You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2020/07/29 17:46:31 UTC
[GitHub] [incubator-tvm] lhutton1 opened a new pull request #6170: [BYOC][ACL] Improve installation tutorial
lhutton1 opened a new pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170
Improves installation script so that ACL can be built natively and improves tutorial to give better information on how ACL can be installed using two different methods.
cc @u99127, @leandron, @comaniac
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] tqchen commented on pull request #6170: [BYOC][ACL] Improve installation tutorial
Posted by GitBox <gi...@apache.org>.
tqchen commented on pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#issuecomment-671439854
Thanks @lhutton1 @leandron @comaniac
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] lhutton1 commented on a change in pull request #6170: [BYOC][ACL] Improve installation tutorial
Posted by GitBox <gi...@apache.org>.
lhutton1 commented on a change in pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#discussion_r462841020
##########
File path: docs/deploy/arm_compute_lib.rst
##########
@@ -26,6 +26,24 @@ and GPU's. Currently the integration offloads operators to ACL to use hand-craft
routines in the library. By offloading select operators from a relay graph to ACL we can achieve
a performance boost on such devices.
+Installing Arm Compute Library
+------------------------------
+
+We recommend two different ways to build and install ACL:
+
+* Use the script located at `docker/install/ubuntu_install_arm_compute_library.sh`. You can use this
+ script for building ACL from source natively or for cross-compiling the library on an x86 machine.
+ You may need to change the architecture of the device you wish to compile for by altering the
+ `target_arch` variable. Binaries will be built from source and installed to the location denoted by
Review comