span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">i</span> <span class="o">-</span> <span class="n">pad_top</span><span class="p">,</span> <span class="n">j</span> <span class="o">-</span> <span class="n">pad_left</span><span class="p">],</span> <span class="n">tvm</span><span class="p">.</span><span class="n">const</span><span class="p">(</span><span class="mf">0.0 [...]
<span class="n">name</span><span class="o">=</span><span class="s">"PaddedInput"</span><span class="p">)</span>
<span class="c1"># depthconv stage
-</span><span class="n">di</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">filter_height</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'di'</span><span class="p">)</span>
-<span class="n">dj</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">filter_width</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'dj'</span><span class="p">)</span>
-<span class="n">Output</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">compute</span><span class="p">(</span>
+</span><span class="n">di</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">filter_height</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'di'</span><span class="p">)</span>
+<span class="n">dj</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">filter_width</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'dj'</span><span class="p">)</span>
+<span class="n">Output</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">compute</span><span class="p">(</span>
<span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="n">out_channel</span><span class="p">,</span> <span class="n">out_height</span><span class="p">,</span> <span class="n">out_width</span><span class="p">),</span>
- <span class="k">lambda</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">:</span> <span class="n">tvm</span><span class="o">.</span><span class="nb">sum</span><span class="p">(</span>
+ <span class="k">lambda</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">i</span><span class="p">,</span> <span class="n">j</span><span class="p">:</span> <span class="n">tvm</span><span class="p">.</span><span class="nb">sum</span><span class="p">(</span>
<span class="n">PaddedInput</span><span class="p">[</span><span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="o">/</span><span class="n">channel_multiplier</span><span class="p">,</span> <span class="n">i</span><span class="o">*</span><span class="n">stride_h</span> <span class="o">+</span> <span class="n">di</span><span class="p">,</span> <span class="n">j</span><span class="o">*</span><span class="n">stride_w</span> <span class="o">+</span> <sp [...]
<span class="n">axis</span><span class="o">=</span><span class="p">[</span><span class="n">di</span><span class="p">,</span> <span class="n">dj</span><span class="p">]),</span>
<span class="n">name</span><span class="o">=</span><span class="s">'DepthwiseConv2d'</span><span class="p">)</span>
@@ -250,21 +240,21 @@ To avoid bank conflicts, it’s better that successive threads access successive
<h3 id="compute-paddedinput-inline-to-save-memory-allocation">Compute PaddedInput Inline to Save Memory Allocation</h3>
<p>As we see from part 1, padding is declared explicitly as a separate stage. We compute it inline to avoid redundant memory allocation:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">s</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">create_schedule</span><span class="p">(</span><span class="n">Output</span><span class="o">.</span><span class="n">op</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">PaddedInput</span><span class="p">]</span><span class="o">.</span><span class="n">compute_inline</span><span class="p">()</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">s</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">create_schedule</span><span class="p">(</span><span class="n">Output</span><span class="p">.</span><span class="n">op</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">PaddedInput</span><span class="p">].</span><span class="n">compute_inline</span><span class="p">()</span>
</code></pre></div></div>
<h3 id="divide-one-large-channel-into-smaller-blocks">Divide One Large Channel into Smaller Blocks</h3>
<p>One straightforward schedule for depthwise convolution is that one cuda block takes care of one input channel and corresponding filters, loading them into shared memory and then computing:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">IS</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">cache_read</span><span class="p">(</span><span class="n">PaddedInput</span><span class="p">,</span> <span class="s">"shared"</span><span class="p">,</span> <span class="p">[</span><span class="n">DepthwiseConv2d</span><span class="p">])</span>
-<span class="n">FS</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">cache_read</span><span class="p">(</span><span class="n">Filter</span><span class="p">,</span> <span class="s">"shared"</span><span class="p">,</span> <span class="p">[</span><span class="n">DepthwiseConv2d</span><span class="p">])</span>
-<span class="n">block_y</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.y"</span><span class="p">)</span>
-<span class="n">block_x</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.x"</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">IS</span> <span class="o">=</span> <span class="n">s</span><span class="p">.</span><span class="n">cache_read</span><span class="p">(</span><span class="n">PaddedInput</span><span class="p">,</span> <span class="s">"shared"</span><span class="p">,</span> <span class="p">[</span><span class="n">DepthwiseConv2d</span><span class="p">])</span>
+<span class="n">FS</span> <span class="o">=</span> <span class="n">s</span><span class="p">.</span><span class="n">cache_read</span><span class="p">(</span><span class="n">Filter</span><span class="p">,</span> <span class="s">"shared"</span><span class="p">,</span> <span class="p">[</span><span class="n">DepthwiseConv2d</span><span class="p">])</span>
+<span class="n">block_y</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.y"</span><span class="p">)</span>
+<span class="n">block_x</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.x"</span><span class="p">)</span>
<span class="c1"># bind the dimension of batch (N in NCHW) with block_y
-</span><span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">Output</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">block_y</span><span class="p">)</span>
+</span><span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">Output</span><span class="p">.</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">block_y</span><span class="p">)</span>
<span class="c1"># bind the dimension of channel (C in NCHW) with block_x
-</span><span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">Output</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">block_x</span><span class="p">)</span>
+</span><span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">Output</span><span class="p">.</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">block_x</span><span class="p">)</span>
</code></pre></div></div>
<p>We test the average time cost of 1000 runs on GTX 1080, and compare with <a href="https://www.tensorflow.org/versions/r0.12/api_docs/python/nn/convolution#depthwise_conv2d">depthwise_conv2d in tensorflow</a>.
@@ -321,14 +311,14 @@ and one cuda block takes care of one 32 x 32 block:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">blocking_h</span> <span class="o">=</span> <span class="mi">32</span>
<span class="n">blocking_w</span> <span class="o">=</span> <span class="mi">32</span>
<span class="c1"># split the dimension of height (H in NCHW)
-</span><span class="n">bx1</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">Output</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <sp [...]
+</span><span class="n">bx1</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">Output</span><span class="p">.</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">factor</sp [...]
<span class="c1"># split the dimension of width (W in NCHW)
-</span><span class="n">bx2</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">Output</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <sp [...]
+</span><span class="n">bx2</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">Output</span><span class="p">.</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="n">factor</sp [...]
<span class="c1"># assign one 32 x 32 block to one cuda block
-</span><span class="n">by</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">fuse</span><span class="p">(</span><span class="n">Output</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">Output</span><span class="o">.</span>< [...]
-<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">by</span><span class="p">,</span> <span class="n">block_y</span><span class="p">)</span>
-<span class="n">bx</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">fuse</span><span class="p">(</span><span class="n">bx1</span><span class="p">,</span> <span class="n">bx2</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">bx</span><span class="p">,</span> <span class="n">block_x</span><span class="p">)</span>
+</span><span class="n">by</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">fuse</span><span class="p">(</span><span class="n">Output</span><span class="p">.</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">Output</span><span class="p">.</span><span class="n">op</span [...]
+<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">by</span><span class="p">,</span> <span class="n">block_y</span><span class="p">)</span>
+<span class="n">bx</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">fuse</span><span class="p">(</span><span class="n">bx1</span><span class="p">,</span> <span class="n">bx2</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">bx</span><span class="p">,</span> <span class="n">block_x</span><span class="p">)</span>
</code></pre></div></div>
<p>Here is the new result:</p>
@@ -366,16 +356,16 @@ and one cuda block takes care of one 32 x 32 block:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">num_thread_y</span> <span class="o">=</span> <span class="mi">8</span>
<span class="n">num_thread_x</span> <span class="o">=</span> <span class="mi">8</span>
-<span class="n">thread_y</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_thread_y</span><span class="p">),</span> <span class="s">"threadIdx.y"</span><span class="p">)</span>
-<span class="n">thread_x</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_thread_x</span><span class="p">),</span> <span class="s">"threadIdx.x"</span><span class="p">)</span>
-<span class="n">ty</span><span class="p">,</span> <span class="n">yi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">h_dim</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_thread_y</span><span class="p">)</span>
-<span class="n">tx</span><span class="p">,</span> <span class="n">xi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">w_dim</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_thread_x</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">reorder</span><span class="p">(</span><span class="n">ty</span><span class="p">,</span> <span class="n">tx</span><span class="p">,</span> <span class="n">yi</span><span class="p">,</span> <span class="n">xi</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">ty</span><span class="p">,</span> <span class="n">thread_y</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">tx</span><span class="p">,</span> <span class="n">thread_x</span><span class="p">)</span>
+<span class="n">thread_y</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_thread_y</span><span class="p">),</span> <span class="s">"threadIdx.y"</span><span class="p">)</span>
+<span class="n">thread_x</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_thread_x</span><span class="p">),</span> <span class="s">"threadIdx.x"</span><span class="p">)</span>
+<span class="n">ty</span><span class="p">,</span> <span class="n">yi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">h_dim</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_thread_y</span><span class="p">)</span>
+<span class="n">tx</span><span class="p">,</span> <span class="n">xi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">w_dim</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_thread_x</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">reorder</span><span class="p">(</span><span class="n">ty</span><span class="p">,</span> <span class="n">tx</span><span class="p">,</span> <span class="n">yi</span><span class="p">,</span> <span class="n">xi</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">ty</span><span class="p">,</span> <span class="n">thread_y</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">tx</span><span class="p">,</span> <span class="n">thread_x</span><span class="p">)</span>
</code></pre></div></div>
-<p>There are two parameters in the schedule: <code class="highlighter-rouge">num_thread_y</code> and <code class="highlighter-rouge">num_thread_x</code>. How to determine the optimal combination of them?
+<p>There are two parameters in the schedule: <code class="language-plaintext highlighter-rouge">num_thread_y</code> and <code class="language-plaintext highlighter-rouge">num_thread_x</code>. How to determine the optimal combination of them?
Well, let’s first do some experiments. Below is the result with Filter = [256, 1, 3, 3] and stride = [1, 1]:</p>
<table>
@@ -431,7 +421,7 @@ It has better data reuse than case 1’s 4x1 tile.</p>
<p>Case 3 is slower than case 2. It’s because in case 3, the workload per thread is too large and leads to much cost of local memory read.</p>
</li>
<li>
- <p>Case 4 is slower than case 3. It’s because <code class="highlighter-rouge">num_thread_x = 32</code> ensures no bank conflicts, while <code class="highlighter-rouge">num_thread_y = 32</code> doesn’t.</p>
+ <p>Case 4 is slower than case 3. It’s because <code class="language-plaintext highlighter-rouge">num_thread_x = 32</code> ensures no bank conflicts, while <code class="language-plaintext highlighter-rouge">num_thread_y = 32</code> doesn’t.</p>
</li>
</ul>
@@ -439,14 +429,14 @@ It has better data reuse than case 1’s 4x1 tile.</p>
<ul>
<li>Large tile is good for data reuse, but not good for local memory read.</li>
- <li>The influence of <code class="highlighter-rouge">num_thread_y</code> and <code class="highlighter-rouge">num_thread_x</code> on bank conflicts is asymmetric.</li>
- <li>To find the optimal combination of <code class="highlighter-rouge">num_thread_y</code> and <code class="highlighter-rouge">num_thread_x</code> is to achieve a balance of efficient shared memory access (avoid bank conflicts), data reuse, and local memory read.</li>
+ <li>The influence of <code class="language-plaintext highlighter-rouge">num_thread_y</code> and <code class="language-plaintext highlighter-rouge">num_thread_x</code> on bank conflicts is asymmetric.</li>
+ <li>To find the optimal combination of <code class="language-plaintext highlighter-rouge">num_thread_y</code> and <code class="language-plaintext highlighter-rouge">num_thread_x</code> is to achieve a balance of efficient shared memory access (avoid bank conflicts), data reuse, and local memory read.</li>
</ul>
<p>Pretty tricky. So, what exactly should we do to find the optimal combination? The answer is brute force search.
-We can pass <code class="highlighter-rouge">num_thread_y</code> and <code class="highlighter-rouge">num_thread_x</code> as arguments to the schedule function, and try all possible combinations to find the optimal one. This can be done easily in TVM:</p>
+We can pass <code class="language-plaintext highlighter-rouge">num_thread_y</code> and <code class="language-plaintext highlighter-rouge">num_thread_x</code> as arguments to the schedule function, and try all possible combinations to find the optimal one. This can be done easily in TVM:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">schedule_depthwise_conv2d</span><span class="p">(</span><span class="o">...</span><span class="p">,</span> <span class="n">num_thread_y</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span> <span class="n">num_thread_x</span><span class="o">=</span><span class="mi">8</span><span class="p">):</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">schedule_depthwise_conv2d</span><span class="p">(...,</span> <span class="n">num_thread_y</span><span class="o">=</span><span class="mi">8</span><span class="p">,</span> <span class="n">num_thread_x</span><span class="o">=</span><span class="mi">8</span><span class="p">):</span>
<span class="n">num_thread_y</span> <span class="o">=</span> <span class="n">num_thread_y</span>
<span class="n">num_thread_x</span> <span class="o">=</span> <span class="n">num_thread_x</span>
<span class="n">do_schedule_as_usual</span>
@@ -454,8 +444,8 @@ We can pass <code class="highlighter-rouge">num_thread_y</code> and <code class=
<span class="n">min_time_cost</span> <span class="o">=</span> <span class="n">inf</span>
<span class="k">for</span> <span class="n">num_thread_y</span><span class="p">,</span> <span class="n">num_thread_x</span> <span class="ow">in</span> <span class="n">all_possible_combinations</span><span class="p">:</span>
- <span class="n">schedule</span> <span class="o">=</span> <span class="n">schedule_depthwise_conv2d</span><span class="p">(</span><span class="o">...</span><span class="p">,</span> <span class="n">num_thread_y</span><span class="o">=</span><span class="n">num_thread_y</span><span class="p">,</span> <span class="n">num_thread_x</span><span class="o">=</span><span class="n">num_thread_x</span><span class="p">)</span>
- <span class="n">time_cost</span> <span class="o">=</span> <span class="n">test_depthwise_conv2d</span><span class="p">(</span><span class="o">...</span><span class="p">,</span> <span class="n">schedule</span><span class="p">)</span>
+ <span class="n">schedule</span> <span class="o">=</span> <span class="n">schedule_depthwise_conv2d</span><span class="p">(...,</span> <span class="n">num_thread_y</span><span class="o">=</span><span class="n">num_thread_y</span><span class="p">,</span> <span class="n">num_thread_x</span><span class="o">=</span><span class="n">num_thread_x</span><span class="p">)</span>
+ <span class="n">time_cost</span> <span class="o">=</span> <span class="n">test_depthwise_conv2d</span><span class="p">(...,</span> <span class="n">schedule</span><span class="p">)</span>
<span class="k">if</span> <span class="n">time_cost</span> <span class="o"><</span> <span class="n">min_time_cost</span><span class="p">:</span>
<span class="n">min_time_cost</span> <span class="o">=</span> <span class="n">time_cost</span>
<span class="n">optimal_combination</span> <span class="o">=</span> <span class="p">[</span><span class="n">num_thread_y</span><span class="p">,</span> <span class="n">num_thread_x</span><span class="p">]</span>
@@ -470,22 +460,22 @@ We can pass <code class="highlighter-rouge">num_thread_y</code> and <code class=
<span class="n">num_vthread_x</span> <span class="o">=</span> <span class="mi">2</span>
<span class="n">num_thread_y</span> <span class="o">=</span> <span class="mi">8</span>
<span class="n">num_thread_x</span> <span class="o">=</span> <span class="mi">8</span>
-<span class="n">thread_vy</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_vthread_y</span><span class="p">),</span> <span class="s">"vthread"</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s">"vy"</span><span class="p">)</span>
-<span class="n">thread_vx</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_vthread_x</span><span class="p">),</span> <span class="s">"vthread"</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s">"vx"</span><span class="p">)</span>
-<span class="n">thread_y</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_thread_y</span><span class="p">),</span> <span class="s">"threadIdx.y"</span><span class="p">)</span>
-<span class="n">thread_x</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_thread_x</span><span class="p">),</span> <span class="s">"threadIdx.x"</span><span class="p">)</span>
+<span class="n">thread_vy</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_vthread_y</span><span class="p">),</span> <span class="s">"vthread"</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s">"vy"</span><span class="p">)</span>
+<span class="n">thread_vx</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_vthread_x</span><span class="p">),</span> <span class="s">"vthread"</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s">"vx"</span><span class="p">)</span>
+<span class="n">thread_y</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_thread_y</span><span class="p">),</span> <span class="s">"threadIdx.y"</span><span class="p">)</span>
+<span class="n">thread_x</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">num_thread_x</span><span class="p">),</span> <span class="s">"threadIdx.x"</span><span class="p">)</span>
<span class="c1"># split the dimension of height (H in NCHW) twice
-</span><span class="n">tvy</span><span class="p">,</span> <span class="n">vyi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">h_dim</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_vthread_y</span><span class="p">)</span>
-<span class="n">ty</span><span class="p">,</span> <span class="n">yi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">vyi</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_thread_y</span><span class="p">)</span>
+</span><span class="n">tvy</span><span class="p">,</span> <span class="n">vyi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">h_dim</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_vthread_y</span><span class="p">)</span>
+<span class="n">ty</span><span class="p">,</span> <span class="n">yi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">vyi</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_thread_y</span><span class="p">)</span>
<span class="c1"># split the dimension of width (W in NCHW) twice
-</span><span class="n">tvx</span><span class="p">,</span> <span class="n">vxi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">w_dim</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_vthread_x</span><span class="p">)</span>
-<span class="n">tx</span><span class="p">,</span> <span class="n">xi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">vxi</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_thread_x</span><span class="p">)</span>
+</span><span class="n">tvx</span><span class="p">,</span> <span class="n">vxi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">w_dim</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_vthread_x</span><span class="p">)</span>
+<span class="n">tx</span><span class="p">,</span> <span class="n">xi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">vxi</span><span class="p">,</span> <span class="n">nparts</span><span class="o">=</span><span class="n">num_thread_x</span><span class="p">)</span>
<span class="c1"># bind thread and vthread respectively
-</span><span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">tvy</span><span class="p">,</span> <span class="n">thread_vy</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">tvx</span><span class="p">,</span> <span class="n">thread_vx</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">ty</span><span class="p">,</span> <span class="n">thread_y</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">tx</span><span class="p">,</span> <span class="n">thread_x</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">]</span><span class="o">.</span><span class="n">reorder</span><span class="p">(</span><span class="n">tvy</span><span class="p">,</span> <span class="n">tvx</span><span class="p">,</span> <span class="n">ty</span><span class="p">,</span> <span class="n">tx</span><span class="p">,</span> <span class="n">yi</span><span class="p">,</span> <span class="n">xi</span><span class="p">)</span>
+</span><span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">tvy</span><span class="p">,</span> <span class="n">thread_vy</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">tvx</span><span class="p">,</span> <span class="n">thread_vx</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">ty</span><span class="p">,</span> <span class="n">thread_y</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">tx</span><span class="p">,</span> <span class="n">thread_x</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">].</span><span class="n">reorder</span><span class="p">(</span><span class="n">tvy</span><span class="p">,</span> <span class="n">tvx</span><span class="p">,</span> <span class="n">ty</span><span class="p">,</span> <span class="n">tx</span><span class="p">,</span> <span class="n">yi</span><span class="p">,</span> <span class="n">xi</span><span class="p">)</span>
</code></pre></div></div>
<p>Let’s print the IR to see what vthread does:</p>
@@ -536,7 +526,7 @@ We can pass <code class="highlighter-rouge">num_thread_y</code> and <code class=
<span class="p">}</span>
</code></pre></div></div>
-<p>As we can see, when <code class="highlighter-rouge">num_vthread_y = 2</code> and <code class="highlighter-rouge">num_vthread_x = 2</code>, the 32 x 32 channel is divided into four sub-channels of 16 x 16.
+<p>As we can see, when <code class="language-plaintext highlighter-rouge">num_vthread_y = 2</code> and <code class="language-plaintext highlighter-rouge">num_vthread_x = 2</code>, the 32 x 32 channel is divided into four sub-channels of 16 x 16.
Each thread computes four output elements at a time, one element in one sub-channel.</p>
<p>Below is the result with Filter = [256, 1, 3, 3], stride = [1, 1], blocking_h = 32, blocking_w = 32:</p>
@@ -592,7 +582,7 @@ table th:nth-of-type(2) {
</tbody>
</table>
-<p>Case 2 is faster than case 1. It’s because in case 2 <code class="highlighter-rouge">num_thread_x=8</code> and <code class="highlighter-rouge">num_vthread_x=4</code> together ensures that consecutive threads access consecutive memory addresses,
+<p>Case 2 is faster than case 1. It’s because in case 2 <code class="language-plaintext highlighter-rouge">num_thread_x=8</code> and <code class="language-plaintext highlighter-rouge">num_vthread_x=4</code> together ensures that consecutive threads access consecutive memory addresses,
thus avoiding bank conflicts, as illustrated below (each color represents one thread’s workload):</p>
<p style="text-align: center"><img src="/images/depthconv_tutorial/vthread_and_strided_pattern.png" alt="image" width="90%" /></p>
@@ -656,17 +646,17 @@ vthread saves additional 5us.</p>
<p>One typical optimization we can do in deep learning is operator fusion, that computes multiple operators together in a single kernel without saving intermediate results back to global memory.
TVM supports that out of the box.</p>
-<p>Consider a common pattern in neural networks: <code class="highlighter-rouge">depthwise_conv2d</code> + <code class="highlighter-rouge">scale_shift</code> + <code class="highlighter-rouge">relu</code>. We can fuse the three operators into one, by slightly modifying the original schedule:</p>
+<p>Consider a common pattern in neural networks: <code class="language-plaintext highlighter-rouge">depthwise_conv2d</code> + <code class="language-plaintext highlighter-rouge">scale_shift</code> + <code class="language-plaintext highlighter-rouge">relu</code>. We can fuse the three operators into one, by slightly modifying the original schedule:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">DepthwiseConv2d</span> <span class="o">=</span> <span class="n">topi</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">depthwise_conv2d</span><span class="p">(</span><span class="n">Input</span><span class="p">,</span> <span class="n">Filter</span><span class="p">,</span> <span class="n">stride</span><span class="p">,</span> <span [...]
-<span class="n">ScaleShift</span> <span class="o">=</span> <span class="n">topi</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">scale_shift</span><span class="p">(</span><span class="n">DepthwiseConv2d</span><span class="p">,</span> <span class="n">Scale</span><span class="p">,</span> <span class="n">Shift</span><span class="p">)</span>
-<span class="n">Relu</span> <span class="o">=</span> <span class="n">topi</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="n">ScaleShift</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">DepthwiseConv2d</span> <span class="o">=</span> <span class="n">topi</span><span class="p">.</span><span class="n">nn</span><span class="p">.</span><span class="n">depthwise_conv2d</span><span class="p">(</span><span class="n">Input</span><span class="p">,</span> <span class="n">Filter</span><span class="p">,</span> <span class="n">stride</span><span class="p">,</span> <span [...]
+<span class="n">ScaleShift</span> <span class="o">=</span> <span class="n">topi</span><span class="p">.</span><span class="n">nn</span><span class="p">.</span><span class="n">scale_shift</span><span class="p">(</span><span class="n">DepthwiseConv2d</span><span class="p">,</span> <span class="n">Scale</span><span class="p">,</span> <span class="n">Shift</span><span class="p">)</span>
+<span class="n">Relu</span> <span class="o">=</span> <span class="n">topi</span><span class="p">.</span><span class="n">nn</span><span class="p">.</span><span class="n">relu</span><span class="p">(</span><span class="n">ScaleShift</span><span class="p">)</span>
<span class="n">Output</span> <span class="o">=</span> <span class="n">Relu</span> <span class="c1"># is no longer DepthwiseConv2d
-</span><span class="n">s</span><span class="p">[</span><span class="n">ScaleShift</span><span class="p">]</span><span class="o">.</span><span class="n">compute_inline</span><span class="p">()</span> <span class="c1"># this line fuses ScaleShift, explicitly
-</span><span class="n">s</span><span class="p">[</span><span class="n">DepthwiseConv2d</span><span class="p">]</span><span class="o">.</span><span class="n">set_scope</span><span class="p">(</span><span class="s">"local"</span><span class="p">)</span> <span class="c1"># this line fuses DepthwiseConv2d, implicitly
+</span><span class="n">s</span><span class="p">[</span><span class="n">ScaleShift</span><span class="p">].</span><span class="n">compute_inline</span><span class="p">()</span> <span class="c1"># this line fuses ScaleShift, explicitly
+</span><span class="n">s</span><span class="p">[</span><span class="n">DepthwiseConv2d</span><span class="p">].</span><span class="n">set_scope</span><span class="p">(</span><span class="s">"local"</span><span class="p">)</span> <span class="c1"># this line fuses DepthwiseConv2d, implicitly
</span><span class="n">schedule</span><span class="p">(</span><span class="n">Output</span><span class="p">)</span> <span class="c1"># schedule for Output the same way we schedule for DepthwiseConv2d as discussed above
-</span><span class="n">s</span><span class="p">[</span><span class="n">DepthwiseConv2d</span><span class="p">]</span><span class="o">.</span><span class="n">compute_at</span><span class="p">(</span><span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">],</span> <span class="n">tx</span><span class="p">)</span> <span class="c1"># tx is the inner most axis, bound to threadIdx.x
+</span><span class="n">s</span><span class="p">[</span><span class="n">DepthwiseConv2d</span><span class="p">].</span><span class="n">compute_at</span><span class="p">(</span><span class="n">s</span><span class="p">[</span><span class="n">Output</span><span class="p">],</span> <span class="n">tx</span><span class="p">)</span> <span class="c1"># tx is the inner most axis, bound to threadIdx.x
</span></code></pre></div></div>
<p>It generates IR like this:</p>
@@ -699,14 +689,14 @@ TVM supports that out of the box.</p>
<span class="p">}</span>
</code></pre></div></div>
-<p>As we can see, each thread computes <code class="highlighter-rouge">scale_shift</code> and <code class="highlighter-rouge">relu</code> before writing the result of <code class="highlighter-rouge">depthwise_conv2d</code> to global memory. The fused operator is as fast as single <code class="highlighter-rouge">depthwise_conv2d</code>.
+<p>As we can see, each thread computes <code class="language-plaintext highlighter-rouge">scale_shift</code> and <code class="language-plaintext highlighter-rouge">relu</code> before writing the result of <code class="language-plaintext highlighter-rouge">depthwise_conv2d</code> to global memory. The fused operator is as fast as single <code class="language-plaintext highlighter-rouge">depthwise_conv2d</code>.
Below is the result with Input = [1, 256, 96, 96], Filter = [256, 1, 3, 3], stride = [1, 1], padding = ‘SAME’:</p>
<ul>
- <li>tf-1.2 <code class="highlighter-rouge">depthwise_conv2d</code>: 251.6 us</li>
- <li>tf-1.2 <code class="highlighter-rouge">depthwise_conv2d</code> + <code class="highlighter-rouge">scale_shift</code> + <code class="highlighter-rouge">relu</code> (separate): 419.9 us</li>
- <li>TVM <code class="highlighter-rouge">depthwise_conv2d</code>: 90.9 us</li>
- <li>TVM <code class="highlighter-rouge">depthwise_conv2d + scale_shift + relu</code> (fused): 91.5 us</li>
+ <li>tf-1.2 <code class="language-plaintext highlighter-rouge">depthwise_conv2d</code>: 251.6 us</li>
+ <li>tf-1.2 <code class="language-plaintext highlighter-rouge">depthwise_conv2d</code> + <code class="language-plaintext highlighter-rouge">scale_shift</code> + <code class="language-plaintext highlighter-rouge">relu</code> (separate): 419.9 us</li>
+ <li>TVM <code class="language-plaintext highlighter-rouge">depthwise_conv2d</code>: 90.9 us</li>
+ <li>TVM <code class="language-plaintext highlighter-rouge">depthwise_conv2d + scale_shift + relu</code> (fused): 91.5 us</li>
</ul>
<p>The advantage of operator fusion is obvious.</p>
@@ -739,37 +729,41 @@ He is experiencing a gap year after obtaining a bachelor’s degree in electrica
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2017/10/06/nnvm-compiler-announcement.html b/2017/10/06/nnvm-compiler-announcement.html
index 792bc1b..a1a73d0 100644
--- a/2017/10/06/nnvm-compiler-announcement.html
+++ b/2017/10/06/nnvm-compiler-announcement.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>NNVM Compiler: Open Compiler for AI Frameworks</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -239,37 +229,41 @@ We also learns from Halide when implementing the lowering pipeline in TVM.</li>
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2017/10/30/Bringing-AMDGPUs-to-TVM-Stack-and-NNVM-Compiler-with-ROCm.html b/2017/10/30/Bringing-AMDGPUs-to-TVM-Stack-and-NNVM-Compiler-with-ROCm.html
index 07f0cb6..cf1e7d6 100644
--- a/2017/10/30/Bringing-AMDGPUs-to-TVM-Stack-and-NNVM-Compiler-with-ROCm.html
+++ b/2017/10/30/Bringing-AMDGPUs-to-TVM-Stack-and-NNVM-Compiler-with-ROCm.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Bringing AMDGPUs to TVM Stack and NNVM Compiler with ROCm</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -187,7 +177,7 @@
<ul>
<li>Loads Resnet 50 model from <a href="https://mxnet.incubator.apache.org/versions/master/api/python/gluon/model_zoo.html">the Gluon model zoo</a></li>
- <li>Converts Gluon Resnet 50 model to NNVM graph format, using <code class="highlighter-rouge">nnvm.frontend.from_mxnet (...)</code></li>
+ <li>Converts Gluon Resnet 50 model to NNVM graph format, using <code class="language-plaintext highlighter-rouge">nnvm.frontend.from_mxnet (...)</code></li>
<li>Compiles and executes the graph with ROCm backend</li>
</ul>
@@ -204,7 +194,7 @@ TVM prediction top-1: 282 tiger cat</code></pre></figure>
<p>The script <a href="https://github.com/ROCmSoftwarePlatform/nnvm-rocm/blob/master/advanced_superres_onnx.py">advanced_superres_onnx.py</a> gives an example of loading a model trained with PyTorch. The model is stored in the <a href="https://onnx.ai/">ONNX</a> format. In this example, our network takes an low resolution image as input, and outputs a 4x high resolution image. We refer the details of a problem setup and the network architecture to <a href="https://arxiv.org/abs/1609.0480 [...]
-<p>In order to use models in the ONNX format with NNVM, we first use <a href="https://github.com/onnx/onnx">the ONNX library</a> to load the ONNX model into the Protocol buffer object. We can then use <code class="highlighter-rouge">nnvm.frontend.from_onnx(...)</code> to obtain an equivalent NNVM graph. With a NNVM graph in hand, we can follow the generic workflow of compilation and graph execution outlined above.</p>
+<p>In order to use models in the ONNX format with NNVM, we first use <a href="https://github.com/onnx/onnx">the ONNX library</a> to load the ONNX model into the Protocol buffer object. We can then use <code class="language-plaintext highlighter-rouge">nnvm.frontend.from_onnx(...)</code> to obtain an equivalent NNVM graph. With a NNVM graph in hand, we can follow the generic workflow of compilation and graph execution outlined above.</p>
<p style="text-align: center"><img src="/images/rocm/butterfly.png" alt="image" /></p>
@@ -229,46 +219,46 @@ We are starting to look at performance optimization and we expect more improveme
<span class="kn">import</span> <span class="nn">tvm</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="n">np</span>
-<span class="n">n</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">var</span><span class="p">(</span><span class="s">"n"</span><span class="p">)</span>
-<span class="n">A</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">n</span><span class="p">,),</span> <span class="n">name</span><span class="o">=</span><span class="s">'A'</span><span class="p">)</span>
-<span class="n">B</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">n</span><span class="p">,),</span> <span class="n">name</span><span class="o">=</span><span class="s">'B'</span><span class="p">)</span>
-<span class="n">C</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">compute</span><span class="p">(</span><span class="n">A</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">i</span><span class="p">:</span> <span class="n">A</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">+</span> <span class="n">B</span><span class= [...]
-<span class="n">s</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">create_schedule</span><span class="p">(</span><span class="n">C</span><span class="o">.</span><span class="n">op</span><span class="p">)</span>
-<span class="n">bx</span><span class="p">,</span> <span class="n">tx</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">C</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">fact [...]
-<span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">bx</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.x"</span><span class="p">))</span>
-<span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">tx</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"threadIdx.x"</span><span class="p">))</span></code></pre></figure>
+<span class="n">n</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">var</span><span class="p">(</span><span class="s">"n"</span><span class="p">)</span>
+<span class="n">A</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">n</span><span class="p">,),</span> <span class="n">name</span><span class="o">=</span><span class="s">'A'</span><span class="p">)</span>
+<span class="n">B</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">n</span><span class="p">,),</span> <span class="n">name</span><span class="o">=</span><span class="s">'B'</span><span class="p">)</span>
+<span class="n">C</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">compute</span><span class="p">(</span><span class="n">A</span><span class="p">.</span><span class="n">shape</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">i</span><span class="p">:</span> <span class="n">A</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">+</span> <span class="n">B</span><span class= [...]
+<span class="n">s</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">create_schedule</span><span class="p">(</span><span class="n">C</span><span class="p">.</span><span class="n">op</span><span class="p">)</span>
+<span class="n">bx</span><span class="p">,</span> <span class="n">tx</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">C</span><span class="p">.</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">factor</span><span class="o [...]
+<span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">bx</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.x"</span><span class="p">))</span>
+<span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">tx</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"threadIdx.x"</span><span class="p">))</span></code></pre></figure>
<p>Next, to use ROCm backend we build our kernel under “rocm” target. This will cause TVM to use our new code generator. We also need a runtime context for ROCm backend.</p>
<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="n">target</span> <span class="o">=</span> <span class="s">"rocm"</span>
-<span class="n">fadd_rocm</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">A</span><span class="p">,</span> <span class="n">B</span><span class="p">,</span> <span class="n">C</span><span class="p">],</span> <span class="n">target</span><span class="p">,</span> <span class="n">target_host</span><span class="o">=</span [...]
-<span class="n">ctx</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">rocm</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span></code></pre></figure>
+<span class="n">fadd_rocm</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">A</span><span class="p">,</span> <span class="n">B</span><span class="p">,</span> <span class="n">C</span><span class="p">],</span> <span class="n">target</span><span class="p">,</span> <span class="n">target_host</span><span class="o">=</span [...]
+<span class="n">ctx</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">rocm</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span></code></pre></figure>
<p>After building the kernel and setting up a runtime context, we can launch our vector add kernel.</p>
<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="n">n</span> <span class="o">=</span> <span class="mi">1024</span>
-<span class="n">a</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">n</span><span class="p">)</span><span class="o">.</span><span class= [...]
-<span class="n">b</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">n</span><span class="p">)</span><span class="o">.</span><span class= [...]
-<span class="n">c</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">C</span><span class="o">.</span><span class="n">dtype</span><span class=" [...]
+<span class="n">a</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="p">.</span><span class="n">random</span><span class="p">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">n</span><span class="p">).</span><span class="n">astype</span><span [...]
+<span class="n">b</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="p">.</span><span class="n">random</span><span class="p">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="n">n</span><span class="p">).</span><span class="n">astype</span><span [...]
+<span class="n">c</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="p">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">C</span><span class="p">.</span><span class="n">dtype</span><span class=" [...]
<span class="n">fadd_rocm</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span>
-<span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">(),</span> <span class="n">a</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span> <span class="o">+</span> <span class="n">b</span><span class="o">.</span><span class="n">asnumpy</span><span class="p" [...]
+<span class="n">np</span><span class="p">.</span><span class="n">testing</span><span class="p">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">c</span><span class="p">.</span><span class="n">asnumpy</span><span class="p">(),</span> <span class="n">a</span><span class="p">.</span><span class="n">asnumpy</span><span class="p">()</span> <span class="o">+</span> <span class="n">b</span><span class="p">.</span><span class="n">asnumpy</span><span class="p" [...]
<p>We can view LLVM IR that TVM generates in the following way:</p>
-<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="n">dev_module</span> <span class="o">=</span> <span class="n">fadd_rocm</span><span class="o">.</span><span class="n">imported_modules</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
-<span class="k">print</span><span class="p">(</span><span class="n">dev_module</span><span class="o">.</span><span class="n">get_source</span><span class="p">(</span><span class="s">"llvm"</span><span class="p">))</span></code></pre></figure>
+<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="n">dev_module</span> <span class="o">=</span> <span class="n">fadd_rocm</span><span class="p">.</span><span class="n">imported_modules</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
+<span class="k">print</span><span class="p">(</span><span class="n">dev_module</span><span class="p">.</span><span class="n">get_source</span><span class="p">(</span><span class="s">"llvm"</span><span class="p">))</span></code></pre></figure>
<p>You should see something like this:</p>
<figure class="highlight"><pre><code class="language-llvm" data-lang="llvm"><span class="c1">; ModuleID = 'myadd__kernel0'</span>
-<span class="err">source_filename</span> <span class="p">=</span> <span class="s">"myadd__kernel0"</span>
+<span class="k">source_filename</span> <span class="p">=</span> <span class="s">"myadd__kernel0"</span>
<span class="k">target</span> <span class="k">datalayout</span> <span class="p">=</span> <span class="s">"e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"</span>
<span class="k">target</span> <span class="k">triple</span> <span class="p">=</span> <span class="s">"amdgcn-amd-amdhsa-hcc"</span>
<span class="c1">; Function Attrs: nounwind</span>
-<span class="k">define</span> <span class="k">dllexport</span> <span class="err">amdgpu_kernel</span> <span class="kt">void</span> <span class="vg">@myadd__kernel0</span><span class="p">(</span><span class="kt">float</span> <span class="k">addrspace</span><span class="p">(</span><span class="m">1</span><span class="p">)*</span> <span class="k">noalias</span> <span class="k">nocapture</span><span class="p">,</span> <span class="kt">float</span> <span class="k">addrspace</span><span class= [...]
+<span class="k">define</span> <span class="k">dllexport</span> <span class="k">amdgpu_kernel</span> <span class="kt">void</span> <span class="vg">@myadd__kernel0</span><span class="p">(</span><span class="kt">float</span> <span class="k">addrspace</span><span class="p">(</span><span class="m">1</span><span class="p">)*</span> <span class="k">noalias</span> <span class="k">nocapture</span><span class="p">,</span> <span class="kt">float</span> <span class="k">addrspace</span><span class="p [...]
<span class="nl">entry:</span>
<span class="nv">%4</span> <span class="p">=</span> <span class="k">tail</span> <span class="k">call</span> <span class="kt">i32</span> <span class="vg">@llvm.amdgcn.workgroup.id.x</span><span class="p">()</span>
<span class="nv">%5</span> <span class="p">=</span> <span class="k">tail</span> <span class="k">call</span> <span class="kt">i32</span> <span class="vg">@llvm.amdgcn.workitem.id.x</span><span class="p">()</span>
@@ -312,7 +302,7 @@ We are starting to look at performance optimization and we expect more improveme
<p>We can also view GPU assembly that ROCm backend generates. This is the real code that runs on your GPU.</p>
-<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="k">print</span><span class="p">(</span><span class="n">dev_module</span><span class="o">.</span><span class="n">get_source</span><span class="p">(</span><span class="s">"asm"</span><span class="p">))</span></code></pre></figure>
+<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="k">print</span><span class="p">(</span><span class="n">dev_module</span><span class="p">.</span><span class="n">get_source</span><span class="p">(</span><span class="s">"asm"</span><span class="p">))</span></code></pre></figure>
<p>The assembly should look something like this, omitting unnecessary details:</p>
@@ -382,37 +372,41 @@ BB0_6:
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2017/11/08/android-rpc-introduction.html b/2017/11/08/android-rpc-introduction.html
index f4b581f..cc55203 100644
--- a/2017/11/08/android-rpc-introduction.html
+++ b/2017/11/08/android-rpc-introduction.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Remote Profile and Test Deep Learning Cross Compilation on Mobile Phones with TVM RPC</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -185,7 +175,7 @@ In order to optimize a computation task, one has to edit the code on the develop
<h2 id="run-tvm-app-on-android-phone">Run TVM APP on Android Phone</h2>
-<p>You can find Android RPC APP in <a href="https://github.com/dmlc/tvm/tree/master/apps/android_rpc">apps/android_rpc</a>. Please follow the instruction to build for your Android device. Once the APK is built, sign it using <code class="highlighter-rouge">apps/android_rpc/dev_tools</code> and install it on the phone. The APP looks like:</p>
+<p>You can find Android RPC APP in <a href="https://github.com/dmlc/tvm/tree/master/apps/android_rpc">apps/android_rpc</a>. Please follow the instruction to build for your Android device. Once the APK is built, sign it using <code class="language-plaintext highlighter-rouge">apps/android_rpc/dev_tools</code> and install it on the phone. The APP looks like:</p>
<p style="text-align: center"><img src="/images/android_rpc/app.png" alt="image" width="25%" />
<img src="/images/android_rpc/app_error.png" alt="image" width="25%" /></p>
@@ -200,17 +190,17 @@ In order to optimize a computation task, one has to edit the code on the develop
<p>Now we can connect to the proxy server from the laptop:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="kn">from</span> <span class="nn">tvm.contrib</span> <span class="kn">import</span> <span class="n">rpc</span>
-<span class="n">remote</span> <span class="o">=</span> <span class="n">rpc</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span><span class="s">"0.0.0.0"</span><span class="p">,</span> <span class="mi">9090</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="s">"android"</span><span class="p">)</span>
+<span class="n">remote</span> <span class="o">=</span> <span class="n">rpc</span><span class="p">.</span><span class="n">connect</span><span class="p">(</span><span class="s">"0.0.0.0"</span><span class="p">,</span> <span class="mi">9090</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="s">"android"</span><span class="p">)</span>
</code></pre></div></div>
-<p>This will give us a handler <code class="highlighter-rouge">remote</code> which we can use to communicate with the mobile phone. For instance, the following lines create a 1024x1024 matrix on phone’s GPU:</p>
+<p>This will give us a handler <code class="language-plaintext highlighter-rouge">remote</code> which we can use to communicate with the mobile phone. For instance, the following lines create a 1024x1024 matrix on phone’s GPU:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">A</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span>
- <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="mi">1024</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">dtype</span><span class="p">),</span>
- <span class="n">ctx</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">cl</span><span class="p">(</span><span class="mi">0</span><span class="p">))</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">A</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span>
+ <span class="n">np</span><span class="p">.</span><span class="n">random</span><span class="p">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="mi">1024</span><span class="p">)).</span><span class="n">astype</span><span class="p">(</span><span class="n">dtype</span><span class="p">),</span>
+ <span class="n">ctx</span> <span class="o">=</span> <span class="n">remote</span><span class="p">.</span><span class="n">cl</span><span class="p">(</span><span class="mi">0</span><span class="p">))</span>
</code></pre></div></div>
-<p>When <code class="highlighter-rouge">A.asnumpy()</code> is called from the laptop, the matrix <code class="highlighter-rouge">A </code>will be copied to phone’s RAM and then transfer to the laptop through the proxy server. The TVM RPC interface is transparent to users.</p>
+<p>When <code class="language-plaintext highlighter-rouge">A.asnumpy()</code> is called from the laptop, the matrix <code class="language-plaintext highlighter-rouge">A </code>will be copied to phone’s RAM and then transfer to the laptop through the proxy server. The TVM RPC interface is transparent to users.</p>
<h2 id="gemm-matrix-multiplication-on-the-phone">GEMM (Matrix Multiplication) on the Phone</h2>
@@ -218,34 +208,34 @@ In order to optimize a computation task, one has to edit the code on the develop
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="kn">import</span> <span class="nn">tvm</span>
<span class="k">def</span> <span class="nf">gemm</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">bn</span><span class="p">):</span>
- <span class="n">A</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'A'</span><span class="p">)</span>
- <span class="n">B</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'B'</span><span class="p">)</span>
- <span class="n">k</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'k'</span><span class="p">)</span>
+ <span class="n">A</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'A'</span><span class="p">)</span>
+ <span class="n">B</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'B'</span><span class="p">)</span>
+ <span class="n">k</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'k'</span><span class="p">)</span>
- <span class="n">C</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">compute</span><span class="p">(</span>
+ <span class="n">C</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">compute</span><span class="p">(</span>
<span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span>
- <span class="k">lambda</span> <span class="n">ii</span><span class="p">,</span> <span class="n">jj</span><span class="p">:</span> <span class="n">tvm</span><span class="o">.</span><span class="nb">sum</span><span class="p">(</span><span class="n">A</span><span class="p">[</span><span class="n">ii</span><span class="p">,</span> <span class="n">k</span><span class="p">]</span> <span class="o">*</span> <span class="n">B</span><span class="p">[</span><span class="n">k</span><span cla [...]
+ <span class="k">lambda</span> <span class="n">ii</span><span class="p">,</span> <span class="n">jj</span><span class="p">:</span> <span class="n">tvm</span><span class="p">.</span><span class="nb">sum</span><span class="p">(</span><span class="n">A</span><span class="p">[</span><span class="n">ii</span><span class="p">,</span> <span class="n">k</span><span class="p">]</span> <span class="o">*</span> <span class="n">B</span><span class="p">[</span><span class="n">k</span><span cla [...]
<span class="n">name</span><span class="o">=</span><span class="s">'C'</span><span class="p">)</span>
- <span class="n">s</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">create_schedule</span><span class="p">(</span><span class="n">C</span><span class="o">.</span><span class="n">op</span><span class="p">)</span>
+ <span class="n">s</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">create_schedule</span><span class="p">(</span><span class="n">C</span><span class="p">.</span><span class="n">op</span><span class="p">)</span>
- <span class="n">block_x</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.x"</span><span class="p">)</span>
- <span class="n">thread_x</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"threadIdx.x"</span><span class="p">)</span>
+ <span class="n">block_x</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.x"</span><span class="p">)</span>
+ <span class="n">thread_x</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"threadIdx.x"</span><span class="p">)</span>
- <span class="n">bo</span><span class="p">,</span> <span class="n">bi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">C</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n"> [...]
- <span class="n">to</span><span class="p">,</span> <span class="n">ti</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">C</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n"> [...]
- <span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">bi</span><span class="p">,</span> <span class="n">block_x</span><span class="p">)</span>
- <span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">ti</span><span class="p">,</span> <span class="n">thread_x</span><span class="p">)</span>
+ <span class="n">bo</span><span class="p">,</span> <span class="n">bi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">C</span><span class="p">.</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">factor</span><span clas [...]
+ <span class="n">to</span><span class="p">,</span> <span class="n">ti</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">C</span><span class="p">.</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">factor</span><span clas [...]
+ <span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">bi</span><span class="p">,</span> <span class="n">block_x</span><span class="p">)</span>
+ <span class="n">s</span><span class="p">[</span><span class="n">C</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">ti</span><span class="p">,</span> <span class="n">thread_x</span><span class="p">)</span>
- <span class="k">print</span><span class="p">(</span><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">A</span><span class="p">,</span> <span class="n">B</span><span class="p">,</span> <span class="n">C</span><span class="p">],</span> <span class="n">simple_mode</span><span class="o">=</span><span class="bp">True</span><span class="p">))</span>
+ <span class="k">print</span><span class="p">(</span><span class="n">tvm</span><span class="p">.</span><span class="n">lower</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">A</span><span class="p">,</span> <span class="n">B</span><span class="p">,</span> <span class="n">C</span><span class="p">],</span> <span class="n">simple_mode</span><span class="o">=</span><span class="bp">True</span><span class="p">))</span>
- <span class="k">return</span> <span class="n">tvm</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">A</span><span class="p">,</span> <span class="n">B</span><span class="p">,</span> <span class="n">C</span><span class="p">],</span>
+ <span class="k">return</span> <span class="n">tvm</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">A</span><span class="p">,</span> <span class="n">B</span><span class="p">,</span> <span class="n">C</span><span class="p">],</span>
<span class="s">"opencl"</span><span class="p">,</span>
<span class="n">target_host</span><span class="o">=</span><span class="s">"llvm -target=arm64-linux-android"</span><span class="p">,</span>
<span class="n">name</span><span class="o">=</span><span class="s">"gemm_gpu"</span><span class="p">)</span>
</code></pre></div></div>
-<p>There’s nothing special except the last line. Here we set the target to ‘opencl’ since this is the computation language which our Mali GPU supports. Note that we set <code class="highlighter-rouge">target_host</code> to ‘<code class="highlighter-rouge">llvm -target=arm64-linux-android</code>’, it depends on what architecture your Android Phone is. We tested on Samsung Galaxy S6 Edge, which has a Mali-T760 GPU. Here is the CPU info for this phone,</p>
+<p>There’s nothing special except the last line. Here we set the target to ‘opencl’ since this is the computation language which our Mali GPU supports. Note that we set <code class="language-plaintext highlighter-rouge">target_host</code> to ‘<code class="language-plaintext highlighter-rouge">llvm -target=arm64-linux-android</code>’, it depends on what architecture your Android Phone is. We tested on Samsung Galaxy S6 Edge, which has a Mali-T760 GPU. Here is the CPU info for this phone,</p>
<div class="language-bash highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="nv">$ </span>adb shell
shell@zenltechn:/ <span class="nv">$ </span><span class="nb">cat</span> /proc/cpuinfo
@@ -270,17 +260,17 @@ Hardware : SAMSUNG Exynos7420
<p>Please refer to <a href="https://clang.llvm.org/docs/CrossCompilation.html#target-triple">target triple</a> to learn the compile options for LLVM.</p>
-<p>We use <code class="highlighter-rouge">tvm.contrib.ndk</code> to build the shared library for the Android system,</p>
+<p>We use <code class="language-plaintext highlighter-rouge">tvm.contrib.ndk</code> to build the shared library for the Android system,</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="kn">from</span> <span class="nn">tvm.contrib</span> <span class="kn">import</span> <span class="n">rpc</span><span class="p">,</span> <span class="n">util</span><span class="p">,</span> <span class="n">ndk</span>
<span class="n">N</span> <span class="o">=</span> <span class="mi">1024</span>
<span class="n">f</span> <span class="o">=</span> <span class="n">gemm</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">bn</span> <span class="o">=</span> <span class="mi">256</span><span class="p">)</span>
-<span class="n">temp</span> <span class="o">=</span> <span class="n">util</span><span class="o">.</span><span class="n">tempdir</span><span class="p">()</span>
-<span class="n">path_dso</span> <span class="o">=</span> <span class="n">temp</span><span class="o">.</span><span class="n">relpath</span><span class="p">(</span><span class="s">"gemm_gpu.so"</span><span class="p">)</span>
-<span class="n">f</span><span class="o">.</span><span class="n">export_library</span><span class="p">(</span><span class="n">path_dso</span><span class="p">,</span> <span class="n">ndk</span><span class="o">.</span><span class="n">create_shared</span><span class="p">)</span>
+<span class="n">temp</span> <span class="o">=</span> <span class="n">util</span><span class="p">.</span><span class="n">tempdir</span><span class="p">()</span>
+<span class="n">path_dso</span> <span class="o">=</span> <span class="n">temp</span><span class="p">.</span><span class="n">relpath</span><span class="p">(</span><span class="s">"gemm_gpu.so"</span><span class="p">)</span>
+<span class="n">f</span><span class="p">.</span><span class="n">export_library</span><span class="p">(</span><span class="n">path_dso</span><span class="p">,</span> <span class="n">ndk</span><span class="p">.</span><span class="n">create_shared</span><span class="p">)</span>
</code></pre></div></div>
-<p><code class="highlighter-rouge">ndk.create_shared</code> reads the environment variable <code class="highlighter-rouge">TVM_NDK_CC</code> to find the compiler & linker for the Android device. We can easily use NDK to generate standalone toolchain for our device. For example, the following commands generate standalone compilers and linkers for ARM64 Android devices.</p>
+<p><code class="language-plaintext highlighter-rouge">ndk.create_shared</code> reads the environment variable <code class="language-plaintext highlighter-rouge">TVM_NDK_CC</code> to find the compiler & linker for the Android device. We can easily use NDK to generate standalone toolchain for our device. For example, the following commands generate standalone compilers and linkers for ARM64 Android devices.</p>
<div class="language-bash highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="nb">cd</span> /opt/android-ndk/build/tools/
./make-standalone-toolchain.sh <span class="nt">--platform</span><span class="o">=</span>android-24 <span class="nt">--use-llvm</span> <span class="nt">--arch</span><span class="o">=</span>arm64 <span class="nt">--install-dir</span><span class="o">=</span>/opt/android-toolchain-arm64
@@ -288,34 +278,34 @@ Hardware : SAMSUNG Exynos7420
<p>If everything goes right, we’ve got a shared library ‘gemm_gpu.so’. Now let’s upload it to the mobile phone, make the phone load the module and get a remote handler,</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">remote</span> <span class="o">=</span> <span class="n">rpc</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span><span class="s">"0.0.0.0"</span><span class="p">,</span> <span class="mi">9090</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="s">"android"</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">remote</span> <span class="o">=</span> <span class="n">rpc</span><span class="p">.</span><span class="n">connect</span><span class="p">(</span><span class="s">"0.0.0.0"</span><span class="p">,</span> <span class="mi">9090</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="s">"android"</span><span class="p">)</span>
-<span class="n">remote</span><span class="o">.</span><span class="n">upload</span><span class="p">(</span><span class="n">path_dso</span><span class="p">)</span>
-<span class="n">f</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">load_module</span><span class="p">(</span><span class="s">"gemm_gpu.so"</span><span class="p">)</span>
+<span class="n">remote</span><span class="p">.</span><span class="n">upload</span><span class="p">(</span><span class="n">path_dso</span><span class="p">)</span>
+<span class="n">f</span> <span class="o">=</span> <span class="n">remote</span><span class="p">.</span><span class="n">load_module</span><span class="p">(</span><span class="s">"gemm_gpu.so"</span><span class="p">)</span>
</code></pre></div></div>
<p>Create the remote arrays and print the running time,</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">ctx</span> <span class="o">=</span> <span class="n">remote</span><span class="o">.</span><span class="n">cl</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">ctx</span> <span class="o">=</span> <span class="n">remote</span><span class="p">.</span><span class="n">cl</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="n">np</span>
-<span class="n">a_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s">"float32"</span>< [...]
-<span class="n">b_np</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">))</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s">"float32"</span>< [...]
+<span class="n">a_np</span> <span class="o">=</span> <span class="n">np</span><span class="p">.</span><span class="n">random</span><span class="p">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">)).</span><span class="n">astype</span><span class="p">(</span><span class="s">"float32"</span><span class="p">)</span>
+<span class="n">b_np</span> <span class="o">=</span> <span class="n">np</span><span class="p">.</span><span class="n">random</span><span class="p">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">)).</span><span class="n">astype</span><span class="p">(</span><span class="s">"float32"</span><span class="p">)</span>
-<span class="n">a</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">a_np</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
-<span class="n">b</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">b_np</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
-<span class="n">c</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="s">"float32"</span><span [...]
+<span class="n">a</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span><span class="n">a_np</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
+<span class="n">b</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span><span class="n">b_np</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
+<span class="n">c</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span><span class="n">np</span><span class="p">.</span><span class="n">zeros</span><span class="p">((</span><span class="n">N</span><span class="p">,</span> <span class="n">N</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="s">"float32"</span><span [...]
-<span class="n">time_f</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">time_evaluator</span><span class="p">(</span><span class="n">f</span><span class="o">.</span><span class="n">entry_name</span><span class="p">,</span> <span class="n">ctx</span><span class="p">,</span> <span class="n">number</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
-<span class="n">cost</span> <span class="o">=</span> <span class="n">time_f</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span>
-<span class="k">print</span><span class="p">(</span><span class="s">'</span><span class="si">%</span><span class="s">g secs/op, </span><span class="si">%</span><span class="s">g GFLOPS'</span> <span class="o">%</span> <span class="p">(</span><span class="n">cost</span><span class="p">,</span> <span class="n">ngflops</span><span class="p">(</span><span class="n">N</span><span class="p">)</span> <span class="o">/</span> <span class="n">cost</span><span class="p">))</span>
+<span class="n">time_f</span> <span class="o">=</span> <span class="n">f</span><span class="p">.</span><span class="n">time_evaluator</span><span class="p">(</span><span class="n">f</span><span class="p">.</span><span class="n">entry_name</span><span class="p">,</span> <span class="n">ctx</span><span class="p">,</span> <span class="n">number</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
+<span class="n">cost</span> <span class="o">=</span> <span class="n">time_f</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">).</span><span class="n">mean</span>
+<span class="k">print</span><span class="p">(</span><span class="s">'%g secs/op, %g GFLOPS'</span> <span class="o">%</span> <span class="p">(</span><span class="n">cost</span><span class="p">,</span> <span class="n">ngflops</span><span class="p">(</span><span class="n">N</span><span class="p">)</span> <span class="o">/</span> <span class="n">cost</span><span class="p">))</span>
</code></pre></div></div>
<p>Now we can verify the results on PC,</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_almost_equal</span><span class="p">(</span>
- <span class="n">c</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">(),</span>
- <span class="n">a_np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">b_np</span><span class="p">),</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">np</span><span class="p">.</span><span class="n">testing</span><span class="p">.</span><span class="n">assert_almost_equal</span><span class="p">(</span>
+ <span class="n">c</span><span class="p">.</span><span class="n">asnumpy</span><span class="p">(),</span>
+ <span class="n">a_np</span><span class="p">.</span><span class="n">dot</span><span class="p">(</span><span class="n">b_np</span><span class="p">),</span>
<span class="n">decimal</span><span class="o">=</span><span class="mi">3</span><span class="p">)</span>
</code></pre></div></div>
@@ -388,37 +378,41 @@ make jvminstall
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2018/01/16/opt-mali-gpu.html b/2018/01/16/opt-mali-gpu.html
index 795539f..8cd4182 100644
--- a/2018/01/16/opt-mali-gpu.html
+++ b/2018/01/16/opt-mali-gpu.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Optimizing Mobile Deep Learning on ARM GPU with TVM</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -228,7 +218,7 @@ not require explicit vectorization. But also notice that the newer
Mali Bitfrost GPUs are based on quad-style vectorization and does not
require explicit vectorization.</li>
<li>All threads in Mali GPUs have individual program counters. It means
-the <code class="highlighter-rouge">warp size</code> is 1, so that branch divergence is not a major problem.</li>
+the <code class="language-plaintext highlighter-rouge">warp size</code> is 1, so that branch divergence is not a major problem.</li>
</ul>
<h1 id="optimization--convolution-as-example">Optimization : Convolution as Example</h1>
@@ -299,15 +289,15 @@ tiling so that we can access the memory sequentially, which reduces
cache miss rate.</p>
<p>We do tiling on the width dimension of the input image and CO dimension
-of the filter matrix. This is described by <code class="highlighter-rouge">tvm.compute</code>.</p>
+of the filter matrix. This is described by <code class="language-plaintext highlighter-rouge">tvm.compute</code>.</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="c1"># set tiling factor
</span><span class="n">VH</span> <span class="o">=</span> <span class="mi">1</span>
<span class="n">VW</span> <span class="o">=</span> <span class="n">VC</span> <span class="o">=</span> <span class="mi">4</span>
<span class="c1"># get input shape
-</span> <span class="n">_</span><span class="p">,</span> <span class="n">CI</span><span class="p">,</span> <span class="n">IH</span><span class="p">,</span> <span class="n">IW</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">shape</span>
-<span class="n">CO</span><span class="p">,</span> <span class="n">CI</span><span class="p">,</span> <span class="n">KH</span><span class="p">,</span> <span class="n">KW</span> <span class="o">=</span> <span class="n">kernel</span><span class="o">.</span><span class="n">shape</span>
+</span> <span class="n">_</span><span class="p">,</span> <span class="n">CI</span><span class="p">,</span> <span class="n">IH</span><span class="p">,</span> <span class="n">IW</span> <span class="o">=</span> <span class="n">data</span><span class="p">.</span><span class="n">shape</span>
+<span class="n">CO</span><span class="p">,</span> <span class="n">CI</span><span class="p">,</span> <span class="n">KH</span><span class="p">,</span> <span class="n">KW</span> <span class="o">=</span> <span class="n">kernel</span><span class="p">.</span><span class="n">shape</span>
<span class="n">TH</span> <span class="o">=</span> <span class="n">IH</span> <span class="o">+</span> <span class="mi">2</span> <span class="o">*</span> <span class="n">H_PAD</span>
<span class="n">TW</span> <span class="o">=</span> <span class="n">IW</span> <span class="o">+</span> <span class="mi">2</span> <span class="o">*</span> <span class="n">W_PAD</span>
@@ -325,33 +315,33 @@ of the filter matrix. This is described by <code class="highlighter-rouge">tvm.
<span class="n">oshape</span> <span class="o">=</span> <span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">CO</span><span class="p">,</span> <span class="n">OH</span><span class="p">,</span> <span class="n">OW</span><span class="p">)</span>
<span class="c1"># define packing
-</span><span class="n">data_vec</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">compute</span><span class="p">(</span><span class="n">dvshape</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">n</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">vh</span><span class="p">, [...]
+</span><span class="n">data_vec</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">compute</span><span class="p">(</span><span class="n">dvshape</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">n</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">vh</span><span class="p">, [...]
<span class="n">data_pad</span><span class="p">[</span><span class="n">n</span><span class="p">][</span><span class="n">ci</span><span class="p">][</span><span class="n">h</span><span class="o">*</span><span class="n">VH</span><span class="o">*</span><span class="n">H_STRIDE</span><span class="o">+</span><span class="n">vh</span><span class="p">][</span><span class="n">w</span><span class="o">*</span><span class="n">VW</span><span class="o">*</span><span class="n">W_STRIDE</span><spa [...]
-<span class="n">kernel_vec</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">compute</span><span class="p">(</span><span class="n">kvshape</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">,</span> <span class="n">vc</span><span class="p">:</span>
+<span class="n">kernel_vec</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">compute</span><span class="p">(</span><span class="n">kvshape</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">,</span> <span class="n">vc</span><span class="p">:</span>
<span class="n">kernel</span><span class="p">[</span><span class="n">co</span><span class="o">*</span><span class="n">VC</span><span class="o">+</span><span class="n">vc</span><span class="p">][</span><span class="n">ci</span><span class="p">][</span><span class="n">kh</span><span class="p">][</span><span class="n">kw</span><span class="p">],</span> <span class="n">name</span><span class="o">=</span><span class="s">'kernel_vec'</span><span class="p">)</span>
<span class="c1"># define convolution
-</span><span class="n">ci</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">CI</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'ci'</span><span class="p">)</span>
-<span class="n">kh</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">KH</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'kh'</span><span class="p">)</span>
-<span class="n">kw</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">KW</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'kw'</span><span class="p">)</span>
+</span><span class="n">ci</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">CI</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'ci'</span><span class="p">)</span>
+<span class="n">kh</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">KH</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'kh'</span><span class="p">)</span>
+<span class="n">kw</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">KW</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'kw'</span><span class="p">)</span>
-<span class="n">conv</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">compute</span><span class="p">(</span><span class="n">ovshape</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">n</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <sp [...]
- <span class="n">tvm</span><span class="o">.</span><span class="nb">sum</span><span class="p">(</span><span class="n">data_vec</span><span class="p">[</span><span class="n">n</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">vh</span><span class="o">*</span><span class="n">H_STRIDE</span><span class="o">+</span><span class="n">kh</span><span [...]
- <span class="n">kernel_vec</span><span class="p">[</span><span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">,</span> <span class="n">vc</span><span class="p">]</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">out_dtype</span><span class="p">),</span>
+<span class="n">conv</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">compute</span><span class="p">(</span><span class="n">ovshape</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">n</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <sp [...]
+ <span class="n">tvm</span><span class="p">.</span><span class="nb">sum</span><span class="p">(</span><span class="n">data_vec</span><span class="p">[</span><span class="n">n</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">vh</span><span class="o">*</span><span class="n">H_STRIDE</span><span class="o">+</span><span class="n">kh</span><span [...]
+ <span class="n">kernel_vec</span><span class="p">[</span><span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">,</span> <span class="n">vc</span><span class="p">].</span><span class="n">astype</span><span class="p">(</span><span class="n">out_dtype</span><span class="p">),</span>
<span class="n">axis</span><span class="o">=</span><span class="p">[</span><span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">]),</span> <span class="n">name</span><span class="o">=</span><span class="s">'conv'</span><span class="p">)</span>
<span class="c1"># unpack to correct layout
-</span><span class="n">output</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">compute</span><span class="p">(</span><span class="n">oshape</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">n</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">:</span>
+</span><span class="n">output</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">compute</span><span class="p">(</span><span class="n">oshape</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">n</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">:</span>
<span class="n">conv</span><span class="p">[</span><span class="n">n</span><span class="p">][</span><span class="n">co</span><span class="o">//</span><span class="n">VC</span><span class="p">][</span><span class="n">h</span><span class="o">/</span><span class="n">VH</span><span class="p">][</span><span class="n">w</span><span class="o">//</span><span class="n">VW</span><span class="p">][</span><span class="n">h</span><span class="o">%</span><span class="n">VH</span>< [...]
<span class="n">name</span><span class="o">=</span><span class="s">'output_unpack'</span><span class="p">,</span> <span class="n">tag</span><span class="o">=</span><span class="s">'direct_conv_output'</span><span class="p">)</span>
</code></pre></div></div>
<p>We can inspect the defined IR by</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">print</span><span class="p">(</span><span class="n">tvm</span><span class="o">.</span><span class="n">lower</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">data</span><span class="p">,</span> <span class="n">kernel</span><span class="p">,</span> <span class="n">output</span><span class="p">],</span> <span [...]
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">print</span><span class="p">(</span><span class="n">tvm</span><span class="p">.</span><span class="n">lower</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">data</span><span class="p">,</span> <span class="n">kernel</span><span class="p">,</span> <span class="n">output</span><span class="p">],</span> <span [...]
</code></pre></div></div>
<p>I pick the convolution part here.</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>produce conv {
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>produce conv {
for (co, 0, 64) {
for (h, 0, 56) {
for (w, 0, 14) {
@@ -390,35 +380,35 @@ our code can run on Mali GPU.</p>
<span class="s">""" tile and bind 3d """</span>
<span class="n">y_factor</span> <span class="o">=</span> <span class="n">y_factor</span> <span class="ow">or</span> <span class="n">z_factor</span>
<span class="n">x_factor</span> <span class="o">=</span> <span class="n">x_factor</span> <span class="ow">or</span> <span class="n">y_factor</span>
- <span class="n">zo</span><span class="p">,</span> <span class="n">zi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">z</span><span class="p">,</span> <span class="n">z_factor</span><span class="p">)</span>
- <span class="n">yo</span><span class="p">,</span> <span class="n">yi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">y_factor</span><span class="p">)</span>
- <span class="n">xo</span><span class="p">,</span> <span class="n">xi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">x_factor</span><span class="p">)</span>
- <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">zo</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.z"</span><span class="p">))</span>
- <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">zi</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"threadIdx.z"</span><span class="p">))</span>
- <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">yo</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.y"</span><span class="p">))</span>
- <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">yi</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"threadIdx.y"</span><span class="p">))</span>
- <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">xo</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.x"</span><span class="p">))</span>
- <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">]</span><span class="o">.</span><span class="n">bind</span><span class="p">(</span><span class="n">xi</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"threadIdx.x"</span><span class="p">))</span>
+ <span class="n">zo</span><span class="p">,</span> <span class="n">zi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">z</span><span class="p">,</span> <span class="n">z_factor</span><span class="p">)</span>
+ <span class="n">yo</span><span class="p">,</span> <span class="n">yi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">y_factor</span><span class="p">)</span>
+ <span class="n">xo</span><span class="p">,</span> <span class="n">xi</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">].</span><span class="n">split</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">x_factor</span><span class="p">)</span>
+ <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">zo</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.z"</span><span class="p">))</span>
+ <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">zi</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"threadIdx.z"</span><span class="p">))</span>
+ <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">yo</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.y"</span><span class="p">))</span>
+ <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">yi</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"threadIdx.y"</span><span class="p">))</span>
+ <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">xo</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"blockIdx.x"</span><span class="p">))</span>
+ <span class="n">s</span><span class="p">[</span><span class="n">tensor</span><span class="p">].</span><span class="n">bind</span><span class="p">(</span><span class="n">xi</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">thread_axis</span><span class="p">(</span><span class="s">"threadIdx.x"</span><span class="p">))</span>
<span class="c1"># set tunable parameter
</span><span class="n">num_thread</span> <span class="o">=</span> <span class="mi">8</span>
<span class="c1"># schedule data packing
-</span><span class="n">_</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">data_vec</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class [...]
+</span><span class="n">_</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">data_vec</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span>
<span class="n">tile_and_bind3d</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">data_vec</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="c1"># schedule kernel packing
-</span><span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span>
+</span><span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span>
<span class="n">tile_and_bind</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">kernel_vec</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="c1"># schedule conv
-</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n" [...]
-<span class="n">kc</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">reduce_axis</span>
+</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">op</span><span class=" [...]
+<span class="n">kc</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">reduce_axis</span>
-<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">reorder</span><span class="p">(</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">kc</span><span class="p">,</span> <span class="n">kh< [...]
+<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">reorder</span><span class="p">(</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">kc</span><span class="p">,</span> <span class="n">kh</span><span class="p">, [...]
<span class="n">tile_and_bind3d</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">conv</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">num_thread</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
-<span class="n">_</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">oh</span><span class="p">,</span> <span class="n">ow</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">output</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span>
+<span class="n">_</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">oh</span><span class="p">,</span> <span class="n">ow</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">output</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span>
<span class="n">tile_and_bind3d</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">output</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">oh</span><span class="p">,</span> <span class="n">ow</span><span class="p">,</span> <span class="n">num_thread</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
</code></pre></div></div>
@@ -452,41 +442,41 @@ our code can run on Mali GPU.</p>
<h3 id="kernel-2-unrolling">Kernel 2: unrolling</h3>
<p>Loop unrolling can reduce the instructions for loop control, reduce
branch penalties and hide latency in reading memory.
-In TVM, this can be done easily by calling <code class="highlighter-rouge">s.unroll(axis)</code></p>
+In TVM, this can be done easily by calling <code class="language-plaintext highlighter-rouge">s.unroll(axis)</code></p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="c1"># set tunable parameter
</span><span class="n">num_thread</span> <span class="o">=</span> <span class="mi">8</span>
<span class="c1"># schedule data packing
-</span><span class="n">_</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">data_vec</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class [...]
+</span><span class="n">_</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">data_vec</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span>
<span class="n">tile_and_bind3d</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">data_vec</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="s">"""!! ADD UNROLL HERE !!"""</span>
-<span class="n">s</span><span class="p">[</span><span class="n">data_vec</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">vw</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">data_vec</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">vw</span><span class="p">)</span>
<span class="c1"># schedule kernel packing
-</span><span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span>
+</span><span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span>
<span class="n">tile_and_bind</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">kernel_vec</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="s">"""!! ADD UNROLL HERE !!"""</span>
-<span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">kh</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">kw</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">vc</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">kh</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">kw</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">vc</span><span class="p">)</span>
<span class="c1"># schedule conv
-</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n" [...]
-<span class="n">kc</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">reduce_axis</span>
+</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">op</span><span class=" [...]
+<span class="n">kc</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">reduce_axis</span>
-<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">reorder</span><span class="p">(</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">kc</span><span class="p">,</span> <span class="n">kh< [...]
+<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">reorder</span><span class="p">(</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">kc</span><span class="p">,</span> <span class="n">kh</span><span class="p">, [...]
<span class="n">tile_and_bind3d</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">conv</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">num_thread</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="s">"""!! ADD UNROLL HERE !!"""</span>
-<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">kh</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">kw</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">vw</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">vc</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">kh</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">kw</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">vw</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">vc</span><span class="p">)</span>
-<span class="n">_</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">oh</span><span class="p">,</span> <span class="n">ow</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">output</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span>
+<span class="n">_</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">oh</span><span class="p">,</span> <span class="n">ow</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">output</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span>
<span class="n">tile_and_bind3d</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">output</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">oh</span><span class="p">,</span> <span class="n">ow</span><span class="p">,</span> <span class="n">num_thread</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
</code></pre></div></div>
@@ -529,37 +519,37 @@ In TVM, this can be done easily by calling <code class="highlighter-rouge">s.unr
</span><span class="n">num_thread</span> <span class="o">=</span> <span class="mi">8</span>
<span class="c1"># schedule data packing
-</span><span class="n">_</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">data_vec</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class [...]
+</span><span class="n">_</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">data_vec</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span>
<span class="n">tile_and_bind3d</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">data_vec</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="c1"># unroll
-</span><span class="n">s</span><span class="p">[</span><span class="n">data_vec</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">vw</span><span class="p">)</span>
+</span><span class="n">s</span><span class="p">[</span><span class="n">data_vec</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">vw</span><span class="p">)</span>
<span class="c1"># schedule kernel packing
-</span><span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span>
+</span><span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span>
<span class="n">tile_and_bind</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">kernel_vec</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">ci</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="c1"># unroll
-</span><span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">kh</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">kw</span><span class="p">)</span>
+</span><span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">kh</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">kw</span><span class="p">)</span>
<span class="s">"""!! VECTORIZE HERE !!"""</span>
-<span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">]</span><span class="o">.</span><span class="n">vectorize</span><span class="p">(</span><span class="n">vc</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">kernel_vec</span><span class="p">].</span><span class="n">vectorize</span><span class="p">(</span><span class="n">vc</span><span class="p">)</span>
<span class="c1"># schedule conv
-</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n" [...]
-<span class="n">kc</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">reduce_axis</span>
+</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">vw</span><span class="p">,</span> <span class="n">vc</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">op</span><span class=" [...]
+<span class="n">kc</span><span class="p">,</span> <span class="n">kh</span><span class="p">,</span> <span class="n">kw</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">reduce_axis</span>
-<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">reorder</span><span class="p">(</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">kc</span><span class="p">,</span> <span class="n">kh< [...]
+<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">reorder</span><span class="p">(</span><span class="n">_</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">vh</span><span class="p">,</span> <span class="n">kc</span><span class="p">,</span> <span class="n">kh</span><span class="p">, [...]
<span class="n">tile_and_bind3d</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">conv</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">num_thread</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="c1"># unroll
-</span><span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">kh</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">kw</span><span class="p">)</span>
-<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span><span class="n">vw</span><span class="p">)</span>
+</span><span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">kh</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">kw</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">unroll</span><span class="p">(</span><span class="n">vw</span><span class="p">)</span>
<span class="s">"""!! VECTORIZE HERE !!"""</span>
-<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">]</span><span class="o">.</span><span class="n">vectorize</span><span class="p">(</span><span class="n">vc</span><span class="p">)</span>
+<span class="n">s</span><span class="p">[</span><span class="n">conv</span><span class="p">].</span><span class="n">vectorize</span><span class="p">(</span><span class="n">vc</span><span class="p">)</span>
-<span class="n">_</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">oh</span><span class="p">,</span> <span class="n">ow</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">output</span><span class="p">]</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">axis</span>
+<span class="n">_</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">oh</span><span class="p">,</span> <span class="n">ow</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">output</span><span class="p">].</span><span class="n">op</span><span class="p">.</span><span class="n">axis</span>
<span class="n">tile_and_bind3d</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="n">output</span><span class="p">,</span> <span class="n">co</span><span class="p">,</span> <span class="n">oh</span><span class="p">,</span> <span class="n">ow</span><span class="p">,</span> <span class="n">num_thread</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
</code></pre></div></div>
@@ -602,7 +592,7 @@ In TVM, this can be done easily by calling <code class="highlighter-rouge">s.unr
<h3 id="how-to-set-the-tunable-parameter">How to set the tunable parameter</h3>
<p>As for the tunable parameters above, some can be calculated.
-For the vectorized dimension <code class="highlighter-rouge">VC</code>, we should fill the 128-bit register,
+For the vectorized dimension <code class="language-plaintext highlighter-rouge">VC</code>, we should fill the 128-bit register,
so it can be set as 128/32=4 for float32 and 128/16=8 for float16.</p>
<p>But more often we cannot determine the optimal value, due to the
@@ -612,7 +602,7 @@ IR rather than direct OpenCL code.</p>
<h3 id="the-generated-opencl-code">The generated OpenCL code</h3>
<p>We can view the generated OpenCL code by</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">print</span><span class="p">(</span><span class="n">func</span><span class="o">.</span><span class="n">imported_modules</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">get_source</span><span class="p">())</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">print</span><span class="p">(</span><span class="n">func</span><span class="p">.</span><span class="n">imported_modules</span><span class="p">[</span><span class="mi">0</span><span class="p">].</span><span class="n">get_source</span><span class="p">())</span>
</code></pre></div></div>
<p>The OpenCL code is too long to be pasted here, and it is hard to read due
to heavy unrolling. If interested, you can view it
@@ -623,7 +613,7 @@ to heavy unrolling. If interested, you can view it
different backends on some popular deep neural networks.
Our test environment is</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>Firefly-RK3399 4G
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>Firefly-RK3399 4G
CPU: dual-core Cortex-A72 + quad-core Cortex-A53
GPU: Mali-T860MP4
@@ -734,37 +724,41 @@ advice and <a href="https://github.com/yzhliu">Yizhi Liu</a> for his earlier wor
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2018/03/12/webgl.html b/2018/03/12/webgl.html
index 988707c..7f141fb 100644
--- a/2018/03/12/webgl.html
+++ b/2018/03/12/webgl.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Compiling Deep Learning Models to WebGL with TVM</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -276,37 +266,41 @@ optimizations into the TVM stack.</p>
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2018/03/23/nmt-transformer-optimize.html b/2018/03/23/nmt-transformer-optimize.html
index b85019d..7f2de7b 100644
--- a/2018/03/23/nmt-transformer-optimize.html
+++ b/2018/03/23/nmt-transformer-optimize.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Bringing TVM into TensorFlow for Optimizing Neural Machine Translation on GPU</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -189,7 +179,7 @@ One paricular challenge we observed, is that batch matmul is a major performance
<p>Batch matmul computation can be described more concretely as follows:</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>void BatchedGemm(input A, input B, output C, M, N, K, batch_dimension) {
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>void BatchedGemm(input A, input B, output C, M, N, K, batch_dimension) {
for (int i = 0; i < batch_dimension; ++i) {
DoGemm(A[i],B[i],C[i],M,K,N)
}
@@ -258,7 +248,7 @@ One paricular challenge we observed, is that batch matmul is a major performance
<p>In TVM, a general batch matmul computation can be declared as:</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code># computation representation
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code># computation representation
A = tvm.placeholder((batch, M, K), name='A')
B = tvm.placeholder((batch, K, N), name='B')
k = tvm.reduce_axis((0, K), 'k')
@@ -273,7 +263,7 @@ C = tvm.compute((batch, M, N),
<h3 id="tuning-parameters-of-blockthread-numbers">Tuning parameters of block/thread numbers</h3>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code> # thread indices
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code> # thread indices
block_y = tvm.thread_axis("blockIdx.y")
block_x = tvm.thread_axis("blockIdx.x")
thread_y = tvm.thread_axis((0, num_thread_y), "threadIdx.y")
@@ -298,9 +288,9 @@ C = tvm.compute((batch, M, N),
s[C].bind(vty, thread_yz)
s[C].bind(vtx, thread_xz)
</code></pre></div></div>
-<p>We fuse the outer dimensions of the batch matmul, i.e. the BB and FF of the op’s dimension, normally known as “batch” dimension in batch matmul computation. Then we split the outer and the inner dimensions by a factor of (<code class="highlighter-rouge">number_thread * vthread</code>).</p>
+<p>We fuse the outer dimensions of the batch matmul, i.e. the BB and FF of the op’s dimension, normally known as “batch” dimension in batch matmul computation. Then we split the outer and the inner dimensions by a factor of (<code class="language-plaintext highlighter-rouge">number_thread * vthread</code>).</p>
-<p>Strided pattern is not needed in batch matmul, thus the virtual thread number (<code class="highlighter-rouge">vthread_y</code> and <code class="highlighter-rouge">vthread_x</code>) are both set to 1.</p>
+<p>Strided pattern is not needed in batch matmul, thus the virtual thread number (<code class="language-plaintext highlighter-rouge">vthread_y</code> and <code class="language-plaintext highlighter-rouge">vthread_x</code>) are both set to 1.</p>
<h4 id="finding-the-best-combination-of-number_thread">Finding the best combination of number_thread</h4>
@@ -349,7 +339,7 @@ C = tvm.compute((batch, M, N),
</tbody>
</table>
-<p>As learned from <a href="http://tvmlang.org/2017/08/22/Optimize-Deep-Learning-GPU-Operators-with-TVM-A-Depthwise-Convolution-Example.html">past experience</a>, the method to find the best combination of <code class="highlighter-rouge">num_thread_y</code> and <code class="highlighter-rouge">num_thread_x</code> is through brute-force search. After a brute-force search, the best combination for current shape can be found, which in current computation is <code class="highlighter-rouge">nu [...]
+<p>As learned from <a href="http://tvmlang.org/2017/08/22/Optimize-Deep-Learning-GPU-Operators-with-TVM-A-Depthwise-Convolution-Example.html">past experience</a>, the method to find the best combination of <code class="language-plaintext highlighter-rouge">num_thread_y</code> and <code class="language-plaintext highlighter-rouge">num_thread_x</code> is through brute-force search. After a brute-force search, the best combination for current shape can be found, which in current computation [...]
<h2 id="fuse-batch-matmul-with-other-operations">Fuse batch matmul with other operations</h2>
@@ -359,7 +349,7 @@ C = tvm.compute((batch, M, N),
<p>Batch matmul and broadcast add fusion computation can be declared as follows:</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code># computation representation
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code># computation representation
A = tvm.placeholder((batch_size, features, M, K), name='A')
# the shape of B is (N, K) other than (K, N) is because B is transposed is this fusion pattern
B = tvm.placeholder((batch_size, features, N, K), name='B')
@@ -374,7 +364,7 @@ D = topi.broadcast_add(C, ENTER)
<p>Batch matmul and transpose fusion computation can be declared as:</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code># computation representation
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code># computation representation
A = tvm.placeholder((batch_size, features, M, K), name='A')
B = tvm.placeholder((batch_size, features, K, N), name='B')
k = tvm.reduce_axis((0, K), 'k')
@@ -388,10 +378,10 @@ C = tvm.compute(
<p>The shape of [batch=64, heads=8, M=1, N=17, K=128] is chosen to elaborate the performance of the generated code. 17 is chosen as the sequence length since it is the average input length in our production scenarios.</p>
<ul>
- <li>tf-r1.4 <code class="highlighter-rouge">BatchMatmul</code>: 513.9 us</li>
- <li>tf-r1.4 <code class="highlighter-rouge">BatchMatmul</code> + <code class="highlighter-rouge">Transpose</code> (separate): 541.9 us</li>
- <li>TVM <code class="highlighter-rouge">BatchMatmul</code>: 37.62 us</li>
- <li>TVM <code class="highlighter-rouge">BatchMatmul</code> + <code class="highlighter-rouge">Transpose</code> (fused): 38.39 us</li>
+ <li>tf-r1.4 <code class="language-plaintext highlighter-rouge">BatchMatmul</code>: 513.9 us</li>
+ <li>tf-r1.4 <code class="language-plaintext highlighter-rouge">BatchMatmul</code> + <code class="language-plaintext highlighter-rouge">Transpose</code> (separate): 541.9 us</li>
+ <li>TVM <code class="language-plaintext highlighter-rouge">BatchMatmul</code>: 37.62 us</li>
+ <li>TVM <code class="language-plaintext highlighter-rouge">BatchMatmul</code> + <code class="language-plaintext highlighter-rouge">Transpose</code> (fused): 38.39 us</li>
</ul>
<p>The kernel fusion optimization brings a further <b><em>1.7X</em></b> speed-up.</p>
@@ -422,37 +412,41 @@ C = tvm.compute(
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2018/07/12/vta-release-announcement.html b/2018/07/12/vta-release-announcement.html
index 08c2b6e..8b0e0fa 100644
--- a/2018/07/12/vta-release-announcement.html
+++ b/2018/07/12/vta-release-announcement.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>VTA: An Open, Customizable Deep Learning Acceleration Stack </title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -298,37 +288,41 @@ This kind of high-level visibility is essential to system designers who want to
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2018/08/10/DLPack-Bridge.html b/2018/08/10/DLPack-Bridge.html
index 9849d29..0ff8471 100644
--- a/2018/08/10/DLPack-Bridge.html
+++ b/2018/08/10/DLPack-Bridge.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Building a Cross-Framework Deep Learning Compiler via DLPack</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -226,21 +216,21 @@ Figure 1</p>
<p>First, we compute a reference output in PyTorch:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code> <span class="kn">import</span> <span class="nn">torch</span>
- <span class="n">x</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">)</span>
- <span class="n">y</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">)</span>
- <span class="n">z</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">mm</span><span class="p">(</span><span class="n">y</span><span class="p">)</span>
+ <span class="n">x</span> <span class="o">=</span> <span class="n">torch</span><span class="p">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">)</span>
+ <span class="n">y</span> <span class="o">=</span> <span class="n">torch</span><span class="p">.</span><span class="n">rand</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">)</span>
+ <span class="n">z</span> <span class="o">=</span> <span class="n">x</span><span class="p">.</span><span class="n">mm</span><span class="p">(</span><span class="n">y</span><span class="p">)</span>
</code></pre></div></div>
<p>We then define and build a TVM matrix multiplication operator, using the default
schedule:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code> <span class="n">n</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">convert</span><span class="p">(</span><span class="mi">56</span><span class="p">)</span>
- <span class="n">X</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">n</span><span class="p">,</span><span class="n">n</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'X'</span><span class="p">)</span>
- <span class="n">Y</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">n</span><span class="p">,</span><span class="n">n</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'Y'</span><span class="p">)</span>
-
- <span class="n">k</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">n</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'k'</span><span class="p">)</span>
- <span class="n">Z</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">compute</span><span class="p">((</span><span class="n">n</span><span class="p">,</span><span class="n">n</span><span class="p">),</span> <span class="k">lambda</span> <span class="n">i</span><span class="p">,</span><span class="n">j</span> <span class="p">:</span> <span class="n">tvm</span><span class="o">.</span><span class="nb">sum</span><span class="p">(</span><span [...]
- <span class="n">s</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">create_schedule</span><span class="p">(</span><span class="n">Z</span><span class="o">.</span><span class="n">op</span><span class="p">)</span>
- <span class="n">fmm</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">X</span><span class="p">,</span> <span class="n">Y</span><span class="p">,</span> <span class="n">Z</span><span class="p">],</span> <span class="n">target_host</span><span class="o">=</span><span class="s">'llvm'</span><span class="p">,</span> < [...]
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code> <span class="n">n</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">convert</span><span class="p">(</span><span class="mi">56</span><span class="p">)</span>
+ <span class="n">X</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">n</span><span class="p">,</span><span class="n">n</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'X'</span><span class="p">)</span>
+ <span class="n">Y</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">placeholder</span><span class="p">((</span><span class="n">n</span><span class="p">,</span><span class="n">n</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'Y'</span><span class="p">)</span>
+
+ <span class="n">k</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">n</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'k'</span><span class="p">)</span>
+ <span class="n">Z</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">compute</span><span class="p">((</span><span class="n">n</span><span class="p">,</span><span class="n">n</span><span class="p">),</span> <span class="k">lambda</span> <span class="n">i</span><span class="p">,</span><span class="n">j</span> <span class="p">:</span> <span class="n">tvm</span><span class="p">.</span><span class="nb">sum</span><span class="p">(</span><span [...]
+ <span class="n">s</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">create_schedule</span><span class="p">(</span><span class="n">Z</span><span class="p">.</span><span class="n">op</span><span class="p">)</span>
+ <span class="n">fmm</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">X</span><span class="p">,</span> <span class="n">Y</span><span class="p">,</span> <span class="n">Z</span><span class="p">],</span> <span class="n">target_host</span><span class="o">=</span><span class="s">'llvm'</span><span class="p">,</span> < [...]
</code></pre></div></div>
<p>For brevity, we do not cover TVM’s large collection of scheduling primitives
that we can use to optimize matrix multiplication. If you wish to make a custom
@@ -252,37 +242,37 @@ found <a href="https://tvm.apache.org/docs//tutorials/optimize/opt_gemm.html">he
<span class="c1"># fmm is the previously built TVM function (Python function)
</span> <span class="c1"># fmm is the wrapped TVM function (Python function)
</span> <span class="n">fmm_pytorch</span> <span class="o">=</span> <span class="n">to_pytorch_func</span><span class="p">(</span><span class="n">fmm</span><span class="p">)</span>
- <span class="n">z2</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">empty</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">)</span>
+ <span class="n">z2</span> <span class="o">=</span> <span class="n">torch</span><span class="p">.</span><span class="n">empty</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">)</span>
<span class="n">fmm_pytorch</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">z2</span><span class="p">)</span>
- <span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">z</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">z2</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
+ <span class="n">np</span><span class="p">.</span><span class="n">testing</span><span class="p">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">z</span><span class="p">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">z2</span><span class="p">.</span><span class="n">numpy</span><span class="p">())</span>
</code></pre></div></div>
<p>and verify that the results match.</p>
<p>We can repeat the same example, but using MxNet instead:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code> <span class="kn">import</span> <span class="nn">mxnet</span>
<span class="kn">from</span> <span class="nn">tvm.contrib.mxnet</span> <span class="kn">import</span> <span class="n">to_mxnet_func</span>
- <span class="n">ctx</span> <span class="o">=</span> <span class="n">mxnet</span><span class="o">.</span><span class="n">cpu</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
- <span class="n">x</span> <span class="o">=</span> <span class="n">mxnet</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">),</span> <span class="n">ctx</span><span class="o">=</span><span class="n">ctx</span><span class="p">)</span>
- <span class="n">y</span> <span class="o">=</span> <span class="n">mxnet</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">),</span> <span class="n">ctx</span><span class="o">=</span><span class="n">ctx</span><span class="p">)</span>
- <span class="n">z</span> <span class="o">=</span> <span class="n">mxnet</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">empty</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">),</span> <span class="n">ctx</span><span class="o">=</span><span class="n">ctx</span><span class="p">)</span>
- <span class="n">f</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">X</span><span class="p">,</span> <span class="n">Y</span><span class="p">,</span> <span class="n">Z</span><span class="p">],</span> <span class="n">target_host</span><span class="o">=</span><span class="s">'llvm'</span><span class="p">,</span> <sp [...]
+ <span class="n">ctx</span> <span class="o">=</span> <span class="n">mxnet</span><span class="p">.</span><span class="n">cpu</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
+ <span class="n">x</span> <span class="o">=</span> <span class="n">mxnet</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">),</span> <span class="n">ctx</span><span class="o">=</span><span class="n">ctx</span><span class="p">)</span>
+ <span class="n">y</span> <span class="o">=</span> <span class="n">mxnet</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">uniform</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">),</span> <span class="n">ctx</span><span class="o">=</span><span class="n">ctx</span><span class="p">)</span>
+ <span class="n">z</span> <span class="o">=</span> <span class="n">mxnet</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">empty</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">56</span><span class="p">,</span><span class="mi">56</span><span class="p">),</span> <span class="n">ctx</span><span class="o">=</span><span class="n">ctx</span><span class="p">)</span>
+ <span class="n">f</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="p">[</span><span class="n">X</span><span class="p">,</span> <span class="n">Y</span><span class="p">,</span> <span class="n">Z</span><span class="p">],</span> <span class="n">target_host</span><span class="o">=</span><span class="s">'llvm'</span><span class="p">,</span> <sp [...]
<span class="n">f_mxnet</span> <span class="o">=</span> <span class="n">to_mxnet_func</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
<span class="n">f_mxnet</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">z</span><span class="p">)</span>
- <span class="n">np</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">z</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">(),</span> <span class="n">x</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">y</span><span class="o">. [...]
+ <span class="n">np</span><span class="p">.</span><span class="n">testing</span><span class="p">.</span><span class="n">assert_allclose</span><span class="p">(</span><span class="n">z</span><span class="p">.</span><span class="n">asnumpy</span><span class="p">(),</span> <span class="n">x</span><span class="p">.</span><span class="n">asnumpy</span><span class="p">().</span><span class="n">dot</span><span class="p">(</span><span class="n">y</span><span class="p">.</span><span class="n"> [...]
</code></pre></div></div>
<h2 id="under-the-hood-of-the-pytorch-example">Under the hood of the PyTorch Example</h2>
-<p>As TVM provides <a href="https://github.com/dmlc/tvm/blob/master/include/tvm/runtime/c_runtime_api.h#L455">functions</a> to convert dlpack tensors to tvm <code class="highlighter-rouge">NDArray</code>s and
+<p>As TVM provides <a href="https://github.com/dmlc/tvm/blob/master/include/tvm/runtime/c_runtime_api.h#L455">functions</a> to convert dlpack tensors to tvm <code class="language-plaintext highlighter-rouge">NDArray</code>s and
vice-versa, so all that is needed is some syntactic sugar by wrapping functions.
-<code class="highlighter-rouge">convert_func</code> is a generic converter for frameworks using tensors with dlpack
+<code class="language-plaintext highlighter-rouge">convert_func</code> is a generic converter for frameworks using tensors with dlpack
support, and can be used to implement convenient converters, such as
-<code class="highlighter-rouge">to_pytorch_func</code>.</p>
+<code class="language-plaintext highlighter-rouge">to_pytorch_func</code>.</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">convert_func</span><span class="p">(</span><span class="n">tvm_func</span><span class="p">,</span> <span class="n">tensor_type</span><span class="p">,</span> <span class="n">to_dlpack_func</span><span class="p">):</span>
<span class="k">assert</span> <span class="nb">callable</span><span class="p">(</span><span class="n">tvm_func</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_wrapper</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">):</span>
- <span class="n">args</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">ndarray</span><span class="o">.</span><span class="n">from_dlpack</span><span class="p">(</span><span class="n">to_dlpack_func</span><span class="p">(</span><span class="n">arg</span><span class="p">))</span>\
+ <span class="n">args</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">ndarray</span><span class="p">.</span><span class="n">from_dlpack</span><span class="p">(</span><span class="n">to_dlpack_func</span><span class="p">(</span><span class="n">arg</span><span class="p">))</span>\
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="n">tensor_type</span><span class="p">)</span> <span class="k">else</span> <span class="n">arg</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="n">args</span><span class="p">)</span>
<span class="k">return</span> <span class="n">tvm_func</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">)</span>
@@ -291,7 +281,7 @@ support, and can be used to implement convenient converters, such as
<span class="k">def</span> <span class="nf">to_pytorch_func</span><span class="p">(</span><span class="n">tvm_func</span><span class="p">):</span>
<span class="kn">import</span> <span class="nn">torch</span>
<span class="kn">import</span> <span class="nn">torch.utils.dlpack</span>
- <span class="k">return</span> <span class="n">convert_func</span><span class="p">(</span><span class="n">tvm_func</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">dlpack</span><span class="o">.</span><span class="n">to_dlpack</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">convert_func</span><span class="p">(</span><span class="n">tvm_func</span><span class="p">,</span> <span class="n">torch</span><span class="p">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">torch</span><span class="p">.</span><span class="n">utils</span><span class="p">.</span><span class="n">dlpack</span><span class="p">.</span><span class="n">to_dlpack</span><span class="p">)</span>
</code></pre></div></div>
</div>
@@ -299,37 +289,41 @@ support, and can be used to implement convenient converters, such as
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2018/10/03/auto-opt-all.html b/2018/10/03/auto-opt-all.html
index 87f8122..d9413e8 100644
--- a/2018/10/03/auto-opt-all.html
+++ b/2018/10/03/auto-opt-all.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Automatic Kernel Optimization for Deep Learning on All Hardware Platforms</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -216,9 +206,9 @@ Links to tutorials for ARM CPU, Mali GPU, NVIDIA GPU, AMD GPU are all available
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="kn">from</span> <span class="nn">mxnet.gluon.model_zoo.vision</span> <span class="kn">import</span> <span class="n">get_model</span>
<span class="n">block</span> <span class="o">=</span> <span class="n">get_model</span><span class="p">(</span><span class="s">'resnet18_v1'</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span>
-<span class="n">net</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">nnvm</span><span class="o">.</span><span class="n">frontend</span><span class="o">.</span><span class="n">from_mxnet</span><span class="p">(</span><span class="n">block</span><span class="p">)</span>
+<span class="n">net</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">nnvm</span><span class="p">.</span><span class="n">frontend</span><span class="p">.</span><span class="n">from_mxnet</span><span class="p">(</span><span class="n">block</span><span class="p">)</span>
-<span class="n">tasks</span> <span class="o">=</span> <span class="n">autotvm</span><span class="o">.</span><span class="n">extract_from_graph</span><span class="p">(</span><span class="n">net</span><span class="p">)</span>
+<span class="n">tasks</span> <span class="o">=</span> <span class="n">autotvm</span><span class="p">.</span><span class="n">extract_from_graph</span><span class="p">(</span><span class="n">net</span><span class="p">)</span>
<span class="n">tune_tasks</span><span class="p">(</span><span class="n">tasks</span><span class="p">,</span> <span class="o">**</span><span class="n">tuning_option</span><span class="p">)</span>
</code></pre></div></div>
<p>There are 12 different conv2d layers in resnet-18, so we launch 12 tuning tasks.
@@ -226,7 +216,7 @@ For each of them, the tuner makes several hundreds of trials and picks the best
After finishing all tuning tasks, we compile the whole network and generate a single deployable minimal library.
One sample output is</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>Extract tasks...
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>Extract tasks...
Tuning...
[Task 1/12] Current/Best: 22.37/ 52.19 GFLOPS | Progress: (544/1000) | 406.59 s Done.
[Task 2/12] Current/Best: 6.51/ 18.77 GFLOPS | Progress: (608/1000) | 325.05 s Done.
@@ -554,37 +544,41 @@ for inference deployment. TVM just provides such a solution.</p>
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2018/10/09/ml-in-tees.html b/2018/10/09/ml-in-tees.html
index b7c74f2..440579f 100644
--- a/2018/10/09/ml-in-tees.html
+++ b/2018/10/09/ml-in-tees.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Efficient Privacy-Preserving ML Using TVM</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -276,37 +266,41 @@ His research interest is in the general domain of ML on shared private data, but
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2018/12/18/lowprecision-conv.html b/2018/12/18/lowprecision-conv.html
index 997729a..8b38138 100644
--- a/2018/12/18/lowprecision-conv.html
+++ b/2018/12/18/lowprecision-conv.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Automating Generation of Low Precision Deep Learning Operators</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -232,8 +222,8 @@ Finally, the output is computed in an unpacked format and in higher precision.</
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">Input_bitpacked</span> <span class="o">=</span> <span class="n">bitpack</span><span class="p">(</span><span class="n">Input</span><span class="p">,</span> <span class="n">activation_bits</span><span class="p">,</span> <span class="n">pack_axis</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">bit_axis</span><span class="o">=</spa [...]
<span class="n">Weights_bitpacked</span> <span class="o">=</span> <span class="n">bitpack</span><span class="p">(</span><span class="n">Filter</span><span class="p">,</span> <span class="n">weight_bits</span><span class="p">,</span> <span class="n">pack_axis</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">bit_axis</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">pack_type</span><span class="o"> [...]
-<span class="n">batch</span><span class="p">,</span> <span class="n">in_height</span><span class="p">,</span> <span class="n">in_width</span><span class="p">,</span> <span class="n">in_channel_q</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">Input_bitpacked</span><span class="o">.</span><span class="n">shape</span>
-<span class="n">kernel_h</span><span class="p">,</span> <span class="n">kernel_w</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">num_filter</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">Filter_bitpakced</span><span class="o">.</span><span class="n">shape</span>
+<span class="n">batch</span><span class="p">,</span> <span class="n">in_height</span><span class="p">,</span> <span class="n">in_width</span><span class="p">,</span> <span class="n">in_channel_q</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">Input_bitpacked</span><span class="p">.</span><span class="n">shape</span>
+<span class="n">kernel_h</span><span class="p">,</span> <span class="n">kernel_w</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">num_filter</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">Filter_bitpakced</span><span class="p">.</span><span class="n">shape</span>
<span class="n">stride_h</span><span class="p">,</span> <span class="n">stride_w</span> <span class="o">=</span> <span class="n">stride</span>
<span class="n">pad_top</span><span class="p">,</span> <span class="n">pad_left</span><span class="p">,</span> <span class="n">pad_down</span><span class="p">,</span> <span class="n">pad_right</span> <span class="o">=</span> <span class="n">get_pad_tuple</span><span class="p">(</span><span class="n">padding</span><span class="p">,</span> <span class="p">(</span><span class="n">kernel_h</span><span class="p">,</span> <span class="n">kernel_w</span><span class="p">))</span>
@@ -247,17 +237,17 @@ Finally, the output is computed in an unpacked format and in higher precision.</
<span class="n">Input_padded</span> <span class="o">=</span> <span class="n">pad</span><span class="p">(</span><span class="n">Input_bitpacked</span><span class="p">,</span> <span class="n">pad_before</span><span class="p">,</span> <span class="n">pad_after</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s">"PaddedInput"</span><span class="p">)</span>
<span class="c1"># Treat the bitplane axes like additional reduction axes
-</span><span class="n">rc</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">in_channel_q</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'rc'</span><span class="p">)</span>
-<span class="n">ry</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">kernel_h</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'ry'</span><span class="p">)</span>
-<span class="n">rx</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">kernel_w</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'rx'</span><span class="p">)</span>
-<span class="n">ib</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">input_bits</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'ib'</span><span class="p">)</span>
-<span class="n">wb</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">weight_bits</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'wb'</span><span class="p">)</span>
+</span><span class="n">rc</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">in_channel_q</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'rc'</span><span class="p">)</span>
+<span class="n">ry</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">kernel_h</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'ry'</span><span class="p">)</span>
+<span class="n">rx</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">kernel_w</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'rx'</span><span class="p">)</span>
+<span class="n">ib</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">input_bits</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'ib'</span><span class="p">)</span>
+<span class="n">wb</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">reduce_axis</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">weight_bits</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="s">'wb'</span><span class="p">)</span>
-<span class="n">tvm</span><span class="o">.</span><span class="n">compute</span><span class="p">((</span><span class="n">batch</span><span class="p">,</span> <span class="n">out_height</span><span class="p">,</span> <span class="n">out_width</span><span class="p">,</span> <span class="n">out_channel</span><span class="p">),</span> <span class="k">lambda</span> <span class="n">nn</span><span class="p">,</span> <span class="n">yy</span><span class="p">,</span> <span class="n">xx</span><spa [...]
- <span class="n">tvm</span><span class="o">.</span><span class="nb">sum</span><span class="p">(</span><span class="n">tvm</span><span class="o">.</span><span class="n">popcount</span><span class="p">(</span>
+<span class="n">tvm</span><span class="p">.</span><span class="n">compute</span><span class="p">((</span><span class="n">batch</span><span class="p">,</span> <span class="n">out_height</span><span class="p">,</span> <span class="n">out_width</span><span class="p">,</span> <span class="n">out_channel</span><span class="p">),</span> <span class="k">lambda</span> <span class="n">nn</span><span class="p">,</span> <span class="n">yy</span><span class="p">,</span> <span class="n">xx</span><spa [...]
+ <span class="n">tvm</span><span class="p">.</span><span class="nb">sum</span><span class="p">(</span><span class="n">tvm</span><span class="p">.</span><span class="n">popcount</span><span class="p">(</span>
<span class="n">Input_padded</span><span class="p">[</span><span class="n">nn</span><span class="p">,</span> <span class="n">yy</span> <span class="o">*</span> <span class="n">stride_h</span> <span class="o">+</span> <span class="n">ry</span><span class="p">,</span> <span class="n">xx</span> <span class="o">*</span> <span class="n">stride_w</span> <span class="o">+</span> <span class="n">rx</span><span class="p">,</span> <span class="n">rc</span><span class="p">,</span> <s [...]
- <span class="n">Weights_bitpacked</span><span class="p">[</span><span class="n">ry</span><span class="p">,</span> <span class="n">rx</span><span class="p">,</span> <span class="n">rc</span><span class="p">,</span> <span class="n">ff</span><span class="p">,</span> <span class="n">wb</span><span class="p">]))</span> <span class="o"><<</span> <span class="p">(</span><span class="n">ib</span><span class="o">+</span><span class="n">wb</span><span class="p">)))</span><span [...]
+ <span class="n">Weights_bitpacked</span><span class="p">[</span><span class="n">ry</span><span class="p">,</span> <span class="n">rx</span><span class="p">,</span> <span class="n">rc</span><span class="p">,</span> <span class="n">ff</span><span class="p">,</span> <span class="n">wb</span><span class="p">]))</span> <span class="o"><<</span> <span class="p">(</span><span class="n">ib</span><span class="o">+</span><span class="n">wb</span><span class="p">))).</span><spa [...]
<span class="n">axis</span><span class="o">=</span><span class="p">[</span><span class="n">rc</span><span class="p">,</span> <span class="n">ry</span><span class="p">,</span> <span class="n">rx</span><span class="p">,</span> <span class="n">wb</span><span class="p">,</span> <span class="n">ib</span><span class="p">]))</span>
</code></pre></div></div>
@@ -321,37 +311,41 @@ Note: x86 doesn’t support a vectorized popcount for this microarchitecture, so
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2019/01/19/Golang.html b/2019/01/19/Golang.html
index cd312b9..0c64181 100644
--- a/2019/01/19/Golang.html
+++ b/2019/01/19/Golang.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>TVM Golang Runtime for Deep Learning Deployment</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -179,12 +169,12 @@ integrates the TVM runtime can load these compiled modules and perform inference
import and compilation using TVM can be found at <a href="https://tvm.apache.org/docs//tutorials/">tutorials</a>.</p>
<p>TVM now supports deploying compiled modules through Golang. Golang applications can make use of this
-to deploy the deep learning models through TVM. The scope of this blog is the introduction of <code class="highlighter-rouge">gotvm</code> package,
-the package build process and a sample application using <code class="highlighter-rouge">gotvm</code> to load a compiled module and perform inference.</p>
+to deploy the deep learning models through TVM. The scope of this blog is the introduction of <code class="language-plaintext highlighter-rouge">gotvm</code> package,
+the package build process and a sample application using <code class="language-plaintext highlighter-rouge">gotvm</code> to load a compiled module and perform inference.</p>
<h2 id="package">Package</h2>
-<p>The golang package <code class="highlighter-rouge">gotvm</code> is built on top of TVM’s C runtime interface. The API in this package
+<p>The golang package <code class="language-plaintext highlighter-rouge">gotvm</code> is built on top of TVM’s C runtime interface. The API in this package
abstracts the native C types and provides Golang compatible types. The package source can be found
at <a href="https://github.com/dmlc/tvm/tree/master/golang">gotvm</a>.</p>
@@ -197,10 +187,10 @@ necessary conversions across API calls.</p>
<h2 id="how-to">How to</h2>
-<p>As shown in the below diagram <code class="highlighter-rouge">gotvm</code> enables golang applications to integrate deep learning models
+<p>As shown in the below diagram <code class="language-plaintext highlighter-rouge">gotvm</code> enables golang applications to integrate deep learning models
from various frameworks without the hassle of understanding each framework related interface API.
Developers can make use of TVM to import and compile deep learning models and generate TVM artifacts.
-<code class="highlighter-rouge">gotvm</code> package provides golang friendly API to load, configure, feed input and get output.</p>
+<code class="language-plaintext highlighter-rouge">gotvm</code> package provides golang friendly API to load, configure, feed input and get output.</p>
<p style="text-align: center"><img src="/images/golang/TVM-Golang-Flow.png" alt="image" width="100%" /></p>
<center> Import, Compile, Integrate and Deploy</center>
@@ -212,8 +202,8 @@ generates the artifacts required to integrate and deploy the model on a target.<
<h2 id="api">API</h2>
-<p><code class="highlighter-rouge">gotvm</code> package provides a handful of datatypes and API functions to initialize, load and infer
-from a golang application. Like any other golang package we just need to import <code class="highlighter-rouge">gotvm</code> package here.</p>
+<p><code class="language-plaintext highlighter-rouge">gotvm</code> package provides a handful of datatypes and API functions to initialize, load and infer
+from a golang application. Like any other golang package we just need to import <code class="language-plaintext highlighter-rouge">gotvm</code> package here.</p>
<ul>
<li>Module : The Module API can be used to load a TVM compiled module into TVM runtime and access any functions.</li>
@@ -302,7 +292,7 @@ For simplicity the error handling is ignored here, but is important in real appl
<span class="p">}</span>
</code></pre></div></div>
-<p><code class="highlighter-rouge">gotvm</code> extends the TVM packed function system to support golang function closures as packed functions.
+<p><code class="language-plaintext highlighter-rouge">gotvm</code> extends the TVM packed function system to support golang function closures as packed functions.
<a href="https://github.com/dmlc/tvm/blob/master/golang/sample">Examples</a> available to register golang
closure as TVM packed function and invoke the same across programming language barriers.</p>
@@ -330,37 +320,41 @@ closure as TVM packed function and invoke the same across programming language b
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2019/03/18/tvm-apache-announcement.html b/2019/03/18/tvm-apache-announcement.html
index b154327..4c0041f 100644
--- a/2019/03/18/tvm-apache-announcement.html
+++ b/2019/03/18/tvm-apache-announcement.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>TVM Deep Learning Compiler Joins Apache Software Foundation</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
+
+
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
+
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
+
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
+
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
+
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
+
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
+
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
+
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
+
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
+
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
+
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
+
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
+
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
+
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
+
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
+
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
+
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
+
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
+
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
+
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
+
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
+
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
+
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li><a href="/community">Community</a></li>
-
-
-
-
-
-
-
-
- <li><a href="/download">Download</a></li>
-
-
-
-
-
-
-
-
- <li><a href="/about">About</a></li>
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
-
-
-
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
-
-
-
-
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -183,37 +173,41 @@
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2019/04/29/opt-cuda-quantized.html b/2019/04/29/opt-cuda-quantized.html
index 40c7157..d2ba1a5 100644
--- a/2019/04/29/opt-cuda-quantized.html
+++ b/2019/04/29/opt-cuda-quantized.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Automating Optimization of Quantized Deep Learning Models on CUDA</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -165,7 +155,7 @@
<p>Deep learning has been successfully applied to a variety of tasks.
On real-time scenarios such as inference on autonomous vehicles, the inference speed of the model is critical.
Network quantization is an effective approach to accelerating deep learning models.
-In quantized models, both data and model parameters are represented with low precision data types such as <code class="highlighter-rouge">int8</code> and <code class="highlighter-rouge">float16</code>.
+In quantized models, both data and model parameters are represented with low precision data types such as <code class="language-plaintext highlighter-rouge">int8</code> and <code class="language-plaintext highlighter-rouge">float16</code>.
The lowered data bandwidth reduces the inference time and memory/storage requirements, as well as the power consumption.
Meanwhile, under proper quantization schemes, we can minimize the accuracy drops of the quantized models.
Therefore, quantized models are of particular interests of researchers and developers as it makes large models suitable to deploy on diverse devices, such as GPU, CPU and mobile devices.</p>
@@ -187,38 +177,38 @@ In emerging models such as ResNeXt and Deformable ConvNets, the automatic optimi
<h1 id="expressing-quantized-cuda-kernels-in-tvm">Expressing Quantized CUDA Kernels in TVM</h1>
<h2 id="leveraging-tensor-intrinsics-via-tensorization">Leveraging Tensor Intrinsics via Tensorization</h2>
-<p>Many platforms provide architecture-specific instructions for special computation patterns, for example, the SIMD instructions on x86, and the <code class="highlighter-rouge">dp4a</code> and <code class="highlighter-rouge">hfma</code> instructions on CUDA.
+<p>Many platforms provide architecture-specific instructions for special computation patterns, for example, the SIMD instructions on x86, and the <code class="language-plaintext highlighter-rouge">dp4a</code> and <code class="language-plaintext highlighter-rouge">hfma</code> instructions on CUDA.
These intrinsic instructions are highly optimized for specific devices.
By leveraging hardware intrinsics, we can achieve a significant performance boost for quantized operators.</p>
<p>Currently, <a href="https://devblogs.nvidia.com/mixed-precision-programming-cuda-8/">dp4a</a> has been extensively used in TVM int8 operators on CUDA.
-<code class="highlighter-rouge">dp4a</code> is a CUDA intrinsic on Compute Capability 6.1 devices.
+<code class="language-plaintext highlighter-rouge">dp4a</code> is a CUDA intrinsic on Compute Capability 6.1 devices.
It is a mixed-precision instruction that provides the efficient computation of the dot product between two 4-element 8-bit integer vectors and accumulates the result in 32-bit format.
-Using <code class="highlighter-rouge">dp4a</code>, we can implement a dot product between 8-bit integer vectors with number of elements evenly divisible by four.
+Using <code class="language-plaintext highlighter-rouge">dp4a</code>, we can implement a dot product between 8-bit integer vectors with number of elements evenly divisible by four.
With an efficient dot product operator, we can implement high-level operators such as 2d convolution and dense layers as these operators are commonly backed by dot products.</p>
<p>To illustrate, in 2d convolution we accumulate along the channel, the width, and the height axis of the kernel.
-This is a typical use case of <code class="highlighter-rouge">dp4a</code>.
+This is a typical use case of <code class="language-plaintext highlighter-rouge">dp4a</code>.
TVM uses tensorization to support calling external intrinsics.
-We do not need to modify the original computation declaration; we use the schedule primitive <code class="highlighter-rouge">tensorize</code> to replace the accumulation with <code class="highlighter-rouge">dp4a</code> tensor intrinsic.
+We do not need to modify the original computation declaration; we use the schedule primitive <code class="language-plaintext highlighter-rouge">tensorize</code> to replace the accumulation with <code class="language-plaintext highlighter-rouge">dp4a</code> tensor intrinsic.
More details of tensorization can be found in the <a href="https://tvm.apache.org/docs//tutorials/language/tensorize.html">tutorial</a>.</p>
<h2 id="data-layout-rearrangement">Data Layout Rearrangement</h2>
<p>One of the challenges in tensorization is that we may need to design special computation logic to adapt to the requirement of tensor intrinsics.
-Although it is natural to accumulate along the inner axis of the tensor in the dense operator, <code class="highlighter-rouge">conv2d</code> can be more challenging.
-In <code class="highlighter-rouge">conv2d</code> we expect to take a slice in the channel dimension as the input of <code class="highlighter-rouge">dp4a</code> because the number of channels is typically multiple of 4 (otherwise we fall back to original <code class="highlighter-rouge">conv2d</code> in NCHW layout).
+Although it is natural to accumulate along the inner axis of the tensor in the dense operator, <code class="language-plaintext highlighter-rouge">conv2d</code> can be more challenging.
+In <code class="language-plaintext highlighter-rouge">conv2d</code> we expect to take a slice in the channel dimension as the input of <code class="language-plaintext highlighter-rouge">dp4a</code> because the number of channels is typically multiple of 4 (otherwise we fall back to original <code class="language-plaintext highlighter-rouge">conv2d</code> in NCHW layout).
Meanwhile, to achieve memory locality, we would like to reduce along the innermost axis first.
Taking these factors into account, we use a custom data layout to address this challenge.</p>
-<p>In CUDA int8 2d convolution, we empirically choose <code class="highlighter-rouge">NCHW4c</code> as data layout and <code class="highlighter-rouge">OIHW4o4i</code> as weight layout.
-The templates can also be easily generalized to <code class="highlighter-rouge">NCHW[x]c</code> and <code class="highlighter-rouge">OIHW[x]o[x]i</code>, where x is an arbitrary positive integer divisible by four.
+<p>In CUDA int8 2d convolution, we empirically choose <code class="language-plaintext highlighter-rouge">NCHW4c</code> as data layout and <code class="language-plaintext highlighter-rouge">OIHW4o4i</code> as weight layout.
+The templates can also be easily generalized to <code class="language-plaintext highlighter-rouge">NCHW[x]c</code> and <code class="language-plaintext highlighter-rouge">OIHW[x]o[x]i</code>, where x is an arbitrary positive integer divisible by four.
In the data layout we choose, slices of channels are in the packed innermost dimension.
Likewise, we pack slices in both the input and output channel dimensions of the weight so that the output has a consistent data layout with the input, which prevents redundant layout transformations between layers.</p>
<p>We show the computation of one element of the output of the 2d convolution in Figure 2.
The element in each position of the super dimension (the outer dimension of the blocked layout which contains packed elements) NCHW and OIHW is the packed input and kernel, respectively.
Each column of the packed kernel comes from a different filter.
-We calculate the dot product between the packed input and each row in the packed kernel using <code class="highlighter-rouge">dp4a</code>, and accumulate the result to the output tensor.</p>
+We calculate the dot product between the packed input and each row in the packed kernel using <code class="language-plaintext highlighter-rouge">dp4a</code>, and accumulate the result to the output tensor.</p>
<p style="text-align: center"><img src="/images/cuda-quantized/conv2d.png" alt="image" width="60%" /></p>
<div>
@@ -229,7 +219,7 @@ Figure 2. 2D convolution with data layout in NCHW4c and weight layout in OIHW4o4
</div>
<p></p>
-<p>After we have specified the layout of convolution layers, other operators such as <code class="highlighter-rouge">add</code> and activations can automatically adapt to the chosen layout during the <a href="https://github.com/dmlc/tvm/blob/master/src/relay/pass/alter_op_layout.cc">AlterOpLayout</a> pass in Relay.
+<p>After we have specified the layout of convolution layers, other operators such as <code class="language-plaintext highlighter-rouge">add</code> and activations can automatically adapt to the chosen layout during the <a href="https://github.com/dmlc/tvm/blob/master/src/relay/pass/alter_op_layout.cc">AlterOpLayout</a> pass in Relay.
The layout transformation of the weight can be precomputed offline. Therefore, we can run the whole model in the same layout without extra overhead.</p>
<h2 id="designing-search-space-for-automatic-optimization">Designing Search Space for Automatic Optimization</h2>
@@ -241,8 +231,8 @@ For example, as caching data in the shared memory is a common practice in CUDA p
We also do some manual tiling such as splitting axes by 4 or 16 to facilitate vectorized memory access.</p>
<p>In quantized 2d convolution, we design a search space that includes a set of tunable options, such as the tile size, the axes to fuse, configurations of loop unrolling and double buffering.
-The templates of quantized <code class="highlighter-rouge">conv2d</code> and <code class="highlighter-rouge">dense</code> on CUDA are registered under template key <code class="highlighter-rouge">int8</code>.
-During automatic tuning, we can create tuning tasks for these quantized operators by setting the <code class="highlighter-rouge">template_key</code> argument.
+The templates of quantized <code class="language-plaintext highlighter-rouge">conv2d</code> and <code class="language-plaintext highlighter-rouge">dense</code> on CUDA are registered under template key <code class="language-plaintext highlighter-rouge">int8</code>.
+During automatic tuning, we can create tuning tasks for these quantized operators by setting the <code class="language-plaintext highlighter-rouge">template_key</code> argument.
Details of how to launch automatic optimization can be found in the <a href="https://tvm.apache.org/docs//tutorials/autotvm/tune_relay_cuda.html">AutoTVM tutorial</a>.</p>
<h1 id="general-workflow">General Workflow</h1>
@@ -253,22 +243,22 @@ Details of how to launch automatic optimization can be found in the <a href="htt
<p>TVM provides an easy workflow to quantize trained models from other frameworks, automatically optimize operators (with AutoTVM), and deploy to different devices.</p>
-<p>First, we use the Relay frontend to import existing models. Here we use an MXNet model with <code class="highlighter-rouge">(1, 3, 224, 224)</code> input shape as an example.</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">sym</span><span class="p">,</span> <span class="n">arg_params</span><span class="p">,</span> <span class="n">aux_params</span> <span class="o">=</span> <span class="n">mxnet</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">load_checkpoint</span><span class="p">(</span><span class="n">model_path</span><span class="p">,</span> < [...]
-<span class="n">net</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">from_mxnet</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">{</span><span class="s">'data'</span><span class="p">:</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</sp [...]
+<p>First, we use the Relay frontend to import existing models. Here we use an MXNet model with <code class="language-plaintext highlighter-rouge">(1, 3, 224, 224)</code> input shape as an example.</p>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">sym</span><span class="p">,</span> <span class="n">arg_params</span><span class="p">,</span> <span class="n">aux_params</span> <span class="o">=</span> <span class="n">mxnet</span><span class="p">.</span><span class="n">model</span><span class="p">.</span><span class="n">load_checkpoint</span><span class="p">(</span><span class="n">model_path</span><span class="p">,</span> < [...]
+<span class="n">net</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">from_mxnet</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">{</span><span class="s">'data'</span><span class="p">:</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</sp [...]
</code></pre></div></div>
<p>Next, we use the relay quantization API to convert it to a quantized model.</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">net</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">quantize</span><span class="o">.</span><span class="n">quantize</span><span class="p">(</span><span class="n">net</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">net</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">quantize</span><span class="p">.</span><span class="n">quantize</span><span class="p">(</span><span class="n">net</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
</code></pre></div></div>
<p>Then, we use AutoTVM to extract tuning tasks for the operators in the model and perform automatic optimization. The <a href="https://tvm.apache.org/docs//tutorials/autotvm/tune_relay_cuda.html">AutoTVM tutorial</a> provides an example for this.</p>
<p>Finally, we build the model and run inference in the quantized mode.</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">with</span> <span class="n">relay</span><span class="o">.</span><span class="n">build_config</span><span class="p">(</span><span class="n">opt_level</span><span class="o">=</span><span class="mi">3</span><span class="p">):</span>
- <span class="n">graph</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">net</span><span class="p">,</span> <span class="n">target</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">with</span> <span class="n">relay</span><span class="p">.</span><span class="n">build_config</span><span class="p">(</span><span class="n">opt_level</span><span class="o">=</span><span class="mi">3</span><span class="p">):</span>
+ <span class="n">graph</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">net</span><span class="p">,</span> <span class="n">target</span><span class="p">)</span>
</code></pre></div></div>
-<p>The result of <code class="highlighter-rouge">relay.build</code> is a deployable library.
+<p>The result of <code class="language-plaintext highlighter-rouge">relay.build</code> is a deployable library.
We can either run inference <a href="https://tvm.apache.org/docs//tutorials/frontend/from_mxnet.html#execute-the-portable-graph-on-tvm">on the GPU</a> directly or deploy <a href="https://tvm.apache.org/docs//tutorials/frontend/deploy_model_on_rasp.html#deploy-the-model-remotely-by-rpc">on the remote devices</a> via RPC.</p>
<h1 id="benchmark">Benchmark</h1>
@@ -304,37 +294,41 @@ We show that automatic optimization in TVM makes it easy and flexible to support
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2019/05/30/pytorch-frontend.html b/2019/05/30/pytorch-frontend.html
index 6d3948b..ad134ff 100644
--- a/2019/05/30/pytorch-frontend.html
+++ b/2019/05/30/pytorch-frontend.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Integrating TVM into PyTorch</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -169,7 +159,7 @@ To that end, PyTorch now has an official TVM-based backend, <a href="https://git
<p>Usage is simple:</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>import torch_tvm
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>import torch_tvm
torch_tvm.enable()
</code></pre></div></div>
@@ -187,11 +177,11 @@ torch_tvm.enable()
<p>To support Relay, two features were added to the PyTorch JIT: custom transformation passes and custom subgraph interpreters.</p>
-<p>When <code class="highlighter-rouge">torch_tvm</code> is enabled, subgraphs of PyTorch IR that can be converted to Relay <code class="highlighter-rouge">Expr</code>s will be marked as Relay-compatible. Since PyTorch IR does not always contain shape information, none of the subgraphs can be compiled in a useful way before invocation.</p>
+<p>When <code class="language-plaintext highlighter-rouge">torch_tvm</code> is enabled, subgraphs of PyTorch IR that can be converted to Relay <code class="language-plaintext highlighter-rouge">Expr</code>s will be marked as Relay-compatible. Since PyTorch IR does not always contain shape information, none of the subgraphs can be compiled in a useful way before invocation.</p>
<p>During user invocation, the PyTorch JIT runtime will determine input shape information and compile the previously marked subgraphs with the new Relay C++ <a href="https://github.com/pytorch/tvm/blob/master/torch_tvm/compiler.cpp#L226-L246">build system</a>. The compilation is cached based on input shapes for subsequent runs. More details can be found in the <a href="https://github.com/pytorch/tvm/blob/master/README.md">README</a>.</p>
-<p><code class="highlighter-rouge">torch_tvm</code> has a continuous benchmark system set up, which is monitoring the performance of ResNet18 on CPU.
+<p><code class="language-plaintext highlighter-rouge">torch_tvm</code> has a continuous benchmark system set up, which is monitoring the performance of ResNet18 on CPU.
Out of the box TVM provides over two times the performance of the default PyTorch JIT backend for various ResNet models.
Below is a graph that details the iterations per second achieved with 16 threads on an AWS c5n.4xlarge instance (larger is better):</p>
@@ -207,9 +197,9 @@ Below is a graph that details the iterations per second achieved with 16 threads
<h3 id="tutorial">Tutorial</h3>
-<p>If you have an already written PyTorch model, the easiest way to get started comes from using <code class="highlighter-rouge">torch.jit.trace</code> as follows</p>
+<p>If you have an already written PyTorch model, the easiest way to get started comes from using <code class="language-plaintext highlighter-rouge">torch.jit.trace</code> as follows</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>import torch_tvm
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>import torch_tvm
from your_model import model, inputs
torch_tvm.enable(opt_level=3)
@@ -237,12 +227,12 @@ with torch.no_grad():
print("Took {}s to run {} iters".format(tvm_time, iters))
</code></pre></div></div>
-<p>Much of this code comes from <a href="https://github.com/pytorch/tvm/blob/master/test/benchmarks.py">benchmarks.py</a>. Note that tuned parameters for AVX2 LLVM compilation is in the <code class="highlighter-rouge">test/</code> folder of the repo.</p>
+<p>Much of this code comes from <a href="https://github.com/pytorch/tvm/blob/master/test/benchmarks.py">benchmarks.py</a>. Note that tuned parameters for AVX2 LLVM compilation is in the <code class="language-plaintext highlighter-rouge">test/</code> folder of the repo.</p>
<p>If you are more comfortable using Relay directly, it is possible to simply extract the expression directly from a
PyTorch function either via (implicit) tracing or TorchScript:</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>def add(a, b, c):
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>def add(a, b, c):
return a + b + c
# via tracing
@@ -262,37 +252,41 @@ relay_graph = torch_tvm.to_relay(mul, inputs)
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2020/05/14/compiling-machine-learning-to-webassembly-and-webgpu.html b/2020/05/14/compiling-machine-learning-to-webassembly-and-webgpu.html
index c51e923..6fae7c4 100644
--- a/2020/05/14/compiling-machine-learning-to-webassembly-and-webgpu.html
+++ b/2020/05/14/compiling-machine-learning-to-webassembly-and-webgpu.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Compiling Machine Learning to WASM and WebGPU with Apache TVM</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -247,37 +237,41 @@
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2020/05/20/bring-your-own-datatypes.html b/2020/05/20/bring-your-own-datatypes.html
index caf053a..90ba24e 100644
--- a/2020/05/20/bring-your-own-datatypes.html
+++ b/2020/05/20/bring-your-own-datatypes.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Bring Your Own Datatypes: Enabling Custom Datatype Exploration in TVM</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -167,7 +157,7 @@
<h2 id="introduction">Introduction</h2>
<p>When designing accelerators, an important decision is how one will approximately represent real numbers in hardware.
-This problem has had a longstanding, industry-standard solution: the IEEE 754 floating-point standard.<sup id="fnref:ieee"><a href="#fn:ieee" class="footnote">1</a></sup>
+This problem has had a longstanding, industry-standard solution: the IEEE 754 floating-point standard.<sup id="fnref:ieee" role="doc-noteref"><a href="#fn:ieee" class="footnote">1</a></sup>
Yet,
when trying to squeeze
the most out of hardware
@@ -181,13 +171,13 @@ If we know the numerical requirements
or more power efficient datatype?
The answer is yes!
Researchers have already begun experimenting with new datatypes in academic and industrial accelerator designs.
-For example, Google’s Tensor Processing Unit (the TPU) uses the <code class="highlighter-rouge">bfloat</code> type: a single-precision IEEE float which has been truncated to 16 bits.
+For example, Google’s Tensor Processing Unit (the TPU) uses the <code class="language-plaintext highlighter-rouge">bfloat</code> type: a single-precision IEEE float which has been truncated to 16 bits.
Due to the lax numerical requirements
of many deep learning workloads,
this truncation often has no effect
on model accuracy,
while instantly cutting the storage cost
- in half.<sup id="fnref:jouppi2017datacenter"><a href="#fn:jouppi2017datacenter" class="footnote">2</a></sup><sup id="fnref:tensorflowbfloat"><a href="#fn:tensorflowbfloat" class="footnote">3</a></sup></p>
+ in half.<sup id="fnref:jouppi2017datacenter" role="doc-noteref"><a href="#fn:jouppi2017datacenter" class="footnote">2</a></sup><sup id="fnref:tensorflowbfloat" role="doc-noteref"><a href="#fn:tensorflowbfloat" class="footnote">3</a></sup></p>
<p>Before researchers begin building hardware for their datatype, however, they first need to determine how their datatype will behave numerically in the workloads they care about.
This often involves first building a software-emulated version of their datatype
@@ -217,8 +207,8 @@ Unlike the posits-in-Tensorflow example above, which enables a single new dataty
using custom datatypes.
In the Bring Your Own Datatypes framework,
“datatype” means a scalar type:
- <code class="highlighter-rouge">float32</code>
- or <code class="highlighter-rouge">uint8</code>, for example.
+ <code class="language-plaintext highlighter-rouge">float32</code>
+ or <code class="language-plaintext highlighter-rouge">uint8</code>, for example.
We do not handle more complicated data formats
such as <a href="https://en.wikipedia.org/wiki/Block_floating_point" target="_blank">block floating point</a>
or Intel’s <a href="https://arxiv.org/abs/1711.02213" target="_blank">Flexpoint</a>.
@@ -234,7 +224,7 @@ Additionally,
A number of these type codes
have hard-coded meanings in TVM,
mapping to common datatypes
- such as <code class="highlighter-rouge">int</code> and <code class="highlighter-rouge">float</code>.
+ such as <code class="language-plaintext highlighter-rouge">int</code> and <code class="language-plaintext highlighter-rouge">float</code>.
However,
the vast majority of type codes
are unused.
@@ -265,21 +255,21 @@ These steps are akin to
where the type code comes from
the range of unused type codes
available to custom datatypes.</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">tvm</span><span class="o">.</span><span class="n">datatype</span><span class="o">.</span><span class="n">register</span><span class="p">(</span><span class="s">'bfloat'</span><span class="p">,</span> <span class="mi">150</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">tvm</span><span class="p">.</span><span class="n">datatype</span><span class="p">.</span><span class="n">register</span><span class="p">(</span><span class="s">'bfloat'</span><span class="p">,</span> <span class="mi">150</span><span class="p">)</span>
</code></pre></div></div>
<p>The above code registers
- the <code class="highlighter-rouge">'bfloat'</code> datatype
+ the <code class="language-plaintext highlighter-rouge">'bfloat'</code> datatype
with type code 150.
This registration step
allows TVM to parse programs
which use the custom type:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">x</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">var</span><span class="p">(</span><span class="s">'x'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="p">),</span> <span class="n">dtype</span><span clas [...]
-<span class="n">y</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">var</span><span class="p">(</span><span class="s">'y'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="s">'float32'</span><span class="p">)</span>
-<span class="n">x_bfloat</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s">'custom[bfloat]16'</span><span class="p">)</span>
-<span class="n">y_bfloat</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s">'custom[bfloat]16'</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">x</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">var</span><span class="p">(</span><span class="s">'x'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="p">),</span> <span class="n">dtype</span><span clas [...]
+<span class="n">y</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">var</span><span class="p">(</span><span class="s">'y'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="s">'float32'</span><span class="p">)</span>
+<span class="n">x_bfloat</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">cast</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s">'custom[bfloat]16'</span><span class="p">)</span>
+<span class="n">y_bfloat</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">cast</span><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s">'custom[bfloat]16'</span><span class="p">)</span>
<span class="n">z_bfloat</span> <span class="o">=</span> <span class="n">x_bfloat</span> <span class="o">+</span> <span class="n">y_bfloat</span>
-<span class="n">z</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">z_bfloat</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s">'float32'</span><span class="p">)</span>
-<span class="n">program</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">Function</span><span class="p">([</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">],</span> <span class="n">z</span><span class="p">)</span>
+<span class="n">z</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">cast</span><span class="p">(</span><span class="n">z_bfloat</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s">'float32'</span><span class="p">)</span>
+<span class="n">program</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">Function</span><span class="p">([</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">],</span> <span class="n">z</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="n">program</span><span class="p">)</span>
<span class="c1"># v0.0.4
@@ -291,18 +281,18 @@ This registration step
# }
</span></code></pre></div></div>
<p>The program above
- casts <code class="highlighter-rouge">float32</code> inputs <code class="highlighter-rouge">x</code> and <code class="highlighter-rouge">y</code>
- into <code class="highlighter-rouge">bfloat</code>s,
+ casts <code class="language-plaintext highlighter-rouge">float32</code> inputs <code class="language-plaintext highlighter-rouge">x</code> and <code class="language-plaintext highlighter-rouge">y</code>
+ into <code class="language-plaintext highlighter-rouge">bfloat</code>s,
adds them,
- and casts the result back to <code class="highlighter-rouge">float32</code>.
-Once the <code class="highlighter-rouge">bfloat</code> type is registered,
- TVM is able to parse the special <code class="highlighter-rouge">dtype</code> syntax
- <code class="highlighter-rouge">custom[<typename>]</code>,
- where <code class="highlighter-rouge"><typename></code> is the name registered for the type.
+ and casts the result back to <code class="language-plaintext highlighter-rouge">float32</code>.
+Once the <code class="language-plaintext highlighter-rouge">bfloat</code> type is registered,
+ TVM is able to parse the special <code class="language-plaintext highlighter-rouge">dtype</code> syntax
+ <code class="language-plaintext highlighter-rouge">custom[<typename>]</code>,
+ where <code class="language-plaintext highlighter-rouge"><typename></code> is the name registered for the type.
This syntax also supports the usual
- <code class="highlighter-rouge"><bits>x<lanes></code> format;
- here, we use <code class="highlighter-rouge">16</code> to indicate that
- each <code class="highlighter-rouge">bfloat</code> is 16 bits wide.
+ <code class="language-plaintext highlighter-rouge"><bits>x<lanes></code> format;
+ here, we use <code class="language-plaintext highlighter-rouge">16</code> to indicate that
+ each <code class="language-plaintext highlighter-rouge">bfloat</code> is 16 bits wide.
(The number of lanes
defaults to 1.)</p>
@@ -312,7 +302,7 @@ This syntax also supports the usual
it cannot yet compile it,
as TVM does not yet understand
how to compile operations
- over the <code class="highlighter-rouge">bfloat</code> type.
+ over the <code class="language-plaintext highlighter-rouge">bfloat</code> type.
To compile these programs,
we register <em>lowering functions</em> for the custom datatype,
which help TVM convert the operations
@@ -335,22 +325,22 @@ Figure 1: The expected result of a user's registered lowering function. A loweri
<p>Figure 1 shows a common pattern.
Let’s assume we are
- interested in exploring the <code class="highlighter-rouge">bfloat</code> type,
+ interested in exploring the <code class="language-plaintext highlighter-rouge">bfloat</code> type,
and have chosen to run some workloads
- by plugging a <code class="highlighter-rouge">bfloat</code> emulation library (e.g. <a href="https://github.com/biovault/biovault_bfloat16" target="_blank">biovault_bfloat16</a>) into TVM
+ by plugging a <code class="language-plaintext highlighter-rouge">bfloat</code> emulation library (e.g. <a href="https://github.com/biovault/biovault_bfloat16" target="_blank">biovault_bfloat16</a>) into TVM
via the Bring Your Own Datatypes framework.
Our workload is a simple program
- which adds two <code class="highlighter-rouge">bfloat</code> inputs.
+ which adds two <code class="language-plaintext highlighter-rouge">bfloat</code> inputs.
Native TVM does not understand
- how to implement <code class="highlighter-rouge">bfloat</code> addition—but it doesn’t need to,
+ how to implement <code class="language-plaintext highlighter-rouge">bfloat</code> addition—but it doesn’t need to,
as we have a library implementing our datatype!
-The library contains an implementation of <code class="highlighter-rouge">bfloat</code> addition,
+The library contains an implementation of <code class="language-plaintext highlighter-rouge">bfloat</code> addition,
alongside other operators such as multiplication and square root.
-To implement this <code class="highlighter-rouge">bfloat</code> addition,
+To implement this <code class="language-plaintext highlighter-rouge">bfloat</code> addition,
we’d just like to call into our library.
Thus, our Add node should become a Call node,
- calling out to a function (call it <code class="highlighter-rouge">BFloat16Add</code>) in our library.
-To store the bits of the input <code class="highlighter-rouge">bfloat</code>s
+ calling out to a function (call it <code class="language-plaintext highlighter-rouge">BFloat16Add</code>) in our library.
+To store the bits of the input <code class="language-plaintext highlighter-rouge">bfloat</code>s
inside a type that TVM understands,
we use 16-bit unsigned integers.
The resulting program
@@ -360,16 +350,16 @@ The resulting program
<p>To achieve the above lowering,
we register a lowering function
- for <code class="highlighter-rouge">bfloat</code>:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">tvm</span><span class="o">.</span><span class="n">datatype</span><span class="o">.</span><span class="n">register_op</span><span class="p">(</span>
- <span class="n">tvm</span><span class="o">.</span><span class="n">datatype</span><span class="o">.</span><span class="n">create_lower_func</span><span class="p">(</span><span class="s">'BFloat16Add'</span><span class="p">),</span>
+ for <code class="language-plaintext highlighter-rouge">bfloat</code>:</p>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">tvm</span><span class="p">.</span><span class="n">datatype</span><span class="p">.</span><span class="n">register_op</span><span class="p">(</span>
+ <span class="n">tvm</span><span class="p">.</span><span class="n">datatype</span><span class="p">.</span><span class="n">create_lower_func</span><span class="p">(</span><span class="s">'BFloat16Add'</span><span class="p">),</span>
<span class="s">'Add'</span><span class="p">,</span> <span class="s">'llvm'</span><span class="p">,</span> <span class="s">'bfloat'</span><span class="p">)</span>
</code></pre></div></div>
<p>The above code registers
a lowering function
for a specific operator (Add),
compilation target (LLVM),
- and datatype (<code class="highlighter-rouge">bfloat</code>).
+ and datatype (<code class="language-plaintext highlighter-rouge">bfloat</code>).
The first argument
is the lowering function.
This can be any function
@@ -378,15 +368,15 @@ This can be any function
In our case,
we use a helper function
provided by the Bring Your Own Datatypes framework.
-<code class="highlighter-rouge">tvm.datatype.create_lower_func('BFloat16Add')</code>
+<code class="language-plaintext highlighter-rouge">tvm.datatype.create_lower_func('BFloat16Add')</code>
creates a lowering function
for the common pattern described above.
The resulting function
converts the arguments of the given node
- to <code class="highlighter-rouge">uint16_t</code>,
+ to <code class="language-plaintext highlighter-rouge">uint16_t</code>,
and then converts the node itself
into a call to the given function name
- (in this case, <code class="highlighter-rouge">'BFloat16Add'</code>).</p>
+ (in this case, <code class="language-plaintext highlighter-rouge">'BFloat16Add'</code>).</p>
<p>To implement a custom datatype,
the user will need to register
@@ -427,16 +417,16 @@ The Bring Your Own Datatypes framework
<h2 id="references">References</h2>
-<div class="footnotes">
+<div class="footnotes" role="doc-endnotes">
<ol>
- <li id="fn:ieee">
- <p><a href="https://standards.ieee.org/standard/754-2019.html" target="_blank">754-2019 - IEEE Standard for Floating-Point Arithmetic</a> <a href="#fnref:ieee" class="reversefootnote">↩</a></p>
+ <li id="fn:ieee" role="doc-endnote">
+ <p><a href="https://standards.ieee.org/standard/754-2019.html" target="_blank">754-2019 - IEEE Standard for Floating-Point Arithmetic</a> <a href="#fnref:ieee" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
- <li id="fn:jouppi2017datacenter">
- <p>Jouppi, Norman P., et al. “In-datacenter performance analysis of a tensor processing unit.” Proceedings of the 44th Annual International Symposium on Computer Architecture. 2017. <a href="#fnref:jouppi2017datacenter" class="reversefootnote">↩</a></p>
+ <li id="fn:jouppi2017datacenter" role="doc-endnote">
+ <p>Jouppi, Norman P., et al. “In-datacenter performance analysis of a tensor processing unit.” Proceedings of the 44th Annual International Symposium on Computer Architecture. 2017. <a href="#fnref:jouppi2017datacenter" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
- <li id="fn:tensorflowbfloat">
- <p><a href="https://cloud.google.com/tpu/docs/bfloat16" target="_blank">Using bfloat16 with TensorFlow models</a> <a href="#fnref:tensorflowbfloat" class="reversefootnote">↩</a></p>
+ <li id="fn:tensorflowbfloat" role="doc-endnote">
+ <p><a href="https://cloud.google.com/tpu/docs/bfloat16" target="_blank">Using bfloat16 with TensorFlow models</a> <a href="#fnref:tensorflowbfloat" class="reversefootnote" role="doc-backlink">↩</a></p>
</li>
</ol>
</div>
@@ -446,37 +436,41 @@ The Bring Your Own Datatypes framework
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2020/06/04/tinyml-how-tvm-is-taming-tiny.html b/2020/06/04/tinyml-how-tvm-is-taming-tiny.html
index 09bca33..b26a39e 100644
--- a/2020/06/04/tinyml-how-tvm-is-taming-tiny.html
+++ b/2020/06/04/tinyml-how-tvm-is-taming-tiny.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>TinyML - How TVM is Taming Tiny</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -182,32 +172,32 @@ A standard µTVM setup, where the host communicates with the device via JTAG.</p
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">OPENOCD_SERVER_ADDR</span> <span class="o">=</span> <span class="s">'127.0.0.1'</span>
<span class="n">OPENOCD_SERVER_PORT</span> <span class="o">=</span> <span class="mi">6666</span>
-<span class="n">TARGET</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">target</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="s">'c -device=micro_dev'</span><span class="p">)</span>
-<span class="n">DEV_CONFIG</span> <span class="o">=</span> <span class="n">stm32f746xx</span><span class="o">.</span><span class="n">default_config</span><span class="p">(</span><span class="n">OPENOCD_SERVER_ADDR</span><span class="p">,</span> <span class="n">OPENOCD_SERVER_PORT</span><span class="p">)</span>
+<span class="n">TARGET</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">target</span><span class="p">.</span><span class="n">create</span><span class="p">(</span><span class="s">'c -device=micro_dev'</span><span class="p">)</span>
+<span class="n">DEV_CONFIG</span> <span class="o">=</span> <span class="n">stm32f746xx</span><span class="p">.</span><span class="n">default_config</span><span class="p">(</span><span class="n">OPENOCD_SERVER_ADDR</span><span class="p">,</span> <span class="n">OPENOCD_SERVER_PORT</span><span class="p">)</span>
<span class="n">module</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">get_cifar10_cnn</span><span class="p">()</span>
-<span class="k">with</span> <span class="n">micro</span><span class="o">.</span><span class="n">Session</span><span class="p">(</span><span class="n">device_config</span><span class="p">)</span> <span class="k">as</span> <span class="n">sess</span><span class="p">:</span>
- <span class="n">graph</span><span class="p">,</span> <span class="n">c_module</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">module</span><span class="p">[</span><span class="s">'main'</span><span class="p">],</span> <span class="n">target</span><span class="o">=</span><span class="n">TARGET</span><span class="p">,</span> <span cl [...]
- <span class="n">micro_mod</span> <span class="o">=</span> <span class="n">micro</span><span class="o">.</span><span class="n">create_micro_mod</span><span class="p">(</span><span class="n">c_module</span><span class="p">,</span> <span class="n">DEV_CONFIG</span><span class="p">)</span>
- <span class="n">graph_mod</span> <span class="o">=</span> <span class="n">graph_runtime</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">graph</span><span class="p">,</span> <span class="n">micro_mod</span><span class="p">,</span> <span class="n">ctx</span><span class="o">=</span><span class="n">tvm</span><span class="o">.</span><span class="n">micro_dev</span><span class="p">(</span><span class="mi">0</span><span class="p">))</span>
- <span class="n">graph_mod</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="n">data_np</span><span class="p">)</span>
- <span class="n">prediction</span> <span class="o">=</span> <span class="n">CIFAR10_CLASSES</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">graph_mod</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">())]</span>
- <span class="k">print</span><span class="p">(</span><span class="n">f</span><span class="s">'prediction was {prediction}'</span><span class="p">)</span>
+<span class="k">with</span> <span class="n">micro</span><span class="p">.</span><span class="n">Session</span><span class="p">(</span><span class="n">device_config</span><span class="p">)</span> <span class="k">as</span> <span class="n">sess</span><span class="p">:</span>
+ <span class="n">graph</span><span class="p">,</span> <span class="n">c_module</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">module</span><span class="p">[</span><span class="s">'main'</span><span class="p">],</span> <span class="n">target</span><span class="o">=</span><span class="n">TARGET</span><span class="p">,</span> <span cl [...]
+ <span class="n">micro_mod</span> <span class="o">=</span> <span class="n">micro</span><span class="p">.</span><span class="n">create_micro_mod</span><span class="p">(</span><span class="n">c_module</span><span class="p">,</span> <span class="n">DEV_CONFIG</span><span class="p">)</span>
+ <span class="n">graph_mod</span> <span class="o">=</span> <span class="n">graph_runtime</span><span class="p">.</span><span class="n">create</span><span class="p">(</span><span class="n">graph</span><span class="p">,</span> <span class="n">micro_mod</span><span class="p">,</span> <span class="n">ctx</span><span class="o">=</span><span class="n">tvm</span><span class="p">.</span><span class="n">micro_dev</span><span class="p">(</span><span class="mi">0</span><span class="p">))</span>
+ <span class="n">graph_mod</span><span class="p">.</span><span class="n">run</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="n">data_np</span><span class="p">)</span>
+ <span class="n">prediction</span> <span class="o">=</span> <span class="n">CIFAR10_CLASSES</span><span class="p">[</span><span class="n">np</span><span class="p">.</span><span class="n">argmax</span><span class="p">(</span><span class="n">graph_mod</span><span class="p">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">).</span><span class="n">asnumpy</span><span class="p">())]</span>
+ <span class="k">print</span><span class="p">(</span><span class="s">f'prediction was </span><span class="si">{</span><span class="n">prediction</span><span class="si">}</span><span class="s">'</span><span class="p">)</span>
</code></pre></div></div>
-<p>Below are the performance results of MicroTVM, compared with <a href="https://github.com/ARM-software/CMSIS_5/releases/tag/5.6.0">CMSIS-NN version 5.7.0</a> (commit <code class="highlighter-rouge">a65b7c9a</code>), a hand-optimized library of ML kernels.</p>
+<p>Below are the performance results of MicroTVM, compared with <a href="https://github.com/ARM-software/CMSIS_5/releases/tag/5.6.0">CMSIS-NN version 5.7.0</a> (commit <code class="language-plaintext highlighter-rouge">a65b7c9a</code>), a hand-optimized library of ML kernels.</p>
<p style="text-align: center"><img src="/images/microtvm/post-2020-05-28/cifar10-int-8-cnn.png" alt="/images/microtvm/post-2020-05-28/cifar10-int-8-cnn.png" width="60%" /><br /></p>
<p>As we can see, the out-of-the-box performance isn’t great, but this is where <a href="https://dl.acm.org/doi/10.5555/3327144.3327258">AutoTVM</a> comes to the rescue. We can write a schedule template for our device, do a round of autotuning, then achieve significantly better results. To plug in our autotuned results, we only need to replace this line:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">graph</span><span class="p">,</span> <span class="n">c_module</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">module</span><span class="p">[</span><span class="s">'main'</span><span class="p">],</span> <span class="n">t [...]
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">graph</span><span class="p">,</span> <span class="n">c_module</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">module</span><span class="p">[</span><span class="s">'main'</span><span class="p">],</span> <span class="n">t [...]
</code></pre></div></div>
<p>with these lines:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">with</span> <span class="n">TARGET</span><span class="p">,</span> <span class="n">autotvm</span><span class="o">.</span><span class="n">apply_history_best</span><span class="p">(</span><span class="n">TUNING_RESULTS_FILE</span><span class="p">):</span>
- <span class="n">graph</span><span class="p">,</span> <span class="n">c_module</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">module</span><span class="p">[</span><span class="s">'main'</span><span class="p">],</span> <span class="n">target</span><span class="o">=</span><span class="n">TARGET</span><span class="p">,</span> <span c [...]
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">with</span> <span class="n">TARGET</span><span class="p">,</span> <span class="n">autotvm</span><span class="p">.</span><span class="n">apply_history_best</span><span class="p">(</span><span class="n">TUNING_RESULTS_FILE</span><span class="p">):</span>
+ <span class="n">graph</span><span class="p">,</span> <span class="n">c_module</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">module</span><span class="p">[</span><span class="s">'main'</span><span class="p">],</span> <span class="n">target</span><span class="o">=</span><span class="n">TARGET</span><span class="p">,</span> <span c [...]
</code></pre></div></div>
<p>And our results now look like this:</p>
@@ -240,7 +230,7 @@ The µTVM Device Memory Layout in RAM</p>
</span> <span class="s">'text'</span><span class="p">:</span> <span class="mi">18000</span><span class="p">,</span>
<span class="s">'rodata'</span><span class="p">:</span> <span class="mi">100</span><span class="p">,</span>
<span class="s">'data'</span><span class="p">:</span> <span class="mi">100</span><span class="p">,</span>
- <span class="o">...</span>
+ <span class="p">...</span>
<span class="p">},</span>
<span class="s">'word_size'</span><span class="p">:</span> <span class="mi">4</span><span class="p">,</span> <span class="c1"># device word size
</span> <span class="s">'thumb_mode'</span><span class="p">:</span> <span class="bp">True</span><span class="p">,</span> <span class="c1"># whether to use ARM's thumb ISA
@@ -276,16 +266,16 @@ The µTVM Device Memory Layout in RAM</p>
<h2 id="device-sessions">Device Sessions</h2>
-<p>Given the networked nature of microcontroller interaction, we slightly deviate from standard TVM code by introducing the concept of <code class="highlighter-rouge">MicroSession</code>.</p>
+<p>Given the networked nature of microcontroller interaction, we slightly deviate from standard TVM code by introducing the concept of <code class="language-plaintext highlighter-rouge">MicroSession</code>.</p>
<p>Every piece of functionality in µTVM relies on having an open session with the target device. If you’re familiar with TVM, you may have noticed a line of code that deviates from the norm in our first code snippet—-namely, this one:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="o">...</span>
-<span class="k">with</span> <span class="n">micro</span><span class="o">.</span><span class="n">Session</span><span class="p">(</span><span class="n">device_config</span><span class="p">)</span> <span class="k">as</span> <span class="n">sess</span><span class="p">:</span>
- <span class="o">...</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="p">...</span>
+<span class="k">with</span> <span class="n">micro</span><span class="p">.</span><span class="n">Session</span><span class="p">(</span><span class="n">device_config</span><span class="p">)</span> <span class="k">as</span> <span class="n">sess</span><span class="p">:</span>
+ <span class="p">...</span>
</code></pre></div></div>
-<p>Every line inside this <code class="highlighter-rouge">with</code> block can call functions in µTVM, with the context being the device specified by <code class="highlighter-rouge">device_config</code>. This line is doing a number of things under the hood, so let’s unpack it.</p>
+<p>Every line inside this <code class="language-plaintext highlighter-rouge">with</code> block can call functions in µTVM, with the context being the device specified by <code class="language-plaintext highlighter-rouge">device_config</code>. This line is doing a number of things under the hood, so let’s unpack it.</p>
<p>First, it initializes a connection with your device, using whichever communication method you specified (usually OpenOCD). The µTVM device runtime is then cross-compiled, using whichever cross-compiler you specified. Finally, space for the compiled binary is allocated by the host, and the binary is loaded onto the device using the opened connection.</p>
@@ -295,14 +285,14 @@ The µTVM Device Memory Layout in RAM</p>
<p>One of the core abstractions in TVM is that of a module. A module stores a set of related functions for a particular device/runtime target. Given that microcontrollers don’t normally have operating systems, µTVM needs to do a lot of extra work to maintain this high-level abstraction. To see what’s going on, we’ll trace through the process of creating and loading a µTVM-compatible module.</p>
-<p>Suppose we have a <code class="highlighter-rouge">micro.Session</code> open with our device and a TVM schedule that implements 2D convolution. If we want to load it onto our microcontroller, we need it to emit C code. To do so, we just need to set the <code class="highlighter-rouge">target</code> in either <code class="highlighter-rouge">tvm.build</code> or <code class="highlighter-rouge">relay.build</code>. Example:</p>
+<p>Suppose we have a <code class="language-plaintext highlighter-rouge">micro.Session</code> open with our device and a TVM schedule that implements 2D convolution. If we want to load it onto our microcontroller, we need it to emit C code. To do so, we just need to set the <code class="language-plaintext highlighter-rouge">target</code> in either <code class="language-plaintext highlighter-rouge">tvm.build</code> or <code class="language-plaintext highlighter-rouge">relay.build</code>. [...]
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">graph</span><span class="p">,</span> <span class="n">c_module</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">module</span><span class="p">[</span><span class="s">'main'</span><span class="p">],</span> <span class="n">t [...]
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">graph</span><span class="p">,</span> <span class="n">c_module</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">module</span><span class="p">[</span><span class="s">'main'</span><span class="p">],</span> <span class="n">t [...]
</code></pre></div></div>
-<p>By setting the target like so, the build process runs through our C code generation backend. However, the resulting C module still resides on the host machine. In order to load it onto the device, we run it through one of the core functions in the µTVM infrastructure: <code class="highlighter-rouge">create_micro_mod</code>. Example:</p>
+<p>By setting the target like so, the build process runs through our C code generation backend. However, the resulting C module still resides on the host machine. In order to load it onto the device, we run it through one of the core functions in the µTVM infrastructure: <code class="language-plaintext highlighter-rouge">create_micro_mod</code>. Example:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">micro_mod</span> <span class="o">=</span> <span class="n">micro</span><span class="o">.</span><span class="n">create_micro_mod</span><span class="p">(</span><span class="n">c_module</span><span class="p">,</span> <span class="n">DEV_CONFIG</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">micro_mod</span> <span class="o">=</span> <span class="n">micro</span><span class="p">.</span><span class="n">create_micro_mod</span><span class="p">(</span><span class="n">c_module</span><span class="p">,</span> <span class="n">DEV_CONFIG</span><span class="p">)</span>
</code></pre></div></div>
<p>The line above cross-compiles the C source within the module, allocates room for the resulting binary (so it can coexist with the runtime in device memory), then sends each section of the binary to its allocated slot on the device. Once the module binary is snug in device memory, function pointers within the binary are patched to give the module access to helper functions in the device runtime (e.g., for allocating scratchpads).</p>
@@ -317,12 +307,12 @@ The µTVM Device Memory Layout in RAM</p>
<p>If we want to call an operator, we first need some tensors as arguments:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">data_np</span><span class="p">,</span> <span class="n">kernel_np</span> <span class="o">=</span> <span class="n">get_conv_inputs</span><span class="p">()</span>
-<span class="n">ctx</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">micro_dev</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
-<span class="n">data</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">data_np</span><span class="p">,</span> <span class="n">ctx</span><span class="o">=</span><span class="n">ctx</span><span class="p">)</span>
-<span class="n">kernel</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">kernel_np</span><span class="p">,</span> <span class="n">ctx</span><span class="o">=</span><span class="n">ctx</span><span class="p">)</span>
+<span class="n">ctx</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">micro_dev</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
+<span class="n">data</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span><span class="n">data_np</span><span class="p">,</span> <span class="n">ctx</span><span class="o">=</span><span class="n">ctx</span><span class="p">)</span>
+<span class="n">kernel</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span><span class="n">kernel_np</span><span class="p">,</span> <span class="n">ctx</span><span class="o">=</span><span class="n">ctx</span><span class="p">)</span>
</code></pre></div></div>
-<p>Based on its data type (e.g., <code class="highlighter-rouge">int8</code>, <code class="highlighter-rouge">float32</code>, etc.) and shape, each tensor’s size in bytes is calculated, and the host allocates a region of memory on the device’s heap. The tensor’s data is then loaded into the allocated region.</p>
+<p>Based on its data type (e.g., <code class="language-plaintext highlighter-rouge">int8</code>, <code class="language-plaintext highlighter-rouge">float32</code>, etc.) and shape, each tensor’s size in bytes is calculated, and the host allocates a region of memory on the device’s heap. The tensor’s data is then loaded into the allocated region.</p>
<h2 id="function-calls">Function Calls</h2>
@@ -352,13 +342,13 @@ The µTVM Device Memory Layout in RAM</p>
<span class="p">}</span> <span class="n">UTVMTask</span><span class="p">;</span>
</code></pre></div></div>
-<p>In the strict setting, there is a single global <code class="highlighter-rouge">UTVMTask</code> instance that we, from the host side, write into. Once we have written to the task, the runtime has everything it needs to execute the function, and we can begin execution at the runtime’s entry point. The runtime will perform some lightweight initialization, run our operator, then return control to the host.</p>
+<p>In the strict setting, there is a single global <code class="language-plaintext highlighter-rouge">UTVMTask</code> instance that we, from the host side, write into. Once we have written to the task, the runtime has everything it needs to execute the function, and we can begin execution at the runtime’s entry point. The runtime will perform some lightweight initialization, run our operator, then return control to the host.</p>
<h3 id="lazy-execution">Lazy Execution</h3>
<p>In practice, executing operators as soon as the user requests to becomes prohibitively expensive, as communication overhead begins to dominate. We can improve the throughput of our system by delaying evaluation until the user wants the results of the call.</p>
-<p>From an implementation standpoint, instead of eagerly serializing argument metadata and <code class="highlighter-rouge">UTVMTask</code> data, we now need to accumulate function call metadata on the host side, before flushing it to the device. The device runtime also needs a few changes: (1) we must now have a global array of <code class="highlighter-rouge">UTVMTask</code> and (2) we need to loop through and execute each task in order.</p>
+<p>From an implementation standpoint, instead of eagerly serializing argument metadata and <code class="language-plaintext highlighter-rouge">UTVMTask</code> data, we now need to accumulate function call metadata on the host side, before flushing it to the device. The device runtime also needs a few changes: (1) we must now have a global array of <code class="language-plaintext highlighter-rouge">UTVMTask</code> and (2) we need to loop through and execute each task in order.</p>
<h2 id="autotvm-with-microtvm">AutoTVM with MicroTVM</h2>
@@ -397,7 +387,7 @@ Diagram of CIFAR-10 CNN</p>
<h2 id="methodology">Methodology</h2>
-<p>In our experiments, we use TVM from HEAD (commit <code class="highlighter-rouge">9fa8341</code>), version 5.7.0 of CMSIS-NN (commit <code class="highlighter-rouge">a65b7c9a</code>), version 1.16.0 of STM32CubeF7, and GCC from Arm’s GNU Tools for Arm Embedded Processors 9-2019-q4-major 9.2.1 toolchain (revision 277599). The host machine used in our experiments runs Ubuntu Linux 18.04.4 LTS and sports an AMD Ryzen Threadripper 2990WX 32-Core Processor with 62GB of RAM. All evaluation [...]
+<p>In our experiments, we use TVM from HEAD (commit <code class="language-plaintext highlighter-rouge">9fa8341</code>), version 5.7.0 of CMSIS-NN (commit <code class="language-plaintext highlighter-rouge">a65b7c9a</code>), version 1.16.0 of STM32CubeF7, and GCC from Arm’s GNU Tools for Arm Embedded Processors 9-2019-q4-major 9.2.1 toolchain (revision 277599). The host machine used in our experiments runs Ubuntu Linux 18.04.4 LTS and sports an AMD Ryzen Threadripper 2990WX 32-Core Proces [...]
<h3 id="arm-specific-optimizations">Arm-Specific Optimizations</h3>
@@ -415,7 +405,7 @@ Diagram from CMSIS-NN paper showing a 2x2 matrix multiplication microkernel</p>
<p>There are certainly other optimizations we could pull from CMSIS-NN to close the gap even further:</p>
<ul>
- <li>Batch expansion of <code class="highlighter-rouge">int8</code> weights into <code class="highlighter-rouge">int16</code>, to cut down on duplicate expansion for SIMD</li>
+ <li>Batch expansion of <code class="language-plaintext highlighter-rouge">int8</code> weights into <code class="language-plaintext highlighter-rouge">int16</code>, to cut down on duplicate expansion for SIMD</li>
<li>Splitting convolution into 3x3 tiles to reduce padding checks</li>
</ul>
@@ -430,10 +420,10 @@ Diagram from CMSIS-NN paper showing a 2x2 matrix multiplication microkernel</p>
<p><a href="https://github.com/areusch/microtvm-blogpost-eval">https://github.com/areusch/microtvm-blogpost-eval</a></p>
<p style="text-align: center"><img src="/images/microtvm/post-2020-05-28/autotuned-cifar10-int-8-cnn.png" alt="/images/microtvm/post-2020-05-28/autotuned-cifar10-int-8-cnn.png" width="60%" /><br />
-<code class="highlighter-rouge">int8</code>-quantized CIFAR-10 CNN comparison on an Arm STM32F746NG (re-posted from above)</p>
+<code class="language-plaintext highlighter-rouge">int8</code>-quantized CIFAR-10 CNN comparison on an Arm STM32F746NG (re-posted from above)</p>
<p style="text-align: center"><img src="/images/microtvm/post-2020-05-28/autotuned-cifar10-int-8-cnn-x86.png" alt="/images/microtvm/post-2020-05-28/autotuned-cifar10-int-8-cnn-x86.png" width="60%" /><br />
-<code class="highlighter-rouge">int8</code>-quantized CIFAR-10 CNN comparison on µTVM’s emulated host device</p>
+<code class="language-plaintext highlighter-rouge">int8</code>-quantized CIFAR-10 CNN comparison on µTVM’s emulated host device</p>
<p>On the Arm STM32-series board, we were able to improve performance by ~2x compared to the initial untuned operators, and we achieved results much closer to CMSIS-NN. Additionally, we were able to significantly improve performance on the host emulated device. Though the x86 <strong><em>numbers</em></strong> don’t mean much, they show we can use the same infrastructure (µTVM) to optimize performance on vastly different architectures.</p>
@@ -469,37 +459,41 @@ Diagram from CMSIS-NN paper showing a 2x2 matrix multiplication microkernel</p>
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2020/07/14/bert-pytorch-tvm.html b/2020/07/14/bert-pytorch-tvm.html
index 66f37bd..4196bda 100644
--- a/2020/07/14/bert-pytorch-tvm.html
+++ b/2020/07/14/bert-pytorch-tvm.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Bridging PyTorch and TVM</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -191,9 +181,9 @@ specifically the part until we have a traced model.</p>
<p>The PyTorch traced model takes around 0.65-0.7 seconds for 100 runs on my AMD Radeon VII with the example inputs, which means 6.5-7ms per run.
We can try to see if we can use TVM get faster. Let converting our model to TVM is a breeze:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">shape_list</span> <span class="o">=</span> <span class="p">[(</span><span class="n">i</span><span class="o">.</span><span class="n">debugName</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s">'.'</span><span class="p">)[</span><span class="mi">0</span><span class="p">],</span> <span class="n">i</span><s [...]
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">shape_list</span> <span class="o">=</span> <span class="p">[(</span><span class="n">i</span><span class="p">.</span><span class="n">debugName</span><span class="p">().</span><span class="n">split</span><span class="p">(</span><span class="s">'.'</span><span class="p">)[</span><span class="mi">0</span><span class="p">],</span> <span class="n">i</span><span class="p">.</span>< [...]
-<span class="n">mod_bert</span><span class="p">,</span> <span class="n">params_bert</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">frontend</span><span class="o">.</span><span class="n">pytorch</span><span class="o">.</span><span class="n">from_pytorch</span><span class="p">(</span><span class="n">traced_model</span><span class="p">,</span>
+<span class="n">mod_bert</span><span class="p">,</span> <span class="n">params_bert</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">frontend</span><span class="p">.</span><span class="n">pytorch</span><span class="p">.</span><span class="n">from_pytorch</span><span class="p">(</span><span class="n">traced_model</span><span class="p">,</span>
<span class="n">shape_list</span><span class="p">,</span> <span class="n">default_dtype</span><span class="o">=</span><span class="s">"float32"</span><span class="p">)</span>
</code></pre></div></div>
@@ -203,24 +193,24 @@ We can now build and run it. Building follows the standard TVM recipe. We also c
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">target</span> <span class="o">=</span> <span class="s">'rocm -model=gfx906'</span> <span class="c1"># use what matches your GPU
</span>
<span class="n">target_host</span> <span class="o">=</span> <span class="s">'llvm'</span>
-<span class="n">ctx</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">context</span><span class="p">(</span><span class="n">target</span><span class="p">)</span>
+<span class="n">ctx</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">context</span><span class="p">(</span><span class="n">target</span><span class="p">)</span>
-<span class="n">tt_a</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">tokens_tensor</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">ctx</span><span class="p">)</span>
-<span class="n">st_a</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">segments_tensors</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">ctx</span><span class="p">)</span>
+<span class="n">tt_a</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span><span class="n">tokens_tensor</span><span class="p">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">ctx</span><span class="p">)</span>
+<span class="n">st_a</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">array</span><span class="p">(</span><span class="n">segments_tensors</span><span class="p">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">ctx</span><span class="p">)</span>
</code></pre></div></div>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">backend</span><span class="o">.</span><span class="n">compile_engine</span><span class="o">.</span><span class="n">get</span><span class="p">()</span><span class="o">.</span><span class="n">clear</span><span class="p">()</span> <span class="c1"># just to be sure, see https:/ [...]
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">backend</span><span class="p">.</span><span class="n">compile_engine</span><span class="p">.</span><span class="n">get</span><span class="p">().</span><span class="n">clear</span><span class="p">()</span> <span class="c1"># just to be sure, see https://github.com/apache/incu [...]
</span>
-<span class="k">with</span> <span class="n">tvm</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="n">PassContext</span><span class="p">(</span><span class="n">opt_level</span><span class="o">=</span><span class="mi">3</span><span class="p">):</span>
- <span class="n">graph</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod_bert</span><span class="p">,</span>
+<span class="k">with</span> <span class="n">tvm</span><span class="p">.</span><span class="n">transform</span><span class="p">.</span><span class="n">PassContext</span><span class="p">(</span><span class="n">opt_level</span><span class="o">=</span><span class="mi">3</span><span class="p">):</span>
+ <span class="n">graph</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod_bert</span><span class="p">,</span>
<span class="n">target</span><span class="o">=</span><span class="n">target</span><span class="p">,</span>
<span class="n">target_host</span><span class="o">=</span><span class="n">target_host</span><span class="p">,</span>
<span class="n">params</span><span class="o">=</span><span class="n">params_bert</span><span class="p">)</span>
-<span class="n">module</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">contrib</span><span class="o">.</span><span class="n">graph_runtime</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">graph</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
+<span class="n">module</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">contrib</span><span class="p">.</span><span class="n">graph_runtime</span><span class="p">.</span><span class="n">create</span><span class="p">(</span><span class="n">graph</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
</code></pre></div></div>
<p>This will warn us a few times times:</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code> WARNING:autotvm:Cannot find config for ... batch_matmul.cuda .... A fallback configuration is used, which may bring great performance regression.
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code> WARNING:autotvm:Cannot find config for ... batch_matmul.cuda .... A fallback configuration is used, which may bring great performance regression.
</code></pre></div></div>
<p>Uh oh, <em>may bring great performance regression</em>. Let us see.</p>
@@ -236,8 +226,8 @@ We can now build and run it. Building follows the standard TVM recipe. We also c
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">x</span><span class="p">():</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">100</span><span class="p">):</span>
- <span class="n">module</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
- <span class="n">ctx</span><span class="o">.</span><span class="n">sync</span><span class="p">()</span>
+ <span class="n">module</span><span class="p">.</span><span class="n">run</span><span class="p">()</span>
+ <span class="n">ctx</span><span class="p">.</span><span class="n">sync</span><span class="p">()</span>
<span class="n">x</span><span class="p">()</span>
<span class="o">%</span><span class="n">timeit</span> <span class="n">x</span><span class="p">()</span>
</code></pre></div></div>
@@ -257,22 +247,22 @@ Now it’s in the region of 6.5-7ms per run, similar to PyTorch. This is what we
<p>Let us take a closer look at what’s going on in BERT.</p>
-<p>Like many deep learning models, BERT comes with a bit some prologue (vocabulary embeddings) and epilogue (pooling) and the bulk is organized into similar-looking blocks, here we have 12 <code class="highlighter-rouge">BertLayer</code> modules.
-The <code class="highlighter-rouge">attention_mask</code> is jsut to prevent BERT from looking at the answer when dealing with the question.</p>
+<p>Like many deep learning models, BERT comes with a bit some prologue (vocabulary embeddings) and epilogue (pooling) and the bulk is organized into similar-looking blocks, here we have 12 <code class="language-plaintext highlighter-rouge">BertLayer</code> modules.
+The <code class="language-plaintext highlighter-rouge">attention_mask</code> is jsut to prevent BERT from looking at the answer when dealing with the question.</p>
<p><img src="/images/bert-pytorch/bert_model.svg" alt="Bert Model" width="100%" /></p>
<p>So let us zoom in and look at a BertLayer in detail, since that ultimately is what we need make fast.
-As we see in the net diagram, the main part of the <code class="highlighter-rouge">BertLayer</code> module is a submodule <code class="highlighter-rouge">BertSelfAttention</code>.</p>
+As we see in the net diagram, the main part of the <code class="language-plaintext highlighter-rouge">BertLayer</code> module is a submodule <code class="language-plaintext highlighter-rouge">BertSelfAttention</code>.</p>
<p><img src="/images/bert-pytorch/bert_layer.svg" alt="BertLayer" width="100%" /></p>
-<p>Now the <code class="highlighter-rouge">BertSelfAttention</code> captures the famed self-attention mechanism that is the hallmark of transformer models. (I cannot recommend Sascha Rush’s <a href="http://nlp.seas.harvard.edu/2018/04/03/attention.html">Annotated Transformer</a> enough as a detailed walkthrough.)</p>
+<p>Now the <code class="language-plaintext highlighter-rouge">BertSelfAttention</code> captures the famed self-attention mechanism that is the hallmark of transformer models. (I cannot recommend Sascha Rush’s <a href="http://nlp.seas.harvard.edu/2018/04/03/attention.html">Annotated Transformer</a> enough as a detailed walkthrough.)</p>
<h2 id="putting-the-bertlayer-under-the-microscope">Putting the BertLayer under the Microscope</h2>
<p>If we want go into details, we should want to run a BertLayer individually.
-We grab the inputs of a BertLayer (see the Notebook for how) and convert a single <code class="highlighter-rouge">BertLayer</code> to TVM as we did for the entire model.</p>
+We grab the inputs of a BertLayer (see the Notebook for how) and convert a single <code class="language-plaintext highlighter-rouge">BertLayer</code> to TVM as we did for the entire model.</p>
<p>To look at the TVM module, we define a little visualization helper (loosely based on TVM <a href="https://github.com/apache/incubator-tvm/pull/4370">PR#4370</a>).</p>
@@ -281,9 +271,9 @@ We grab the inputs of a BertLayer (see the Notebook for how) and convert a singl
<span class="k">def</span> <span class="nf">collect_ops</span><span class="p">(</span><span class="n">node</span><span class="p">):</span>
<span class="n">ops</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">visitor</span><span class="p">(</span><span class="n">e</span><span class="p">):</span>
- <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">ir</span><span class="o">.</span><span class="n">Op</span><span class="p">):</span>
- <span class="n">ops</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">e</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
- <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">analysis</span><span class="o">.</span><span class="n">post_order_visit</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">visitor</span><span class="p">)</span>
+ <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">ir</span><span class="p">.</span><span class="n">Op</span><span class="p">):</span>
+ <span class="n">ops</span><span class="p">.</span><span class="n">add</span><span class="p">(</span><span class="n">e</span><span class="p">.</span><span class="n">name</span><span class="p">)</span>
+ <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">analysis</span><span class="p">.</span><span class="n">post_order_visit</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">visitor</span><span class="p">)</span>
<span class="k">return</span> <span class="n">ops</span>
<span class="c1"># node_dict maps a Relay node to an index (node ID)
@@ -293,105 +283,105 @@ We grab the inputs of a BertLayer (see the Notebook for how) and convert a singl
<span class="n">node_dict</span><span class="p">[</span><span class="n">node</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">node_dict</span><span class="p">)</span>
<span class="n">node_dict</span> <span class="o">=</span> <span class="p">{}</span>
- <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">analysis</span><span class="o">.</span><span class="n">post_order_visit</span><span class="p">(</span><span class="n">expr</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">_traverse_expr</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">node_dict</ [...]
+ <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">analysis</span><span class="p">.</span><span class="n">post_order_visit</span><span class="p">(</span><span class="n">expr</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">_traverse_expr</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">node_dict</ [...]
<span class="n">relayviz_nodes</span> <span class="o">=</span> <span class="p">[]</span>
- <span class="n">dot</span> <span class="o">=</span> <span class="n">graphviz</span><span class="o">.</span><span class="n">Digraph</span><span class="p">(</span><span class="nb">format</span><span class="o">=</span><span class="s">'svg'</span><span class="p">,</span> <span class="p">)</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">attr</span><span class="p">(</span><span class="s">'node'</span><span class="p">,</span> <span class="n">shape</span> <span class="o">=</span> <span class="s">'box'</span><span class="p">)</span>
+ <span class="n">dot</span> <span class="o">=</span> <span class="n">graphviz</span><span class="p">.</span><span class="n">Digraph</span><span class="p">(</span><span class="nb">format</span><span class="o">=</span><span class="s">'svg'</span><span class="p">,</span> <span class="p">)</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">attr</span><span class="p">(</span><span class="s">'node'</span><span class="p">,</span> <span class="n">shape</span> <span class="o">=</span> <span class="s">'box'</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">to_str</span><span class="p">(</span><span class="n">node</span><span class="p">):</span>
- <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">Constant</span><span class="p">):</span>
- <span class="k">return</span> <span class="nb">repr</span><span class="p">(</span><span class="n">node</span><span class="p">)</span><span class="o">.</span><span class="n">lstrip</span><span class="p">(</span><span class="s">'Constant('</span><span class="p">)[:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
+ <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">Constant</span><span class="p">):</span>
+ <span class="k">return</span> <span class="nb">repr</span><span class="p">(</span><span class="n">node</span><span class="p">).</span><span class="n">lstrip</span><span class="p">(</span><span class="s">'Constant('</span><span class="p">)[:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="nb">NotImplementedError</span><span class="p">(</span><span class="s">"to_str:"</span> <span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="n">node</span><span class="p">))</span>
<span class="k">def</span> <span class="nf">is_small_const</span><span class="p">(</span><span class="n">c</span><span class="p">):</span>
- <span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="n">collapse_small</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">c</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">Constant</span><span class="p">)):</span>
+ <span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="n">collapse_small</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">c</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">Constant</span><span class="p">)):</span>
<span class="k">return</span> <span class="bp">False</span>
- <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">data</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">runtime</span><span class="o">.</span><span class="n">ndarray</span><span class="o">.</span><span class="n">NDArray</span><span class="p">):</span>
- <span class="k">return</span> <span class="n">numpy</span><span class="o">.</span><span class="n">prod</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o"><</span> <span class="mi">10</span>
+ <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">c</span><span class="p">.</span><span class="n">data</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">runtime</span><span class="p">.</span><span class="n">ndarray</span><span class="p">.</span><span class="n">NDArray</span><span class="p">):</span>
+ <span class="k">return</span> <span class="n">numpy</span><span class="p">.</span><span class="n">prod</span><span class="p">(</span><span class="n">c</span><span class="p">.</span><span class="n">data</span><span class="p">.</span><span class="n">shape</span><span class="p">)</span> <span class="o"><</span> <span class="mi">10</span>
<span class="k">return</span> <span class="bp">True</span>
<span class="c1"># Sort by node ID
-</span> <span class="k">for</span> <span class="n">node</span><span class="p">,</span> <span class="n">node_id</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">node_dict</span><span class="o">.</span><span class="n">items</span><span class="p">(),</span> <span class="n">key</span><span class="o">=</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="p">[</span><s [...]
- <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">Function</span><span class="p">):</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="s">'Function'</span><span class="p">,</span> <span class="o">**</span><span class="n">node_attr_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">node</span><span class="o">.</span><span class="n">body</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">))</span>
- <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">Var</span><span class="p">):</span>
- <span class="k">if</span> <span class="n">node</span><span class="o">.</span><span class="n">type_annotation</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
- <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">node</span><span class="o">.</span><span class="n">type_annotation</span><span class="p">,</span> <span class="s">'shape'</span><span class="p">):</span>
- <span class="n">shape</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">([</span><span class="nb">int</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">node</span><span class="o">.</span><span class="n">type_annotation</span><span class="o">.</span><span class="n">shape</span><span class="p">])</span>
- <span class="n">dtype</span> <span class="o">=</span> <span class="n">node</span><span class="o">.</span><span class="n">type_annotation</span><span class="o">.</span><span class="n">dtype</span>
- <span class="n">typstr</span> <span class="o">=</span> <span class="s">'Tensor[{}, {}]'</span><span class="o">.</span><span class="nb">format</span><span class="p">(</span><span class="n">shape</span><span class="p">,</span> <span class="n">dtype</span><span class="p">)</span>
+</span> <span class="k">for</span> <span class="n">node</span><span class="p">,</span> <span class="n">node_id</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">node_dict</span><span class="p">.</span><span class="n">items</span><span class="p">(),</span> <span class="n">key</span><span class="o">=</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="p">[</span><s [...]
+ <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">Function</span><span class="p">):</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="s">'Function'</span><span class="p">,</span> <span class="o">**</span><span class="n">node_attr_dict</span><span class="p">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">node</span><span class="p">.</span><span class="n">body</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">))</span>
+ <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">Var</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">node</span><span class="p">.</span><span class="n">type_annotation</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
+ <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">node</span><span class="p">.</span><span class="n">type_annotation</span><span class="p">,</span> <span class="s">'shape'</span><span class="p">):</span>
+ <span class="n">shape</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">([</span><span class="nb">int</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">node</span><span class="p">.</span><span class="n">type_annotation</span><span class="p">.</span><span class="n">shape</span><span class="p">])</span>
+ <span class="n">dtype</span> <span class="o">=</span> <span class="n">node</span><span class="p">.</span><span class="n">type_annotation</span><span class="p">.</span><span class="n">dtype</span>
+ <span class="n">typstr</span> <span class="o">=</span> <span class="s">'Tensor[{}, {}]'</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span><span class="n">shape</span><span class="p">,</span> <span class="n">dtype</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
- <span class="n">typstr</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">node</span><span class="o">.</span><span class="n">type_annotation</span><span class="p">)</span>
+ <span class="n">typstr</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">node</span><span class="p">.</span><span class="n">type_annotation</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">typstr</span> <span class="o">=</span> <span class="s">'?'</span>
<span class="n">d</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="n">shape</span> <span class="o">=</span> <span class="s">'ellipse'</span><span class="p">)</span>
- <span class="n">d</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">node_attr_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span>
- <span class="s">'{}: {}'</span><span class="o">.</span><span class="nb">format</span><span class="p">(</span>
- <span class="n">node</span><span class="o">.</span><span class="n">name_hint</span><span class="p">,</span> <span class="n">typstr</span>
+ <span class="n">d</span><span class="p">.</span><span class="n">update</span><span class="p">(</span><span class="n">node_attr_dict</span><span class="p">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span>
+ <span class="s">'{}: {}'</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span>
+ <span class="n">node</span><span class="p">.</span><span class="n">name_hint</span><span class="p">,</span> <span class="n">typstr</span>
<span class="p">),</span> <span class="o">**</span><span class="n">d</span><span class="p">)</span>
- <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">Tuple</span><span class="p">):</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="s">'Tuple[...])'</span><span class="p">,</span> <span class="o">**</span><span class="n">node_attr_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
- <span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">node</span><span class="o">.</span><span class="n">fields</span><span class="p">:</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">field</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">))</span>
- <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">Constant</span><span class="p">):</span>
+ <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">Tuple</span><span class="p">):</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="s">'Tuple[...])'</span><span class="p">,</span> <span class="o">**</span><span class="n">node_attr_dict</span><span class="p">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
+ <span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">node</span><span class="p">.</span><span class="n">fields</span><span class="p">:</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">field</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">))</span>
+ <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">Constant</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">is_small_const</span><span class="p">(</span><span class="n">node</span><span class="p">):</span> <span class="c1"># small consts are shown in ops
-</span> <span class="n">dot</span><span class="o">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="s">'Constant({}, {})'</span><span class="o">.</span><span class="nb">format</span><span class="p">(</span><span class="n">node</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class= [...]
- <span class="o">**</span><span class="n">node_attr_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
- <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">Call</span><span class="p">):</span>
+</span> <span class="n">dot</span><span class="p">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="s">'Constant({}, {})'</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span><span class="n">node</span><span class="p">.</span><span class="n">data</span><span class="p">.</span><span class="n">shape</span><span class= [...]
+ <span class="o">**</span><span class="n">node_attr_dict</span><span class="p">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
+ <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">Call</span><span class="p">):</span>
<span class="n">args_with_edge</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">arg_str_list</span> <span class="o">=</span> <span class="p">[]</span>
- <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="n">node</span><span class="o">.</span><span class="n">args</span><span class="p">:</span>
+ <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="n">node</span><span class="p">.</span><span class="n">args</span><span class="p">:</span>
<span class="k">if</span> <span class="n">is_small_const</span><span class="p">(</span><span class="n">arg</span><span class="p">):</span>
- <span class="n">arg_str_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">to_str</span><span class="p">(</span><span class="n">arg</span><span class="p">))</span>
+ <span class="n">arg_str_list</span><span class="p">.</span><span class="n">append</span><span class="p">(</span><span class="n">to_str</span><span class="p">(</span><span class="n">arg</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
- <span class="n">arg_str_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s">'·'</span><span class="p">)</span>
- <span class="n">args_with_edge</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">arg</span><span class="p">)</span>
- <span class="n">arg_str</span> <span class="o">=</span> <span class="s">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">arg_str_list</span><span class="p">)</span>
- <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="o">.</span><span class="n">op</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">ir</span><span class="o">.</span><span class="n">Op</span><span class="p">):</span>
- <span class="n">name</span> <span class="o">=</span> <span class="n">node</span><span class="o">.</span><span class="n">op</span><span class="o">.</span><span class="n">name</span>
- <span class="n">attrs</span> <span class="o">=</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span><span class="nb">getattr</span><span class="p">(</span><span class="n">node</span><span class="o">.</span><span class="n">attrs</span><span class="p">,</span> <span class="n">k</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">node</span><span class="o">.</span><span class= [...]
+ <span class="n">arg_str_list</span><span class="p">.</span><span class="n">append</span><span class="p">(</span><span class="s">'·'</span><span class="p">)</span>
+ <span class="n">args_with_edge</span><span class="p">.</span><span class="n">append</span><span class="p">(</span><span class="n">arg</span><span class="p">)</span>
+ <span class="n">arg_str</span> <span class="o">=</span> <span class="s">', '</span><span class="p">.</span><span class="n">join</span><span class="p">(</span><span class="n">arg_str_list</span><span class="p">)</span>
+ <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">.</span><span class="n">op</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">ir</span><span class="p">.</span><span class="n">Op</span><span class="p">):</span>
+ <span class="n">name</span> <span class="o">=</span> <span class="n">node</span><span class="p">.</span><span class="n">op</span><span class="p">.</span><span class="n">name</span>
+ <span class="n">attrs</span> <span class="o">=</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span><span class="nb">getattr</span><span class="p">(</span><span class="n">node</span><span class="p">.</span><span class="n">attrs</span><span class="p">,</span> <span class="n">k</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">node</span><span class="p">.</span><span class= [...]
<span class="c1">#attrs = inspect.getmembers(node.attrs)
-</span> <span class="n">attr_str_list</span> <span class="o">=</span> <span class="p">[</span><span class="n">k</span><span class="o">+</span><span class="s">'='</span><span class="o">+</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">v</span><span cla [...]
+</span> <span class="n">attr_str_list</span> <span class="o">=</span> <span class="p">[</span><span class="n">k</span><span class="o">+</span><span class="s">'='</span><span class="o">+</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">v</span><span cla [...]
<span class="k">if</span> <span class="n">attr_str_list</span><span class="p">:</span>
- <span class="n">attr_str</span> <span class="o">=</span> <span class="s">'| '</span><span class="o">+</span> <span class="s">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">attr_str_list</span><span class="p">)</span>
+ <span class="n">attr_str</span> <span class="o">=</span> <span class="s">'| '</span><span class="o">+</span> <span class="s">', '</span><span class="p">.</span><span class="n">join</span><span class="p">(</span><span class="n">attr_str_list</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">attr_str</span> <span class="o">=</span> <span class="s">''</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">ops</span> <span class="o">=</span> <span class="n">collect_ops</span><span class="p">(</span><span class="n">node</span><span class="p">)</span>
<span class="k">if</span> <span class="n">ops</span><span class="p">:</span>
- <span class="n">name</span> <span class="o">=</span> <span class="s">'_'</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">ops</span><span class="p">)</span>
+ <span class="n">name</span> <span class="o">=</span> <span class="s">'_'</span><span class="p">.</span><span class="n">join</span><span class="p">(</span><span class="n">ops</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">name</span> <span class="o">=</span> <span class="s">'...'</span>
<span class="n">attr_str</span> <span class="o">=</span> <span class="s">''</span>
- <span class="n">s</span> <span class="o">=</span> <span class="n">f</span><span class="s">'{name}({arg_str}{attr_str})'</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="n">s</span><span class="p">,</span> <span class="o">**</span><span class="n">node_attr_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
+ <span class="n">s</span> <span class="o">=</span> <span class="s">f'</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s">(</span><span class="si">{</span><span class="n">arg_str</span><span class="si">}{</span><span class="n">attr_str</span><span class="si">}</span><span class="s">)'</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="n">s</span><span class="p">,</span> <span class="o">**</span><span class="n">node_attr_dict</span><span class="p">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
<span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="n">args_with_edge</span><span class="p">:</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">arg</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">))</span>
- <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">ir</span><span class="o">.</span><span class="n">Op</span><span class="p">):</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">arg</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">))</span>
+ <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">ir</span><span class="p">.</span><span class="n">Op</span><span class="p">):</span>
<span class="c1"># dot.node(str(node_id), 'Op {}'.format(node.name))
</span> <span class="k">pass</span> <span class="c1"># covered in call
-</span> <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">TupleGetItem</span><span class="p">):</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="s">'TupleGetItem(idx={})'</span><span class="o">.</span><span class="nb">format</span><span class="p">(</span><span class="n">node</span><span class="o">.</span><span class="n">index</span><span class="p">),</span> <span class="o">**</span><span class="n">nod [...]
- <span class="n">dot</span><span class="o">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">node</span><span class="o">.</span><span class="n">tuple_value</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">))</span>
- <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">Let</span><span class="p">):</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="s">'Let(XX)'</span><span class="p">,</span> <span class="o">**</span><span class="n">node_attr_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">node</span><span class="o">.</span><span class="n">value</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">))</span>
- <span class="n">dot</span><span class="o">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">node</span><span class="o">.</span><span class="n">var</span><span class="p">]))</span>
+</span> <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">TupleGetItem</span><span class="p">):</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="s">'TupleGetItem(idx={})'</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span><span class="n">node</span><span class="p">.</span><span class="n">index</span><span class="p">),</span> <span class="o">**</span><span class="n">nod [...]
+ <span class="n">dot</span><span class="p">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">node</span><span class="p">.</span><span class="n">tuple_value</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">))</span>
+ <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">Let</span><span class="p">):</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">node</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="s">'Let(XX)'</span><span class="p">,</span> <span class="o">**</span><span class="n">node_attr_dict</span><span class="p">.</span><span class="n">get</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="p">{}))</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">node</span><span class="p">.</span><span class="n">value</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">))</span>
+ <span class="n">dot</span><span class="p">.</span><span class="n">edge</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">node_id</span><span class="p">),</span> <span class="nb">str</span><span class="p">(</span><span class="n">node_dict</span><span class="p">[</span><span class="n">node</span><span class="p">.</span><span class="n">var</span><span class="p">]))</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="nb">RuntimeError</span><span class="p">(</span>
- <span class="s">'Unknown node type. node_id: {}, node: {}'</span><span class="o">.</span><span class="nb">format</span><span class="p">(</span><span class="n">node_id</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">node</span><span class="p">)))</span>
+ <span class="s">'Unknown node type. node_id: {}, node: {}'</span><span class="p">.</span><span class="nb">format</span><span class="p">(</span><span class="n">node_id</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">node</span><span class="p">)))</span>
<span class="k">return</span> <span class="n">dot</span>
</code></pre></div></div>
-<p>Let’s run that on our main function. For some reason (well, to be fully general, probably) the PyTorch converter will convert <code class="highlighter-rouge">Linear</code> layers to <code class="highlighter-rouge">batch_matmul</code> rather than just <code class="highlighter-rouge">dense</code>. We’ll get back to this in a bit. As TVM’s <code class="highlighter-rouge">batch_matmul</code> has the contraction axis last on both operands (unlike PyTorch), there are quite a few transpose o [...]
+<p>Let’s run that on our main function. For some reason (well, to be fully general, probably) the PyTorch converter will convert <code class="language-plaintext highlighter-rouge">Linear</code> layers to <code class="language-plaintext highlighter-rouge">batch_matmul</code> rather than just <code class="language-plaintext highlighter-rouge">dense</code>. We’ll get back to this in a bit. As TVM’s <code class="language-plaintext highlighter-rouge">batch_matmul</code> has the contraction ax [...]
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">visualize</span><span class="p">(</span><span class="n">mod</span><span class="p">[</span><span class="s">'main'</span><span class="p">])</span>
</code></pre></div></div>
@@ -404,7 +394,7 @@ We grab the inputs of a BertLayer (see the Notebook for how) and convert a singl
<p>Just like the full model, we can run and time our submodule after checking that it computes the same quantities.</p>
-<p>100 runs take 20.2ms. The back of the envelope calculation here is that with <code class="highlighter-rouge">BertLayer</code> in PyTorch we are spending about 0.2ms in this layer, so about 2.4ms on 12 layers - a not the majority but a sizeable part of the 6-7ms overall runtime. Let’s compare to TVM. (A good rule is to never optimize without measuring.)</p>
+<p>100 runs take 20.2ms. The back of the envelope calculation here is that with <code class="language-plaintext highlighter-rouge">BertLayer</code> in PyTorch we are spending about 0.2ms in this layer, so about 2.4ms on 12 layers - a not the majority but a sizeable part of the 6-7ms overall runtime. Let’s compare to TVM. (A good rule is to never optimize without measuring.)</p>
<p>Similarly, TVM clocks in at 18.2ms for 100 runs. So here we are again roughly on par with PyTorch.</p>
@@ -412,16 +402,16 @@ We grab the inputs of a BertLayer (see the Notebook for how) and convert a singl
(A while ago, this did not succeed because it had distinct shape arguments, but this was since solved by the TVM developers in the dynamic to static conversion pass.)
Also, the model parameters that are reshaped and transposed. Can we get rid of that, too?
Yes. And for that we would first <em>bind</em> the parameters, i.e. put them into the model. Then the parameters have become constants instead of input nodes.
-With the <code class="highlighter-rouge">Foldconstant</code> pass, we can propagate the constants through the <code class="highlighter-rouge">transpose</code>s and <code class="highlighter-rouge">reshape</code>s to move them closer to the matmuls.</p>
+With the <code class="language-plaintext highlighter-rouge">Foldconstant</code> pass, we can propagate the constants through the <code class="language-plaintext highlighter-rouge">transpose</code>s and <code class="language-plaintext highlighter-rouge">reshape</code>s to move them closer to the matmuls.</p>
<p>After these three (which TVM will do when we compile a relay model), our model looks like this:</p>
<p><img src="/images/bert-pytorch/bert-tvm_72_0.svg" alt="svg" width="100%" /></p>
-<p>And now comes an interesting trick. It is more efficient to merge the three batch matmuls with the same input into a single <code class="highlighter-rouge">batch_matmul</code>. We implemented a pass doing this in <a href="https://github.com/apache/incubator-tvm/pull/5791">TVM PR 5791</a>. So let’s call it and also have another constant-folding pass.</p>
+<p>And now comes an interesting trick. It is more efficient to merge the three batch matmuls with the same input into a single <code class="language-plaintext highlighter-rouge">batch_matmul</code>. We implemented a pass doing this in <a href="https://github.com/apache/incubator-tvm/pull/5791">TVM PR 5791</a>. So let’s call it and also have another constant-folding pass.</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">new_mod</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="n">CombineParallelBatchMatmul</span><span class="p">()(</span><span class="n">new_mod</span><span class="p">)</span>
-<span class="n">new_mod</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">relay</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="n">FoldConstant</span><span class="p">()(</span><span class="n">new_mod</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">new_mod</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">transform</span><span class="p">.</span><span class="n">CombineParallelBatchMatmul</span><span class="p">()(</span><span class="n">new_mod</span><span class="p">)</span>
+<span class="n">new_mod</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">relay</span><span class="p">.</span><span class="n">transform</span><span class="p">.</span><span class="n">FoldConstant</span><span class="p">()(</span><span class="n">new_mod</span><span class="p">)</span>
<span class="n">visualize</span><span class="p">(</span><span class="n">new_mod</span><span class="p">[</span><span class="s">"main"</span><span class="p">])</span>
</code></pre></div></div>
@@ -449,12 +439,12 @@ We go through the same exercise as above.</p>
Also, when I investigated some inner layer, I grabbed the inputs to that to convert and feed into the TVM model. I do believe that this is a very effective technique.</p>
<p>Sometimes, however, it is difficult to assess whether a deviation between the results is from numerical accuracy or from an error somewhere.
-When I initially converted the model, the the <code class="highlighter-rouge">SelfAttention</code> submodule output was replicated by the TVM model to about 1e-6.
+When I initially converted the model, the the <code class="language-plaintext highlighter-rouge">SelfAttention</code> submodule output was replicated by the TVM model to about 1e-6.
However, the BertLayer conversion had something like 1-e3. I was not entirely clear whether that might be due to accumulated numerical errors or some material deviation somewhere.
(This turned out to be the GELU activation, which was converted to FastGELU.)</p>
<p>One of the things I like to do in this case is jump to double precision and check there. Numerical errors should get much smaller, while other deviations would remain of the same order.
-With the PyTorch frontend, you can trace the model converted to float64 on the PyTorch side if you pass <code class="highlighter-rouge">default_dtype="float64"</code> to the conversion function.</p>
+With the PyTorch frontend, you can trace the model converted to float64 on the PyTorch side if you pass <code class="language-plaintext highlighter-rouge">default_dtype="float64"</code> to the conversion function.</p>
<p>Running the module and comparing to PyTorch should now have 1e-14 or so deviation.</p>
@@ -473,21 +463,21 @@ With the PyTorch frontend, you can trace the model converted to float64 on the P
<p>In this second part we want see if we could use TVM while training BERT in PyTorch.
Of course, this opens an entire new can of worms as we need to deal with autodifferentiation.
-While we stay with the theme from above and take <code class="highlighter-rouge">BertLayer</code> as the example, our methodology is representative of non-trivial modules in general.
+While we stay with the theme from above and take <code class="language-plaintext highlighter-rouge">BertLayer</code> as the example, our methodology is representative of non-trivial modules in general.
We will want to divert the computation during training to TVM.</p>
<p>So the user can take a (traceable) module and do</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>add_tvm_dispatch(module, sample_input)
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>add_tvm_dispatch(module, sample_input)
</code></pre></div></div>
<p>and then if she calls module with inputs of the same shape as the sample_input, she’ll get the outputs computed by TVM (as PyTorch tensors, of course) and if not, it’ll just use the regular forward.</p>
<p>The but so we already hinted at the bad news: In this part we will see how to do these things. We will not yet achieve a great speedup.</p>
<p>But enough talk, let us dive right in!
-Again, we get our relay model with running a traced <code class="highlighter-rouge">BertLayer</code> from the transformer <code class="highlighter-rouge">Bert</code> model through <code class="highlighter-rouge">tvm.relay.frontend.from_pytorch</code>.</p>
+Again, we get our relay model with running a traced <code class="language-plaintext highlighter-rouge">BertLayer</code> from the transformer <code class="language-plaintext highlighter-rouge">Bert</code> model through <code class="language-plaintext highlighter-rouge">tvm.relay.frontend.from_pytorch</code>.</p>
<p>One thing we’ll do in between is to move from a modular interface in PyTorch - with named parameters - to a functional
-interface (which is what TVM can do for us). The first thing we want to do for that is arrange for the function arguments to be in an order that we can work with - i.e. first the direct inputs to the module and then the parameters in the same order that PyTorch uses them. After this operation, our <code class="highlighter-rouge">BertLayer </code> in TVM looks like this:</p>
+interface (which is what TVM can do for us). The first thing we want to do for that is arrange for the function arguments to be in an order that we can work with - i.e. first the direct inputs to the module and then the parameters in the same order that PyTorch uses them. After this operation, our <code class="language-plaintext highlighter-rouge">BertLayer </code> in TVM looks like this:</p>
<p><img src="/images/bert-pytorch/pytorch-tvm-training_20_0.svg" alt="svg" width="100%" /></p>
@@ -496,21 +486,21 @@ interface (which is what TVM can do for us). The first thing we want to do for t
<p>But we also have a few new transformations:</p>
<ul>
- <li>One particularity of the Autodifferentiation is that it’ll use a lot of <code class="highlighter-rouge">..._like</code> operations to broadcast or “unbroadcast” (summation is the dual of broadcasting w.r.t. autodifferentiation) things. But this means that you now have two tensor arguments, even if the latter doesn’t really need a gradient. <code class="highlighter-rouge">ZappLike</code> replaces those operations with the corresponding functions taking a shape parameter instead.</li>
+ <li>One particularity of the Autodifferentiation is that it’ll use a lot of <code class="language-plaintext highlighter-rouge">..._like</code> operations to broadcast or “unbroadcast” (summation is the dual of broadcasting w.r.t. autodifferentiation) things. But this means that you now have two tensor arguments, even if the latter doesn’t really need a gradient. <code class="language-plaintext highlighter-rouge">ZappLike</code> replaces those operations with the corresponding functions [...]
<li>Another thing is the “rooting” of derivatives. TVM generates a tensors with all ones of the same shape as the return values of our function as the starting point for the chain rule. These are then multiplied to the derivatives of our operations. But multiplication with ones is not doing much, so we strike that. Similarly, TVM initializes the gradient of a variable (an input) to zeros of the same shape. If it isn’t used, the gradient will be zero, but if it is, the “real gradient” w [...]
- <li>TVM doesn’t have a training variant for the <code class="highlighter-rouge">LayerNorm</code> (or <code class="highlighter-rouge">BatchNorm</code> or others). So we implement a pass to spell out the computation.</li>
+ <li>TVM doesn’t have a training variant for the <code class="language-plaintext highlighter-rouge">LayerNorm</code> (or <code class="language-plaintext highlighter-rouge">BatchNorm</code> or others). So we implement a pass to spell out the computation.</li>
<li>TVM also doesn’t have training dropout. Here the problem is somewhat harder to fix, as TVM doesn’t have random currently. We instead replace the dropout by a construct taking a random bernoulli draw (of 0/1 values) and mimicking dropout with that. The idea is that we’ll use PyTorch to generate this mask for us. This has the added benefit that (if we generate dropout masks in the same order as PyTorch) we’ll get the exact same result.</li>
</ul>
-<p>As hinted at above, TVM’s gradient taking assumes that it is the last element in the computation (the ones-Tensors discussed above). This isn’t a good fit with PyTorch’s modular view which expects a <code class="highlighter-rouge">grad_out</code> for each output to be given. Happily, this is computationally equivalent to multiplying by grad out and summation, so we amend our function with that. We wish to be flexible, so we allow both functions returning a single tensor and those retu [...]
+<p>As hinted at above, TVM’s gradient taking assumes that it is the last element in the computation (the ones-Tensors discussed above). This isn’t a good fit with PyTorch’s modular view which expects a <code class="language-plaintext highlighter-rouge">grad_out</code> for each output to be given. Happily, this is computationally equivalent to multiplying by grad out and summation, so we amend our function with that. We wish to be flexible, so we allow both functions returning a single te [...]
<p>With these modificaitons applied, our model looks like this:</p>
<p><img src="/images/bert-pytorch/pytorch-tvm-training_25_0.svg" alt="svg" width="100%" /></p>
-<p>Finally we can take the grad. As we get a lot of <code class="highlighter-rouge">let</code> nodes, we bring it to normal form using the <code class="highlighter-rouge">ToGraphNormalForm</code> pass.
-TVM’s gradient-taking returns a function that has the same parameters as the original function (in our case amended with the <code class="highlighter-rouge">grad_out</code> and dropout) and then returns a tuple of the original return and a tuple containing gradients for all inputs.
-The first thing we do is to drop all the gradients for <code class="highlighter-rouge">grad_out</code> and <code class="highlighter-rouge">dropout</code> which we don’t need.
+<p>Finally we can take the grad. As we get a lot of <code class="language-plaintext highlighter-rouge">let</code> nodes, we bring it to normal form using the <code class="language-plaintext highlighter-rouge">ToGraphNormalForm</code> pass.
+TVM’s gradient-taking returns a function that has the same parameters as the original function (in our case amended with the <code class="language-plaintext highlighter-rouge">grad_out</code> and dropout) and then returns a tuple of the original return and a tuple containing gradients for all inputs.
+The first thing we do is to drop all the gradients for <code class="language-plaintext highlighter-rouge">grad_out</code> and <code class="language-plaintext highlighter-rouge">dropout</code> which we don’t need.
Then we run our simplification passes.</p>
<p>So this is the graph we have now for forward and backward:</p>
@@ -530,12 +520,12 @@ split our graph. One of the difficult problems is what to do with things compute
<p>We use a coloring here. First we color all nodes of the forward computation in red. Then we traverse the gradient calculation and then color the nodes it needs from the backward blue. This gives us a chance to show off the attribute support in our visualization.</p>
-<p>A bit of (PyTorch) terminology: When we have a function <em>Layer : x ↦ y</em> followed by some <em>Loss: y ↦ l ∈ ℝ</em>, the backward is <em>BackwardOfLayer : grad<code class="highlighter-rouge">_</code>out ↦ grad<code class="highlighter-rouge">_</code>in</em> with <em>grad<code class="highlighter-rouge">_</code>out = dl/dy</em> and *grad<code class="highlighter-rouge">_</code>in = dl/dx`.</p>
+<p>A bit of (PyTorch) terminology: When we have a function <em>Layer : x ↦ y</em> followed by some <em>Loss: y ↦ l ∈ ℝ</em>, the backward is <em>BackwardOfLayer : grad<code class="language-plaintext highlighter-rouge">_</code>out ↦ grad<code class="language-plaintext highlighter-rouge">_</code>in</em> with <em>grad<code class="language-plaintext highlighter-rouge">_</code>out = dl/dy</em> and *grad<code class="language-plaintext highlighter-rouge">_</code>in = dl/dx`.</p>
<p><img src="/images/bert-pytorch/pytorch-tvm-training_34_0.svg" alt="svg" width="100%" /></p>
<p>In order to split the function as described above, we collect the blue nodes as to capture - but constants will
-just be duplicated and inputs (<code class="highlighter-rouge">Var</code> nodes) need to be treated separately.
+just be duplicated and inputs (<code class="language-plaintext highlighter-rouge">Var</code> nodes) need to be treated separately.
Now we can split out the backward, replacing all the blue nodes with variables.</p>
<p>Next we take the forward and amend it to also return the required intermediates. The forward then looks like this:</p>
@@ -544,92 +534,92 @@ Now we can split out the backward, replacing all the blue nodes with variables.<
<p>TVM cannot return nested tuples, so we flatten the output in the function. Again we differentiate between tensor-valued functions and tuple valued ones (i.e. those returning potentially multiple tensors).</p>
-<p>And at last, we can let TVM do its magic and compile our functions, say to <code class="highlighter-rouge">gr_only_compiled_module</code>
-and <code class="highlighter-rouge">fw_and_cap_compiled_module</code>.
+<p>And at last, we can let TVM do its magic and compile our functions, say to <code class="language-plaintext highlighter-rouge">gr_only_compiled_module</code>
+and <code class="language-plaintext highlighter-rouge">fw_and_cap_compiled_module</code>.
Time to give it a spin. We define convenience functions to move tensors between PyTorch and TVM and get the model parameters as a TVM dictionary.</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">tensor_to_tvm</span><span class="p">(</span><span class="n">t</span><span class="p">):</span>
- <span class="k">return</span> <span class="n">tvm</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">from_dlpack</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">dlpack</span><span class="o">.</span><span class="n">to_dlpack</span><span class="p">(</span><span class="n">t</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">tvm</span><span class="p">.</span><span class="n">nd</span><span class="p">.</span><span class="n">from_dlpack</span><span class="p">(</span><span class="n">torch</span><span class="p">.</span><span class="n">utils</span><span class="p">.</span><span class="n">dlpack</span><span class="p">.</span><span class="n">to_dlpack</span><span class="p">(</span><span class="n">t</span><span class="p">))</span>
<span class="k">def</span> <span class="nf">tensor_from_tvm</span><span class="p">(</span><span class="n">a</span><span class="p">):</span>
- <span class="k">return</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">dlpack</span><span class="o">.</span><span class="n">from_dlpack</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">to_dlpack</span><span class="p">()))</span>
+ <span class="k">return</span><span class="p">(</span><span class="n">torch</span><span class="p">.</span><span class="n">utils</span><span class="p">.</span><span class="n">dlpack</span><span class="p">.</span><span class="n">from_dlpack</span><span class="p">(</span><span class="n">a</span><span class="p">.</span><span class="n">to_dlpack</span><span class="p">()))</span>
-<span class="n">model_params_tvm</span> <span class="o">=</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">tensor_to_tvm</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">pytorch_model</span><span class="o">.</span><span class="n">state_dict</span><span class="p">()</span [...]
+<span class="n">model_params_tvm</span> <span class="o">=</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">tensor_to_tvm</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">pytorch_model</span><span class="p">.</span><span class="n">state_dict</span><span class="p">().</spa [...]
</code></pre></div></div>
<p>Similarly, we get the inputs on the GPU in PyTorch and TVM.</p>
<p>We need to deal with the dropout. It will turn out that our record of the three dropout random draws happens in the same order as the dropout in the model. We did a depth-first search on the computational graph to find them and if the values of the the dropout are connected in the graph rather than being on independent branches, this will be the order in which PyTorch draws the matrices, too. If not, good luck fiddeling with the order.</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">torch</span><span class="o">.</span><span class="n">manual_seed</span><span class="p">(</span><span class="mi">12345</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">torch</span><span class="p">.</span><span class="n">manual_seed</span><span class="p">(</span><span class="mi">12345</span><span class="p">)</span>
<span class="n">drop_c</span> <span class="o">=</span> <span class="p">{}</span>
-<span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">dropout_info</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span> <span class="c1"># we don't know the order
+<span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">dropout_info</span><span class="p">.</span><span class="n">keys</span><span class="p">():</span> <span class="c1"># we don't know the order
</span> <span class="n">p</span><span class="p">,</span> <span class="n">typ</span> <span class="o">=</span> <span class="n">dropout_info</span><span class="p">[</span><span class="n">k</span><span class="p">]</span>
- <span class="n">drop_c</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">functional</span><span class="o">.</span><span class="n">dropout</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">ones</span><span class="p">([</span><span class="nb">int</span><span class="p">(< [...]
- <span class="n">dtype</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span><span class="n">torch</span><span class="p">,</span> <span class="n">typ</span><span class="o">.</span><span class="n">dtype</span><span class="p">),</span> <span class="n">device</span><span class="o">=</span><span class="s">"cuda"</span><span class="p">),</span> <span class="n">p</span><span class="o">=</span><span class="n">p</span><s [...]
+ <span class="n">drop_c</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> <span class="o">=</span> <span class="n">torch</span><span class="p">.</span><span class="n">nn</span><span class="p">.</span><span class="n">functional</span><span class="p">.</span><span class="n">dropout</span><span class="p">(</span><span class="n">torch</span><span class="p">.</span><span class="n">ones</span><span class="p">([</span><span class="nb">int</span><span class="p">(< [...]
+ <span class="n">dtype</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span><span class="n">torch</span><span class="p">,</span> <span class="n">typ</span><span class="p">.</span><span class="n">dtype</span><span class="p">),</span> <span class="n">device</span><span class="o">=</span><span class="s">"cuda"</span><span class="p">),</span> <span class="n">p</span><span class="o">=</span><span class="n">p</span><s [...]
-<span class="n">drop_tvm</span> <span class="o">=</span> <span class="p">{</span><span class="n">n</span><span class="p">:</span> <span class="n">tensor_to_tvm</span><span class="p">(</span><span class="n">t</span><span class="p">)</span> <span class="k">for</span> <span class="n">n</span><span class="p">,</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">drop_c</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span>
+<span class="n">drop_tvm</span> <span class="o">=</span> <span class="p">{</span><span class="n">n</span><span class="p">:</span> <span class="n">tensor_to_tvm</span><span class="p">(</span><span class="n">t</span><span class="p">)</span> <span class="k">for</span> <span class="n">n</span><span class="p">,</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">drop_c</span><span class="p">.</span><span class="n">items</span><span class="p">()}</span>
</code></pre></div></div>
<p>Now we can run the forward.</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">fw_and_cap_compiled_module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s">'input'</span><span class="p">,</span> <span class="n">inp_tvm</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
-<span class="n">fw_and_cap_compiled_module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s">'attention_mask'</span><span class="p">,</span> <span class="n">inp_tvm</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
-<span class="n">fw_and_cap_compiled_module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">model_params_tvm</span><span class="p">)</span>
-<span class="n">fw_and_cap_compiled_module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">drop_tvm</span><span class="p">)</span>
-<span class="n">fw_and_cap_compiled_module</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">fw_and_cap_compiled_module</span><span class="p">.</span><span class="n">set_input</span><span class="p">(</span><span class="s">'input'</span><span class="p">,</span> <span class="n">inp_tvm</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
+<span class="n">fw_and_cap_compiled_module</span><span class="p">.</span><span class="n">set_input</span><span class="p">(</span><span class="s">'attention_mask'</span><span class="p">,</span> <span class="n">inp_tvm</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
+<span class="n">fw_and_cap_compiled_module</span><span class="p">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">model_params_tvm</span><span class="p">)</span>
+<span class="n">fw_and_cap_compiled_module</span><span class="p">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">drop_tvm</span><span class="p">)</span>
+<span class="n">fw_and_cap_compiled_module</span><span class="p">.</span><span class="n">run</span><span class="p">()</span>
</code></pre></div></div>
<p>And we can compare the output to PyTorch’s:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">torch</span><span class="o">.</span><span class="n">manual_seed</span><span class="p">(</span><span class="mi">12345</span><span class="p">)</span>
-<span class="n">pytorch_model</span><span class="o">.</span><span class="n">train</span><span class="p">()</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">torch</span><span class="p">.</span><span class="n">manual_seed</span><span class="p">(</span><span class="mi">12345</span><span class="p">)</span>
+<span class="n">pytorch_model</span><span class="p">.</span><span class="n">train</span><span class="p">()</span>
<span class="n">res</span> <span class="o">=</span> <span class="n">pytorch_model</span><span class="p">(</span><span class="o">*</span><span class="n">inp_c</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
-<span class="n">numpy</span><span class="o">.</span><span class="nb">abs</span><span class="p">(</span><span class="n">fw_and_cap_compiled_module</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span><span class="o">-</span><span class="n">res</span><span class="o">.</span><span class="n">detach</span><span class="p">()</span><sp [...]
+<span class="n">numpy</span><span class="p">.</span><span class="nb">abs</span><span class="p">(</span><span class="n">fw_and_cap_compiled_module</span><span class="p">.</span><span class="n">get_output</span><span class="p">(</span><span class="mi">0</span><span class="p">).</span><span class="n">asnumpy</span><span class="p">()</span><span class="o">-</span><span class="n">res</span><span class="p">.</span><span class="n">detach</span><span class="p">().</span><span class="n">cpu</span [...]
</code></pre></div></div>
-<p>This gives <code class="highlighter-rouge">2.1457672e-06</code>.</p>
+<p>This gives <code class="language-plaintext highlighter-rouge">2.1457672e-06</code>.</p>
-<p>Supergood. Let’s also try the backward. We generate a <code class="highlighter-rouge">grad_out</code>, set all the variables and run the backward model and run the backward model</p>
+<p>Supergood. Let’s also try the backward. We generate a <code class="language-plaintext highlighter-rouge">grad_out</code>, set all the variables and run the backward model and run the backward model</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">gr_out_c</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="n">res</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s">"cuda"</span><span class="p">,</span> <span class="n">dtype< [...]
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">gr_out_c</span> <span class="o">=</span> <span class="n">torch</span><span class="p">.</span><span class="n">randn</span><span class="p">(</span><span class="n">res</span><span class="p">.</span><span class="n">shape</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s">"cuda"</span><span class="p">,</span> <span class="n">dtype< [...]
</code></pre></div></div>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">num_captures</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">capture_vars</span><span class="p">)</span>
-<span class="n">num_regular_outputs</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">fw_and_cap_fn_flattened</span><span class="o">.</span><span class="n">body</span><span class="o">.</span><span class="n">fields</span><span class="p">)</span> <span class="o">-</span> <span class="n">num_captures</span>
-<span class="n">captured_values</span> <span class="o">=</span> <span class="p">{</span><span class="n">v</span><span class="o">.</span><span class="n">name_hint</span><span class="p">:</span> <span class="n">fw_and_cap_compiled_module</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">num_regular_outputs</span> <span class="o">+</span> <span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span>< [...]
-
-<span class="n">gr_only_compiled_module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">drop_tvm</span><span class="p">)</span>
-<span class="n">gr_only_compiled_module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">model_params_tvm</span><span class="p">)</span>
-<span class="n">gr_only_compiled_module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">captured_values</span><span class="p">)</span>
-<span class="n">gr_only_compiled_module</span><span class="o">.</span><span class="n">set_input</span><span class="p">(</span><span class="s">'gr:out:0'</span><span class="p">,</span> <span class="n">tensor_to_tvm</span><span class="p">(</span><span class="n">gr_out_c</span><span class="p">))</span>
-<span class="n">gr_only_compiled_module</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
+<span class="n">num_regular_outputs</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">fw_and_cap_fn_flattened</span><span class="p">.</span><span class="n">body</span><span class="p">.</span><span class="n">fields</span><span class="p">)</span> <span class="o">-</span> <span class="n">num_captures</span>
+<span class="n">captured_values</span> <span class="o">=</span> <span class="p">{</span><span class="n">v</span><span class="p">.</span><span class="n">name_hint</span><span class="p">:</span> <span class="n">fw_and_cap_compiled_module</span><span class="p">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">num_regular_outputs</span> <span class="o">+</span> <span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span>< [...]
+
+<span class="n">gr_only_compiled_module</span><span class="p">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">drop_tvm</span><span class="p">)</span>
+<span class="n">gr_only_compiled_module</span><span class="p">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">model_params_tvm</span><span class="p">)</span>
+<span class="n">gr_only_compiled_module</span><span class="p">.</span><span class="n">set_input</span><span class="p">(</span><span class="o">**</span><span class="n">captured_values</span><span class="p">)</span>
+<span class="n">gr_only_compiled_module</span><span class="p">.</span><span class="n">set_input</span><span class="p">(</span><span class="s">'gr:out:0'</span><span class="p">,</span> <span class="n">tensor_to_tvm</span><span class="p">(</span><span class="n">gr_out_c</span><span class="p">))</span>
+<span class="n">gr_only_compiled_module</span><span class="p">.</span><span class="n">run</span><span class="p">()</span>
</code></pre></div></div>
<p>On the PyTorch side, it is easiest to re-run the forward (remembering to reset the random seed) and get the grads.</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">torch</span><span class="o">.</span><span class="n">manual_seed</span><span class="p">(</span><span class="mi">12345</span><span class="p">)</span>
-<span class="n">pytorch_model</span><span class="o">.</span><span class="n">train</span><span class="p">()</span>
-<span class="n">inp_c_rq</span> <span class="o">=</span> <span class="p">[</span><span class="n">i</span><span class="o">.</span><span class="n">requires_grad_</span><span class="p">()</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">inp_c</span><span class="p">]</span>
-<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">pytorch_model</span><span class="o">.</span><span class="n">parameters</span><span class="p">():</span>
- <span class="n">p</span><span class="o">.</span><span class="n">requires_grad_</span><span class="p">()</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">torch</span><span class="p">.</span><span class="n">manual_seed</span><span class="p">(</span><span class="mi">12345</span><span class="p">)</span>
+<span class="n">pytorch_model</span><span class="p">.</span><span class="n">train</span><span class="p">()</span>
+<span class="n">inp_c_rq</span> <span class="o">=</span> <span class="p">[</span><span class="n">i</span><span class="p">.</span><span class="n">requires_grad_</span><span class="p">()</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">inp_c</span><span class="p">]</span>
+<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">pytorch_model</span><span class="p">.</span><span class="n">parameters</span><span class="p">():</span>
+ <span class="n">p</span><span class="p">.</span><span class="n">requires_grad_</span><span class="p">()</span>
<span class="n">res</span> <span class="o">=</span> <span class="n">pytorch_model</span><span class="p">(</span><span class="o">*</span><span class="n">inp_c_rq</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
-<span class="n">grads_pt</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">autograd</span><span class="o">.</span><span class="n">grad</span><span class="p">(</span><span class="n">res</span><span class="p">,</span> <span class="n">inp_c_rq</span> <span class="o">+</span> <span class="nb">list</span><span class="p">(</span><span class="n">pytorch_model</span><span class="o">.</span><span class="n">parameters</span><span class="p">()),</sp [...]
+<span class="n">grads_pt</span> <span class="o">=</span> <span class="n">torch</span><span class="p">.</span><span class="n">autograd</span><span class="p">.</span><span class="n">grad</span><span class="p">(</span><span class="n">res</span><span class="p">,</span> <span class="n">inp_c_rq</span> <span class="o">+</span> <span class="nb">list</span><span class="p">(</span><span class="n">pytorch_model</span><span class="p">.</span><span class="n">parameters</span><span class="p">()),</sp [...]
</code></pre></div></div>
<p>Did it work? It seems so:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">g_pt</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">grads_pt</span><span class="p">):</span>
- <span class="k">print</span><span class="p">(</span><span class="n">numpy</span><span class="o">.</span><span class="nb">abs</span><span class="p">(</span><span class="n">gr_only_compiled_module</span><span class="o">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">i</span><span class="p">)</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span> <span class="o">-</span> <span class="n">g_pt</span><span class="o">.</span><s [...]
+ <span class="k">print</span><span class="p">(</span><span class="n">numpy</span><span class="p">.</span><span class="nb">abs</span><span class="p">(</span><span class="n">gr_only_compiled_module</span><span class="p">.</span><span class="n">get_output</span><span class="p">(</span><span class="n">i</span><span class="p">).</span><span class="n">asnumpy</span><span class="p">()</span> <span class="o">-</span> <span class="n">g_pt</span><span class="p">.</span><span class="n">cpu</span [...]
</code></pre></div></div>
<p>gives us a list of numbers in the 1e-5ish range.</p>
<p>But we wanted to get something running in PyTorch, right?</p>
-<p>Keeping with how PyTorch works, we first define an <code class="highlighter-rouge">autograd.Function</code> that the things we just did manually:</p>
+<p>Keeping with how PyTorch works, we first define an <code class="language-plaintext highlighter-rouge">autograd.Function</code> that the things we just did manually:</p>
-<p>In the <code class="highlighter-rouge">forward</code>:</p>
+<p>In the <code class="language-plaintext highlighter-rouge">forward</code>:</p>
<ul>
<li>Generate the dropout random values,</li>
@@ -637,11 +627,11 @@ Time to give it a spin. We define convenience functions to move tensors between
<li>Record the captures, inputs, and dropout values needed for backward.</li>
</ul>
-<p>In the <code class="highlighter-rouge">backward</code>, run the backward and return the result (as PyTorch tensors).</p>
+<p>In the <code class="language-plaintext highlighter-rouge">backward</code>, run the backward and return the result (as PyTorch tensors).</p>
<p>With that, we get a PyTorch autograd.Function calling into TVM (we would want a small wrapper for that.</p>
-<p>Now all we need to do to achive our goal of getting a method <code class="highlighter-rouge">add_tvm_dispatch(module, sample_inputs)</code> is
+<p>Now all we need to do to achive our goal of getting a method <code class="language-plaintext highlighter-rouge">add_tvm_dispatch(module, sample_inputs)</code> is
to trace the module, create the TVM-based autograd function from it and then replace the forward that calls
that (with the parameters) if applicable or falls back to the usual forward.
Python’s unlimited dynamism makes that kind of hackery relatively easy.
@@ -683,37 +673,41 @@ He is a PyTorch core developer and co-authored <a href="https://www.manning.com/
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/2020/07/15/how-to-bring-your-own-codegen-to-tvm.html b/2020/07/15/how-to-bring-your-own-codegen-to-tvm.html
index ca7024e..f0102c7 100644
--- a/2020/07/15/how-to-bring-your-own-codegen-to-tvm.html
+++ b/2020/07/15/how-to-bring-your-own-codegen-to-tvm.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>How to Bring Your Own Codegen to TVM</title>
-
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
</head>
+<body>
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
+<div class="bannerPage">
+ <header class="header">
+ <div class="container">
+ <div class="headerInner d-flex justify-content-between align-items-center">
+ <div class="headerLogo">
+ <a href="/"><img src="/assets/images/logo.svg" alt="Logo"></a>
+ </div>
+ <div id="headMenu" class="headerNav">
+ <button type="button" id="closeHeadMenu" class="navCloseBtn"><img src="assets/images/close-icon.svg"
+ alt="Close"></button>
+ <ul class="nav">
-
+ <li class="nav-item">
+ <a class="nav-link" href="/#community">Community</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/download">Download</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="/vta">VTA</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="/blog">Blog</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvm.apache.org/docs/">Docs</a>
+ </li>
-
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://tvmconf.org/">Conference</a>
+ </li>
-
+ <li class="nav-item">
+ <a class="nav-link" href="https://github.com/apache/incubator-tvm/">Github</a>
+ </li>
-
-
-
-
+</ul>
+ <div class="responsiveasfdropdown">
+ <button type="button" class="btn-link">
+ ASF
+ </button>
+ <ul>
-
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
-
- <li><a href="/community">Community</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
-
- <li><a href="/download">Download</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
- <li><a href="/about">About</a></li>
-
-
-
+</ul>
+ </div>
+ </div>
+ <div class="responsiveMenuIcon">
+ <button type="button" id="menuBtn" class="btn-menu"><img src="assets/images/menu-icon.svg"
+ alt="Menu Icon" /></button>
+ </div>
+ <div class="asfDropdown">
+ <div class="dropdown">
+ <button type="button" class="btn-link dropdown-toggle" data-toggle="dropdown" aria-haspopup="true"
+ aria-expanded="false">
+ ASF
+ </button>
+ <div class="dropdown-menu dropdown-menu-right">
+ <ul>
-
+ <li>
+ <a href="https://www.apache.org/">Apache Homepage</a>
+ </li>
-
-
+ <li>
+ <a href="https://www.apache.org/licenses/">License</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a>
+ </li>
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
+ <li>
+ <a href="https://www.apache.org/security/">Security</a>
+ </li>
-
+ <li>
+ <a href="https://www.apache.org/foundation/thanks.html">Thanks</a>
+ </li>
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
+ <li>
+ <a href="https://apachecon.com/?ref=tvm.apache.org">Current Events</a>
+ </li>
-
-
+</ul>
+ </div>
+ </div>
+ </div>
+ </div>
+ </div>
+ </header>
+</div>
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
<div class="container">
<div class="content">
<div class="row">
@@ -189,7 +179,7 @@
<p><strong>Generate a graph representation and feed it to a graph engine</strong>:
You may have your own graph engine that is capable of executing a graph (or a neural network model) on your accelerator. For example, both Intel DNNL and NVIDIA TensorRT use an engine to run a whole graph or a model, so that they are able to 1) reduce memory transaction between operators and 2) optimize graph execution with operator fusion.</p>
-<p>In order to achieve the above two optimizations, you may need to process the graph during the compilation time. For example, Conv2D and bias addition are two separate operators in TVM, but they may be one operator (Conv2D with bias addition capability) on your accelerator. In this case, you may want to optimize the graph by replacing the <code class="highlighter-rouge">conv2d - add</code> graph pattern to a <code class="highlighter-rouge">your_conv2d_with_bias</code> node.</p>
+<p>In order to achieve the above two optimizations, you may need to process the graph during the compilation time. For example, Conv2D and bias addition are two separate operators in TVM, but they may be one operator (Conv2D with bias addition capability) on your accelerator. In this case, you may want to optimize the graph by replacing the <code class="language-plaintext highlighter-rouge">conv2d - add</code> graph pattern to a <code class="language-plaintext highlighter-rouge">your_con [...]
<p>If your compilation flow falls into this case, then we recommend reading all the rest sections in this post but skipping <a href="#bring-dnnl-to-tvm-c-source-codegen">Bring DNNL to TVM: C Source Codegen</a>.</p>
@@ -228,7 +218,7 @@ Figure 3: After Merging Compiler Regions.
</center>
<p></p>
-<p><strong>2.2: Partition Graph</strong>: For each region from the previous step, we create a Relay function with an attribute <code class="highlighter-rouge">Compiler</code> to indicate that this Relay function should be entirely offloaded to your accelerator, as shown in Figure 4.</p>
+<p><strong>2.2: Partition Graph</strong>: For each region from the previous step, we create a Relay function with an attribute <code class="language-plaintext highlighter-rouge">Compiler</code> to indicate that this Relay function should be entirely offloaded to your accelerator, as shown in Figure 4.</p>
<p style="text-align: center"><img src="/images/bring-your-own-codegen/after_partitioning.png" alt="After Graph Partitioning" width="50%" /></p>
<center>
@@ -237,9 +227,9 @@ Figure 4: After Graph Partitioning.
<p></p>
<h3 id="3-code-generation">3. Code Generation</h3>
-<p>Now we know which part of the Relay graph should be offloaded. In this step, we sequentially send every Relay function with <code class="highlighter-rouge">Compiler=your_accelerator</code> to your codegen. Your codegen should compile the Relay function to the form that matches your own compilation flow. It can be either C source code or any text formats.</p>
+<p>Now we know which part of the Relay graph should be offloaded. In this step, we sequentially send every Relay function with <code class="language-plaintext highlighter-rouge">Compiler=your_accelerator</code> to your codegen. Your codegen should compile the Relay function to the form that matches your own compilation flow. It can be either C source code or any text formats.</p>
-<p>Finally, all compiled functions will be serialized along with other non-offloaded Relay functions to a single <code class="highlighter-rouge">.so</code> file by the TVM <code class="highlighter-rouge">export_library</code> Python API. In other words, the user will get only one <code class="highlighter-rouge">.so</code> file after running this flow.</p>
+<p>Finally, all compiled functions will be serialized along with other non-offloaded Relay functions to a single <code class="language-plaintext highlighter-rouge">.so</code> file by the TVM <code class="language-plaintext highlighter-rouge">export_library</code> Python API. In other words, the user will get only one <code class="language-plaintext highlighter-rouge">.so</code> file after running this flow.</p>
<h3 id="4-runtime">4. Runtime</h3>
<p>You may also need to implement a runtime to initialize your graph engine (if applicable) and execute the compiled functions. During the inference, TVM runtime (i.e., graph runtime or VM) will leverage your runtime to invoke the offloaded functions when the TVM runtime encounters the corresponding function call in Figure 4. Your runtime is responsible for launching the compiled function with the given input tensor arrays and filling in the results to the output tensor arrays.</p>
@@ -248,21 +238,21 @@ Figure 4: After Graph Partitioning.
<h2 id="bring-dnnl-to-tvm-annotation-rules">Bring DNNL to TVM: Annotation Rules</h2>
-<p>The BYOC framework provides two approaches for you to describe the supported operators and patterns. You can use both of them simultaneously. In this section, we use DNNL as an example to show how to make use of them. The complete implementation is available <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/python/tvm/relay/op/contrib/dnnl.py">here</a>. Note that we put the annotation rules for your codegen under <code class="highlighter-ro [...]
+<p>The BYOC framework provides two approaches for you to describe the supported operators and patterns. You can use both of them simultaneously. In this section, we use DNNL as an example to show how to make use of them. The complete implementation is available <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/python/tvm/relay/op/contrib/dnnl.py">here</a>. Note that we put the annotation rules for your codegen under <code class="language-plain [...]
<h3 id="rules-for-single-operators">Rules for single operators</h3>
<p>You can intuitively specify which Relay operators are supported by your accelerator with the BYOC API. For example, we use the following code snippet to build a rule saying that our DNNL codegen supports Conv2D:</p>
-<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="o">@</span><span class="n">tvm</span><span class="o">.</span><span class="n">ir</span><span class="o">.</span><span class="n">register_op_attr</span><span class="p">(</span><span class="s">"nn.conv2d"</span><span class="p">,</span> <span class="s">"target.dnnl"</span><span class="p">)</span>
+<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="o">@</span><span class="n">tvm</span><span class="p">.</span><span class="n">ir</span><span class="p">.</span><span class="n">register_op_attr</span><span class="p">(</span><span class="s">"nn.conv2d"</span><span class="p">,</span> <span class="s">"target.dnnl"</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_dnnl_conv2d_wrapper</span><span class="p">(</span><span class="n">attrs</span><span class="p">,</span> <span class="n">args</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">True</span>
</code></pre></div></div>
-<p>This registers a new attribute <code class="highlighter-rouge">target.dnnl</code> to Relay <code class="highlighter-rouge">nn.conv2d</code> operator. By this way, the BYOC annotation could invoke <code class="highlighter-rouge">target.dnnl()</code> for every operator in the graph to check if it is supported in DNNL codegen.</p>
+<p>This registers a new attribute <code class="language-plaintext highlighter-rouge">target.dnnl</code> to Relay <code class="language-plaintext highlighter-rouge">nn.conv2d</code> operator. By this way, the BYOC annotation could invoke <code class="language-plaintext highlighter-rouge">target.dnnl()</code> for every operator in the graph to check if it is supported in DNNL codegen.</p>
-<p>On the other hand, it might be tedious to write the above code snippet for every single operator. For the DNNL implementation, we implemented a helper function, <code class="highlighter-rouge">_register_external_op_helper</code>, to make our life easier:</p>
+<p>On the other hand, it might be tedious to write the above code snippet for every single operator. For the DNNL implementation, we implemented a helper function, <code class="language-plaintext highlighter-rouge">_register_external_op_helper</code>, to make our life easier:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">_register_external_op_helper</span><span class="p">(</span><span class="n">op_name</span><span class="p">,</span> <span class="n">supported</span><span class="o">=</span><span class="bp">True</span><span class="p">):</span>
- <span class="o">@</span><span class="n">tvm</span><span class="o">.</span><span class="n">ir</span><span class="o">.</span><span class="n">register_op_attr</span><span class="p">(</span><span class="n">op_name</span><span class="p">,</span> <span class="s">"target.dnnl"</span><span class="p">)</span>
+ <span class="o">@</span><span class="n">tvm</span><span class="p">.</span><span class="n">ir</span><span class="p">.</span><span class="n">register_op_attr</span><span class="p">(</span><span class="n">op_name</span><span class="p">,</span> <span class="s">"target.dnnl"</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_func_wrapper</span><span class="p">(</span><span class="n">attrs</span><span class="p">,</span> <span class="n">args</span><span class="p">):</span>
<span class="k">return</span> <span class="n">supported</span>
<span class="k">return</span> <span class="n">_func_wrapper</span>
@@ -300,7 +290,7 @@ Figure 4: After Graph Partitioning.
<span class="n">conv_desc</span><span class="p">,</span> <span class="n">attr</span><span class="p">,</span> <span class="n">engine_</span><span class="p">);</span>
<span class="c1">// ... skip ...</span>
</code></pre></div></div>
-<p>In this case, except for a single <code class="highlighter-rouge">conv2d</code>, we would like to map the graph pattern <code class="highlighter-rouge">conv2d+relu</code> to <code class="highlighter-rouge">DNNLConv2d(false, true)</code>, and map <code class="highlighter-rouge">conv2d+add+relu</code> to <code class="highlighter-rouge">DNNLConv2d(true, true)</code>. We can achieve it with the following code snippet:</p>
+<p>In this case, except for a single <code class="language-plaintext highlighter-rouge">conv2d</code>, we would like to map the graph pattern <code class="language-plaintext highlighter-rouge">conv2d+relu</code> to <code class="language-plaintext highlighter-rouge">DNNLConv2d(false, true)</code>, and map <code class="language-plaintext highlighter-rouge">conv2d+add+relu</code> to <code class="language-plaintext highlighter-rouge">DNNLConv2d(true, true)</code>. We can achieve it with the [...]
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">make_pattern</span><span class="p">(</span><span class="n">with_bias</span><span class="o">=</span><span class="bp">True</span><span class="p">):</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">wildcard</span><span class="p">()</span>
@@ -325,12 +315,12 @@ Figure 4: After Graph Partitioning.
<p>With the pattern table, we can then use a Relay pass to perform the transformation from</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>%1 = nn.conv2d(%data, %weight, ...)
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>%1 = nn.conv2d(%data, %weight, ...)
%2 = add(%1, %bias)
%3 = nn.relu(%2)
</code></pre></div></div>
<p>to</p>
-<div class="highlighter-rouge"><div class="highlight"><pre class="highlight"><code>%1 = fn(%input1, %input2, %input3,
+<div class="language-plaintext highlighter-rouge"><div class="highlight"><pre class="highlight"><code>%1 = fn(%input1, %input2, %input3,
Composite="dnnl.conv2d_bias_relu",
PartitionedFromPattern="nn.conv2d_add_nn.relu_") {
%1 = nn.conv2d(%input1, %input2, ...)
@@ -339,9 +329,9 @@ Figure 4: After Graph Partitioning.
}
%2 = %1(%data, %weight, %bias)
</code></pre></div></div>
-<p>Thus, the DNNL codegen can get the pattern name <code class="highlighter-rouge">conv2d_bias_relu</code> and map <code class="highlighter-rouge">%1</code> to <code class="highlighter-rouge">DNNLConv2d(true, true)</code>.</p>
+<p>Thus, the DNNL codegen can get the pattern name <code class="language-plaintext highlighter-rouge">conv2d_bias_relu</code> and map <code class="language-plaintext highlighter-rouge">%1</code> to <code class="language-plaintext highlighter-rouge">DNNLConv2d(true, true)</code>.</p>
-<p>As you may have noticed that we also have an attribute called “PartitionedFromPattern” in the composite function. This could be helpful if your pattern contains <code class="highlighter-rouge">wildcard</code> operators. For example we may have a pattern table <code class="highlighter-rouge">("conv2d_with_something", conv2d -> *)</code>:</p>
+<p>As you may have noticed that we also have an attribute called “PartitionedFromPattern” in the composite function. This could be helpful if your pattern contains <code class="language-plaintext highlighter-rouge">wildcard</code> operators. For example we may have a pattern table <code class="language-plaintext highlighter-rouge">("conv2d_with_something", conv2d -> *)</code>:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">make_pattern</span><span class="p">(</span><span class="n">with_bias</span><span class="o">=</span><span class="bp">True</span><span class="p">):</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">wildcard</span><span class="p">()</span>
@@ -349,27 +339,27 @@ Figure 4: After Graph Partitioning.
<span class="n">conv</span> <span class="o">=</span> <span class="n">is_op</span><span class="p">(</span><span class="s">'nn.conv2d'</span><span class="p">)(</span><span class="n">data</span><span class="p">,</span> <span class="n">weight</span><span class="p">)</span>
<span class="k">return</span> <span class="n">wildcard</span><span class="p">()(</span><span class="n">conv</span><span class="p">)</span>
</code></pre></div></div>
-<p>In this case, you will get a composite function with <code class="highlighter-rouge">Composite=conv2d_with_something</code>, but you have no idea about what graph it actually matched. That’s where PartitionedFromPattern comes into play. You can know that if the matched graph is <code class="highlighter-rouge">conv2d -> add</code> or <code class="highlighter-rouge">conv2d -> relu</code> by looking at <code class="highlighter-rouge">PartitionedFromPattern</code> to see if it is <c [...]
+<p>In this case, you will get a composite function with <code class="language-plaintext highlighter-rouge">Composite=conv2d_with_something</code>, but you have no idea about what graph it actually matched. That’s where PartitionedFromPattern comes into play. You can know that if the matched graph is <code class="language-plaintext highlighter-rouge">conv2d -> add</code> or <code class="language-plaintext highlighter-rouge">conv2d -> relu</code> by looking at <code class="language-p [...]
<h2 id="bring-dnnl-to-tvm-relay-graph-transformation">Bring DNNL to TVM: Relay Graph Transformation</h2>
<p>With the annotation rules from the previous step, we can now apply a list of BYOC Relay passes to transform the Relay graph from Figure 1 to Figure 4:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">mod</span> <span class="o">=</span> <span class="n">create_relay_module_from_model</span><span class="p">()</span> <span class="c1"># Output: Figure 1
-</span><span class="n">mod</span> <span class="o">=</span> <span class="n">transform</span><span class="o">.</span><span class="n">MergeComposite</span><span class="p">(</span><span class="n">pattern_table</span><span class="p">)(</span><span class="n">mod</span><span class="p">)</span>
-<span class="n">mod</span> <span class="o">=</span> <span class="n">transform</span><span class="o">.</span><span class="n">AnnotateTarget</span><span class="p">([</span><span class="s">"dnnl"</span><span class="p">])(</span><span class="n">mod</span><span class="p">)</span> <span class="c1"># Output: Figure 2
-</span><span class="n">mod</span> <span class="o">=</span> <span class="n">transform</span><span class="o">.</span><span class="n">MergeCompilerRegions</span><span class="p">()(</span><span class="n">mod</span><span class="p">)</span> <span class="c1"># Output: Figure 3
-</span><span class="n">mod</span> <span class="o">=</span> <span class="n">transform</span><span class="o">.</span><span class="n">PartitionGraph</span><span class="p">()(</span><span class="n">mod</span><span class="p">)</span> <span class="c1"># Output: Figure 4
+</span><span class="n">mod</span> <span class="o">=</span> <span class="n">transform</span><span class="p">.</span><span class="n">MergeComposite</span><span class="p">(</span><span class="n">pattern_table</span><span class="p">)(</span><span class="n">mod</span><span class="p">)</span>
+<span class="n">mod</span> <span class="o">=</span> <span class="n">transform</span><span class="p">.</span><span class="n">AnnotateTarget</span><span class="p">([</span><span class="s">"dnnl"</span><span class="p">])(</span><span class="n">mod</span><span class="p">)</span> <span class="c1"># Output: Figure 2
+</span><span class="n">mod</span> <span class="o">=</span> <span class="n">transform</span><span class="p">.</span><span class="n">MergeCompilerRegions</span><span class="p">()(</span><span class="n">mod</span><span class="p">)</span> <span class="c1"># Output: Figure 3
+</span><span class="n">mod</span> <span class="o">=</span> <span class="n">transform</span><span class="p">.</span><span class="n">PartitionGraph</span><span class="p">()(</span><span class="n">mod</span><span class="p">)</span> <span class="c1"># Output: Figure 4
</span></code></pre></div></div>
<p>As can be seen, each Relay pass can be mapped to a step we have introduced in <a href="#how-byoc-works">How BYOC Works</a>.</p>
<h2 id="bring-dnnl-to-tvm-json-codegenruntime">Bring DNNL to TVM: JSON Codegen/Runtime</h2>
<p>Now let’s implement the DNNL codegen that serializes a Relay graph to a JSON representation, and then implement the DNNL JSON runtime to deserialize and execute the graph. <em>Note that if you attempt to implement a codegen to generate C-compatible programs, you may want to directly proceed to the next section.</em></p>
-<p>To enable DNNL JSON codegen/runtime in TVM to work on this example, please make sure DNNL is available on your machine, and build the TVM with <code class="highlighter-rouge">set(USE_DNNL_CODEGEN ON)</code> in <code class="highlighter-rouge">config.cmake</code>.</p>
+<p>To enable DNNL JSON codegen/runtime in TVM to work on this example, please make sure DNNL is available on your machine, and build the TVM with <code class="language-plaintext highlighter-rouge">set(USE_DNNL_CODEGEN ON)</code> in <code class="language-plaintext highlighter-rouge">config.cmake</code>.</p>
-<p>The DNNL codegen is implemented in <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc"><code class="highlighter-rouge">src/relay/backend/contrib/dnnl/codegen.cc</code></a>. Since we implemented DNNL codegen in both forms in this file for illustration purpose, you could focus on the part covered by <code class="highlighter-rouge">USE_JSON_RUNTIME</code> macro when tracing the code.</p>
+<p>The DNNL codegen is implemented in <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc"><code class="language-plaintext highlighter-rouge">src/relay/backend/contrib/dnnl/codegen.cc</code></a>. Since we implemented DNNL codegen in both forms in this file for illustration purpose, you could focus on the part covered by <code class="language-plaintext highlighter-rouge">USE_JSON_RUNTIME</code> macro when [...]
-<p>We first register the codegen with TVM registration API (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc#L510">L510</a>). This registration makes TVM compile engine dispatch the Relay function with <code class="highlighter-rouge">Compiler=<your codegen></code> to <code class="highlighter-rouge">relay.ext.<your codegen></code>. Then we implement the entry function of the DNNL compiler [...]
+<p>We first register the codegen with TVM registration API (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc#L510">L510</a>). This registration makes TVM compile engine dispatch the Relay function with <code class="language-plaintext highlighter-rouge">Compiler=<your codegen></code> to <code class="language-plaintext highlighter-rouge">relay.ext.<your codegen></code>. Then we implement th [...]
<div class="language-c highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">runtime</span><span class="o">::</span><span class="n">Module</span> <span class="nf">DNNLCompiler</span><span class="p">(</span><span class="k">const</span> <span class="n">ObjectRef</span><span class="o">&</span> <span class="n">ref</span><span class="p">)</span> <span class="p">{</span>
<span class="c1">// "ref" should be the paritioned Relay function with kCompiler=dnnl.</span>
@@ -400,10 +390,10 @@ Figure 4: After Graph Partitioning.
<span class="n">TVM_REGISTER_GLOBAL</span><span class="p">(</span><span class="s">"relay.ext.dnnl"</span><span class="p">).</span><span class="n">set_body_typed</span><span class="p">(</span><span class="n">DNNLCompiler</span><span class="p">);</span>
</code></pre></div></div>
-<p>Note that <strong><em>each runtime module is only responsible for one Relay function, meaning that you may have several DNNL runtime modules in a single <code class="highlighter-rouge">.so</code> file.</em></strong></p>
+<p>Note that <strong><em>each runtime module is only responsible for one Relay function, meaning that you may have several DNNL runtime modules in a single <code class="language-plaintext highlighter-rouge">.so</code> file.</em></strong></p>
<h3 id="dnnl-json-serialization">DNNL JSON Serialization</h3>
-<p>Next, we implement DNNL JSON serializer (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc#L429">L429</a>). We derived it from the BYOC JSON codegen (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/codegen_json/codegen_json.h">src/relay/backend/contrib/codegen_json/codegen_json.h</a>). The special process in DNNL JSON serialize [...]
+<p>Next, we implement DNNL JSON serializer (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc#L429">L429</a>). We derived it from the BYOC JSON codegen (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/codegen_json/codegen_json.h">src/relay/backend/contrib/codegen_json/codegen_json.h</a>). The special process in DNNL JSON serialize [...]
<div class="language-json highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="p">{</span><span class="w">
</span><span class="err">op:</span><span class="w"> </span><span class="s2">"kernel"</span><span class="p">,</span><span class="w">
@@ -435,9 +425,9 @@ Figure 4: After Graph Partitioning.
<h3 id="dnnl-json-runtime">DNNL JSON Runtime</h3>
-<p>We then implement a DNNL JSON runtime to interpret and execute the serialized JSON graph. We put it under <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/runtime/contrib/dnnl/dnnl_json_runtime.cc"><code class="highlighter-rouge">src/runtime/contrib/dnnl/dnnl_json_runtime.cc</code></a>.</p>
+<p>We then implement a DNNL JSON runtime to interpret and execute the serialized JSON graph. We put it under <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/runtime/contrib/dnnl/dnnl_json_runtime.cc"><code class="language-plaintext highlighter-rouge">src/runtime/contrib/dnnl/dnnl_json_runtime.cc</code></a>.</p>
-<p>Again, we first register two APIs to create the runtime so that we can use them anywhere. The <code class="highlighter-rouge">runtime.DNNLJSONRuntimeCreate</code> is used in the previous part after serialization, and <code class="highlighter-rouge">runtime.module.loadbinary_dnnl_json</code> could be used when loading the <code class="highlighter-rouge">.so</code> back.</p>
+<p>Again, we first register two APIs to create the runtime so that we can use them anywhere. The <code class="language-plaintext highlighter-rouge">runtime.DNNLJSONRuntimeCreate</code> is used in the previous part after serialization, and <code class="language-plaintext highlighter-rouge">runtime.module.loadbinary_dnnl_json</code> could be used when loading the <code class="language-plaintext highlighter-rouge">.so</code> back.</p>
<div class="language-c highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="c1">// Create a DNNL JSON runtime to interpret and execute the given JSON graph.</span>
<span class="n">runtime</span><span class="o">::</span><span class="n">Module</span> <span class="nf">DNNLJSONRuntimeCreate</span><span class="p">(</span><span class="n">String</span> <span class="n">symbol_name</span><span class="p">,</span> <span class="n">String</span> <span class="n">graph_json</span><span class="p">,</span>
@@ -474,20 +464,20 @@ Figure 4: After Graph Partitioning.
<span class="p">}</span>
</code></pre></div></div>
-<p>The <code class="highlighter-rouge">Init</code> function is in charge of building the DNNL engine by interpreting the JSON graph string (see <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/runtime/contrib/dnnl/dnnl_json_runtime.cc#L93">L93</a> for <code class="highlighter-rouge">BuildEngine</code>), and filling the constant weights to the corresponding data entry buffers (the <code class="highlighter-rouge">SetupConstant</code> is imp [...]
+<p>The <code class="language-plaintext highlighter-rouge">Init</code> function is in charge of building the DNNL engine by interpreting the JSON graph string (see <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/runtime/contrib/dnnl/dnnl_json_runtime.cc#L93">L93</a> for <code class="language-plaintext highlighter-rouge">BuildEngine</code>), and filling the constant weights to the corresponding data entry buffers (the <code class="language [...]
-<p>Next, the <code class="highlighter-rouge">Run</code> function (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/runtime/contrib/dnnl/dnnl_json_runtime.cc#L64">L64</a>) first writes the input tensors, which may come from user inputs or constant weights, to the corresponding DNNL memory buffers we initialized when building the DNNL engine. Then launch the DNNL engine to execute the JSON graph. Finally, it writes the DNNL output memory bu [...]
+<p>Next, the <code class="language-plaintext highlighter-rouge">Run</code> function (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/runtime/contrib/dnnl/dnnl_json_runtime.cc#L64">L64</a>) first writes the input tensors, which may come from user inputs or constant weights, to the corresponding DNNL memory buffers we initialized when building the DNNL engine. Then launch the DNNL engine to execute the JSON graph. Finally, it writes the DN [...]
<p>Since the rest implementation in DNNL JSON runtime are too DNNL specific to be dived into details in this post, we will stop here. We would like to emphasize that while the DNNL JSON runtime is a good reference to start with, your JSON runtime could be fully customized to fit your requirements.</p>
<h2 id="bring-dnnl-to-tvm-c-source-codegen">Bring DNNL to TVM: C Source Codegen</h2>
<p>Now let’s implement the DNNL codegen that generates C source code which invokes DNNL APIs to execute the Relay graph.<em>Note that if you attempt to implement a codegen to generate other graph representation like in JSON format, you may want to read <a href="#bring-dnnl-to-tvm-json-codegenruntime">Bring DNNL to TVM: JSON Codegen/Runtime</a> and skip this section.</em></p>
-<p>To enable DNNL C source codegen in TVM to work on this example, please make sure DNNL is available on your machine, and build the TVM with <code class="highlighter-rouge">set(USE_DNNL_CODEGEN C_SRC)</code> in <code class="highlighter-rouge">config.cmake</code>.</p>
+<p>To enable DNNL C source codegen in TVM to work on this example, please make sure DNNL is available on your machine, and build the TVM with <code class="language-plaintext highlighter-rouge">set(USE_DNNL_CODEGEN C_SRC)</code> in <code class="language-plaintext highlighter-rouge">config.cmake</code>.</p>
-<p>The DNNL codegen is implemented in <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc"><code class="highlighter-rouge">src/relay/backend/contrib/dnnl/codegen.cc</code></a>. Since we implemented DNNL codegen in both forms in this file for illustration purpose, you could focus on the part <strong>NOT</strong> covered by <code class="highlighter-rouge">USE_JSON_RUNTIME</code> macro when tracing the code.</p>
+<p>The DNNL codegen is implemented in <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc"><code class="language-plaintext highlighter-rouge">src/relay/backend/contrib/dnnl/codegen.cc</code></a>. Since we implemented DNNL codegen in both forms in this file for illustration purpose, you could focus on the part <strong>NOT</strong> covered by <code class="language-plaintext highlighter-rouge">USE_JSON_RUNT [...]
-<p>We first register the codegen with TVM registration API (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc#L510">L510</a>). This registration makes TVM compile engine dispatch the Relay function with <code class="highlighter-rouge">Compiler=<your codegen></code> to <code class="highlighter-rouge">relay.ext.<your codegen></code>. Then we implement the entry function of the DNNL compiler [...]
+<p>We first register the codegen with TVM registration API (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc#L510">L510</a>). This registration makes TVM compile engine dispatch the Relay function with <code class="language-plaintext highlighter-rouge">Compiler=<your codegen></code> to <code class="language-plaintext highlighter-rouge">relay.ext.<your codegen></code>. Then we implement th [...]
<div class="language-c highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">runtime</span><span class="o">::</span><span class="n">Module</span> <span class="nf">DNNLCompiler</span><span class="p">(</span><span class="k">const</span> <span class="n">ObjectRef</span><span class="o">&</span> <span class="n">ref</span><span class="p">)</span> <span class="p">{</span>
<span class="n">DNNLModuleCodegen</span> <span class="n">dnnl</span><span class="p">;</span>
@@ -496,9 +486,9 @@ Figure 4: After Graph Partitioning.
<span class="n">TVM_REGISTER_GLOBAL</span><span class="p">(</span><span class="s">"relay.ext.dnnl"</span><span class="p">).</span><span class="n">set_body_typed</span><span class="p">(</span><span class="n">DNNLCompiler</span><span class="p">);</span>
</code></pre></div></div>
-<p>Note that <strong><em>each runtime module is only responsible for one Relay function, meaning that you may have several DNNL runtime modules in a single <code class="highlighter-rouge">.so</code> file.</em></strong></p>
+<p>Note that <strong><em>each runtime module is only responsible for one Relay function, meaning that you may have several DNNL runtime modules in a single <code class="language-plaintext highlighter-rouge">.so</code> file.</em></strong></p>
-<p>Then, we derive <code class="highlighter-rouge">CSourceModuleCodegenBase</code> to implement <code class="highlighter-rouge">DNNLModuleCodegen</code> in <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc#L362">L362</a>. While <code class="highlighter-rouge">CSourceModuleCodegenBase</code> is in charge of other module level processes such as serialization, we only need to implement the DNNL code gene [...]
+<p>Then, we derive <code class="language-plaintext highlighter-rouge">CSourceModuleCodegenBase</code> to implement <code class="language-plaintext highlighter-rouge">DNNLModuleCodegen</code> in <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc#L362">L362</a>. While <code class="language-plaintext highlighter-rouge">CSourceModuleCodegenBase</code> is in charge of other module level processes such as se [...]
<div class="language-c highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">runtime</span><span class="o">::</span><span class="n">Module</span> <span class="n">CreateCSourceModule</span><span class="p">(</span><span class="k">const</span> <span class="n">ObjectRef</span><span class="o">&</span> <span class="n">ref</span><span class="p">)</span> <span class="n">override</span> <span class="p">{</span>
<span class="c1">// Include headers</span>
@@ -526,7 +516,7 @@ Figure 4: After Graph Partitioning.
<span class="p">}</span>
</code></pre></div></div>
-<p>Next, we implement <code class="highlighter-rouge">GenDNNLFunc</code> (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc#L365">L365</a>) to generate the compilable C code with DNNL APIs as follows. Please see the embedded comments for the explanations of TVM C source runtime module compatible function interfaces.</p>
+<p>Next, we implement <code class="language-plaintext highlighter-rouge">GenDNNLFunc</code> (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc#L365">L365</a>) to generate the compilable C code with DNNL APIs as follows. Please see the embedded comments for the explanations of TVM C source runtime module compatible function interfaces.</p>
<div class="language-c highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="c1">// The example Relay graph: conv2d -> add -> relu.</span>
<span class="cp">#include <cstdint>
@@ -583,41 +573,41 @@ Figure 4: After Graph Partitioning.
<p>Note that the pre-implemented op-based DNNL functions are in <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/runtime/contrib/dnnl/dnnl.cc">src/runtime/contrib/dnnl/dnnl.cc</a>.</p>
-<p>Since the rest implementation in <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc"><code class="highlighter-rouge">src/relay/backend/contrib/dnnl/codegen.cc</code></a> are too DNNL specific to be dived into details in this post, we will stop here. The main idea is implementing a Relay graph visitor (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/r [...]
+<p>Since the rest implementation in <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/src/relay/backend/contrib/dnnl/codegen.cc"><code class="language-plaintext highlighter-rouge">src/relay/backend/contrib/dnnl/codegen.cc</code></a> are too DNNL specific to be dived into details in this post, we will stop here. The main idea is implementing a Relay graph visitor (<a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9 [...]
<h3 id="c-source-compilation">C Source Compilation</h3>
-<p>As you may have noticed, the output of <code class="highlighter-rouge">DNNLCompiler</code> is a module with the generated C code in text format, which has not been compiled by <code class="highlighter-rouge">gcc</code> to be executable binary. In fact, the generated C code will be compiled when users call <code class="highlighter-rouge">export_libray(mod)</code>, like the following code snippet:</p>
+<p>As you may have noticed, the output of <code class="language-plaintext highlighter-rouge">DNNLCompiler</code> is a module with the generated C code in text format, which has not been compiled by <code class="language-plaintext highlighter-rouge">gcc</code> to be executable binary. In fact, the generated C code will be compiled when users call <code class="language-plaintext highlighter-rouge">export_libray(mod)</code>, like the following code snippet:</p>
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">update_lib</span><span class="p">(</span><span class="n">lib</span><span class="p">):</span>
<span class="c1"># Include the path of src/runtime/contrib/dnnl/dnnl.cc
-</span> <span class="n">test_dir</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">realpath</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n" [...]
- <span class="n">source_dir</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">test_dir</span><span class="p">,</span> <span class="s">".."</span><span class="p">,</span> <span class="s">".."</span><span class="p">,</span> <span class="s">".."</span><span class="p">)</span>
- <span class="n">contrib_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">source_dir</span><span class="p">,</span> <span class="s">"src"</span><span class="p">,</span> <span class="s">"runtime"</span><span class="p">,</span> <span class="s">"contrib"</span><span class="p">)</span>
+</span> <span class="n">test_dir</span> <span class="o">=</span> <span class="n">os</span><span class="p">.</span><span class="n">path</span><span class="p">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">os</span><span class="p">.</span><span class="n">path</span><span class="p">.</span><span class="n">realpath</span><span class="p">(</span><span class="n">os</span><span class="p">.</span><span class="n">path</span><span class="p">.</span><span class="n" [...]
+ <span class="n">source_dir</span> <span class="o">=</span> <span class="n">os</span><span class="p">.</span><span class="n">path</span><span class="p">.</span><span class="n">join</span><span class="p">(</span><span class="n">test_dir</span><span class="p">,</span> <span class="s">".."</span><span class="p">,</span> <span class="s">".."</span><span class="p">,</span> <span class="s">".."</span><span class="p">)</span>
+ <span class="n">contrib_path</span> <span class="o">=</span> <span class="n">os</span><span class="p">.</span><span class="n">path</span><span class="p">.</span><span class="n">join</span><span class="p">(</span><span class="n">source_dir</span><span class="p">,</span> <span class="s">"src"</span><span class="p">,</span> <span class="s">"runtime"</span><span class="p">,</span> <span class="s">"contrib"</span><span class="p">)</span>
<span class="c1"># Setup the gcc flag to compile DNNL code.
</span> <span class="n">kwargs</span> <span class="o">=</span> <span class="p">{}</span>
<span class="n">kwargs</span><span class="p">[</span><span class="s">"options"</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span><span class="s">"-O2"</span><span class="p">,</span> <span class="s">"-std=c++14"</span><span class="p">,</span> <span class="s">"-I"</span> <span class="o">+</span> <span class="n">contrib_path</span><span class="p">]</span>
- <span class="n">tmp_path</span> <span class="o">=</span> <span class="n">util</span><span class="o">.</span><span class="n">tempdir</span><span class="p">()</span>
+ <span class="n">tmp_path</span> <span class="o">=</span> <span class="n">util</span><span class="p">.</span><span class="n">tempdir</span><span class="p">()</span>
<span class="n">lib_name</span> <span class="o">=</span> <span class="s">'lib.so'</span>
- <span class="n">lib_path</span> <span class="o">=</span> <span class="n">tmp_path</span><span class="o">.</span><span class="n">relpath</span><span class="p">(</span><span class="n">lib_name</span><span class="p">)</span>
+ <span class="n">lib_path</span> <span class="o">=</span> <span class="n">tmp_path</span><span class="p">.</span><span class="n">relpath</span><span class="p">(</span><span class="n">lib_name</span><span class="p">)</span>
<span class="c1"># The generated C code with DNNL APIs is compiled to a binary lib.so.
-</span> <span class="n">lib</span><span class="o">.</span><span class="n">export_library</span><span class="p">(</span><span class="n">lib_path</span><span class="p">,</span> <span class="n">fcompile</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
+</span> <span class="n">lib</span><span class="p">.</span><span class="n">export_library</span><span class="p">(</span><span class="n">lib_path</span><span class="p">,</span> <span class="n">fcompile</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="c1"># Load the lib.so back to a runtime module.
-</span> <span class="n">lib</span> <span class="o">=</span> <span class="n">runtime</span><span class="o">.</span><span class="n">load_module</span><span class="p">(</span><span class="n">lib_path</span><span class="p">)</span>
+</span> <span class="n">lib</span> <span class="o">=</span> <span class="n">runtime</span><span class="p">.</span><span class="n">load_module</span><span class="p">(</span><span class="n">lib_path</span><span class="p">)</span>
<span class="k">return</span> <span class="n">lib</span>
-<span class="k">with</span> <span class="n">tvm</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="n">PassContext</span><span class="p">(</span><span class="n">opt_level</span><span class="o">=</span><span class="mi">3</span><span class="p">):</span>
- <span class="n">json</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">param</span> <span class="o">=</span> <span class="n">relay</span><span class="o">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="n">target</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n"> [...]
+<span class="k">with</span> <span class="n">tvm</span><span class="p">.</span><span class="n">transform</span><span class="p">.</span><span class="n">PassContext</span><span class="p">(</span><span class="n">opt_level</span><span class="o">=</span><span class="mi">3</span><span class="p">):</span>
+ <span class="n">json</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">param</span> <span class="o">=</span> <span class="n">relay</span><span class="p">.</span><span class="n">build</span><span class="p">(</span><span class="n">mod</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="n">target</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n"> [...]
<span class="n">lib</span> <span class="o">=</span> <span class="n">update_lib</span><span class="p">(</span><span class="n">lib</span><span class="p">)</span>
-<span class="n">rt_mod</span> <span class="o">=</span> <span class="n">tvm</span><span class="o">.</span><span class="n">contrib</span><span class="o">.</span><span class="n">graph_runtime</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">json</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
+<span class="n">rt_mod</span> <span class="o">=</span> <span class="n">tvm</span><span class="p">.</span><span class="n">contrib</span><span class="p">.</span><span class="n">graph_runtime</span><span class="p">.</span><span class="n">create</span><span class="p">(</span><span class="n">json</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">ctx</span><span class="p">)</span>
</code></pre></div></div>
<h2 id="bring-dnnl-to-tvm-build-tvm-with-dnnl-codegenruntime">Bring DNNL to TVM: Build TVM with DNNL Codegen/Runtime</h2>
<p>Finally, we create <a href="https://github.com/apache/incubator-tvm/blob/8a0249cd4d12a2eb1a4e7a692a9265bc63fec5c8/cmake/modules/contrib/DNNL.cmake">cmake/modules/contrib/DNNL.cmake</a> to include the DNNL codegen when building TVM. For demonstration purpose our DNNL codegen has two implementations in the same cmake file. You can only focus on one of them based on your need.</p>
-<p>With the cmake file ready, now users can specify <code class="highlighter-rouge">set(USE_DNNL_CODEGEN ON)</code> in their <code class="highlighter-rouge">build/config.cmake</code> to enable the DNNL codegen.</p>
+<p>With the cmake file ready, now users can specify <code class="language-plaintext highlighter-rouge">set(USE_DNNL_CODEGEN ON)</code> in their <code class="language-plaintext highlighter-rouge">build/config.cmake</code> to enable the DNNL codegen.</p>
<hr />
<ul>
@@ -639,37 +629,41 @@ Figure 4: After Graph Partitioning.
</div>
</div>
-
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
+ </div>
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
- </footer>
- </div>
- </body>
+</section>
</html>
-
-
diff --git a/404.html b/404.html
index 6904bcd..a86a23f 100644
--- a/404.html
+++ b/404.html
@@ -1 +1,72 @@
-Sorry this page does not exist =(
+<html lang="en">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
+ <title></title>
+ <link rel="shortcut icon" href="/assets/images/favicon.ico">
+ <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/css/bootstrap.min.css" integrity="sha384-MCw98/SFnGE8fJT3GXwEOngsV7Zt27NXFoaoApmYm81iuXoPkFOJwJ8ERdknLPMO" crossorigin="anonymous">
+ <link rel="stylesheet" href="/css/slick.css">
+ <link rel="stylesheet" href="/css/slick-theme.css">
+ <link rel="stylesheet" href="/css/custom.css">
+</head>
+<body>
+
+ <style type="text/css" media="screen">
+ .container {
+ margin: 10px auto;
+ max-width: 600px;
+ text-align: center;
+ }
+ h1 {
+ margin: 30px 0;
+ font-size: 4em;
+ line-height: 1;
+ letter-spacing: -1px;
+ }
+</style>
+
+<div class="container">
+ <h1>404</h1>
+
+ <p><strong>Page not found :(</strong></p>
+ <p>The requested page could not be found.</p>
+</div>
+
+
+
+
+
+
+ <script src="https://code.jquery.com/jquery-2.2.0.min.js" type="text/javascript"></script>
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.3/umd/popper.min.js" integrity="sha384-ZMP7rVo3mIykV+2+9J3UJ46jBk0WLaUAdn689aCwoqbBJiSnjAK/l8WvCWPIPm49" crossorigin="anonymous"></script>
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.1.3/js/bootstrap.min.js" integrity="sha384-ChfqqxuZUCnJSK3+MXmPNIyE6ZbWh2IMqE241rYiqJxyMiZ6OW/JmZQ5stwEULTy" crossorigin="anonymous"></script>
+ <!-- <script src="./assets/js/slick.js"></script> -->
+ <script src="/assets/js/custome.js"></script>
+ <script async src="https://www.googletagmanager.com/gtag/js?id=UA-179122341-1"></script>
+ <script>
+ window.dataLayer = window.dataLayer || [];
+ function gtag(){dataLayer.push(arguments);}
+ gtag('js', new Date());
+ gtag('config', 'UA-75982049-2');
+ </script>
+</body>
+<section class="footerSec">
+ <div class="footerHeader">
+ <ul class="container d-flex align-md-items-center justify-content-between flex-column flex-md-row">
+ <li class="logo">
+
+ <p><a href="/"><img src="/assets/images/logo.svg" alt="logo" title="logo" /></a></p>
+ </li>
+ <li class="copywrite d-flex align-items-center">
+ <h5 id="apache-software-foundation--all-right-reserved">© 2020 Apache Software Foundation | All right reserved</h5>
+ </li>
+ </ul>
+
+ </div>
+
+ <ul class="container">
+ <li class="footernote">Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does in [...]
+ </ul>
+
+</section>
+</html>
diff --git a/about.html b/about.html
index 37b8785..69f1c54 100644
--- a/about.html
+++ b/about.html
@@ -1,218 +1,10 @@
-
-<!DOCTYPE html>
-<html lang="en">
- <head>
- <meta charset="utf-8">
- <title>About</title>
- <meta name="description" content="TVM">
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
- window.dataLayer = window.dataLayer || [];
- function gtag(){dataLayer.push(arguments);}
-
- gtag('js', new Date());
- gtag('config', 'UA-75982049-2');
- </script>
-
-</head>
-
- <body>
- <div class="topbar">
- <div class="fill">
- <div class="container">
- <h2 id="logo-wrap">
- <a href="/" class="nav">
- <img src="/images/logo/tvm-logo-small-black.png" width="100px">
- </a>
- </h2>
- <ul class="nav" id="nav-bar">
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li><a href="/community">Community</a></li>
-
-
-
-
-
-
-
-
- <li><a href="/download">Download</a></li>
-
-
-
-
-
-
-
-
- <li class="active"><a href="/about" class="active">About</a></li>
-
-
-
-
-
-
-
-
-
-
-
-
-
- <li><a href="/vta">VTA</a></li>
-
-
-
-
-
-
-
-
-
- <li><a href="/blog">Blog</a></li>
-
-
-
-
-
-
-
-
- <li> <a href="https://tvm.apache.org/docs">Docs</a></li>
- <li> <a href="https://tvmconf.org">TVM Conference</a></li>
- <li> <a href="https://github.com/apache/incubator-tvm/">Github</a></li>
- <li> <a href="/asf">ASF</a></li>
- </ul>
- </div>
- </div>
- </div>
-
-<div class="container">
- <div class="content">
- <div class="row">
- <div class="span14">
-
-<h1 id="about-apache-tvm-incubating">About Apache TVM (incubating)</h1>
-
-<p><strong>The vision of the Apache TVM Project is to host a diverse community of experts and practitioners
-in machine learning, compilers, and systems architecture to build an accessible, extensible, and
-automated open-source framework that optimizes current and emerging machine learning models for
-any hardware platform.</strong></p>
-
-<p>Apache(incubating) TVM is an open deep learning compiler stack for CPUs, GPUs, and specialized accelerators. It aims to close the gap between the productivity-focused deep learning frameworks,
-and the performance- or efficiency-oriented hardware backends. TVM provides the following main features:</p>
-
-<ul>
- <li>Compilation of deep learning models in Keras, MXNet, PyTorch, Tensorflow, CoreML, DarkNet into minimum deployable modules on diverse hardware backends.</li>
- <li>Infrastructure to automatic generate and optimize tensor operators
-on more backend with better performance.</li>
-</ul>
-
-<p>TVM began as a research project at the <a href="https://sampl.cs.washington.edu/">SAMPL group</a> of
-Paul G. Allen School of Computer Science & Engineering, University of Washington.
-The project is now an effort undergoing incubation at The Apache Software Foundation (ASF),
-driven by an open source community involving multiple industry and academic institutions
-under the Apache way.</p>
-
-<p>TVM provides two level optimizations show in the following figure.
-Computational graph optimization to perform tasks such as high-level operator fusion, layout transformation, and memory management.
-Then a tensor operator optimization and code generation layer that optimizes tensor operators. More details can be found at the <a href="https://arxiv.org/abs/1802.04799">techreport</a>.</p>
-
-<p style="text-align: center"><img src="/images/main/tvm-stack.png" alt="image" width="80%" /></p>
-
- </div>
- </div>
- </div>
-</div> <!-- /container -->
-
-
-
-
-
-
-
-
- <div class="container">
-
- <footer class="small">
- Apache TVM is an effort undergoing incubation at The Apache Software Foundation (ASF),
- sponsored by the <i>Apache Incubator</i>. Incubation is required
- of all newly accepted projects until a further review indicates that the infrastructure,
- communications, and decision making process have stabilized in a manner consistent with other
- successful ASF projects. While incubation status is not necessarily a reflection of the completeness
- or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
-
- Copyright © 2020 The Apache Software Foundation. Apache TVM, Apache,
- the Apache feather, and the Apache TVM project logo are either trademarks or registered trademarks of the Apache Software Foundation.
-
- See also other useful <a href="/asf" class="footer-link">ASF links</a>:
- <a href="https://www.apache.org/" class="footer-link">Apache Homepage</a>,
- <a href="https://www.apache.org/licenses/" class="footer-link">License</a>
- <a href="https://www.apache.org/foundation/sponsorship.html" class="footer-link">Sponsorship</a>,
- <a href="https://www.apache.org/security/" class="footer-link">Security</a>
- <a href="https://www.apache.org/foundation/thanks.html" class="footer-link">Thanks</a>,
- <a href="https://www.apache.org/events/current-event.html" class="footer-link">Current Event</a>
-
- </footer>
- </div>
- </body>
+<html lang="en-US">
+ <meta charset="utf-8">
+ <title>Redirecting…</title>
+ <link rel="canonical" href="/#about" >
+ <script>location="/#about"</script>
+ <meta http-equiv="refresh" content="0; url=/#about">
+ <meta name="robots" content="noindex">
+ <h1>Redirecting…</h1>
+ <a href="/#about">Click here if you are not redirected.</a>
</html>
-
-
diff --git a/asf.html b/asf.html
index dccf464..ccb7e5d 100644
--- a/asf.html
+++ b/asf.html
@@ -1,149 +1,139 @@
-
-<!DOCTYPE html>
<html lang="en">
- <head>
- <meta charset="utf-8">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>ASF</title>
- <meta name="description" content="ASF">
- <meta name="author" content="">
-
- <!-- Le HTML5 shim, for IE6-8 support of HTML elements -->
- <!--[if lt IE 9]>
- <script src="http://html5shim.googlecode.com/svn/trunk/html5.js"></script>
- <![endif]-->
-
- <!-- Le styles -->
- <link href="/assets/themes/custom-twitter/css/1.4.0/bootstrap.css" rel="stylesheet">
- <link href="/assets/themes/custom-twitter/css/style.css?body=1" rel="stylesheet" type="text/css" media="all">
-
- <!-- Le fav and touch icons -->
- <!-- Update these with your own images
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- <link rel="shortcut icon" href="images/logo/tvm-logo.png">
- -->
- <link href="/images/logo/tvm-logo-square.png" rel="icon" type="image/png"/>
- <!-- Global site tag (gtag.js) - Google Analytics -->
- <script async src="https://www.googletagmanager.com/gtag/js?id=UA-75982049-2"></script>
- <script>
... 16746 lines suppressed ...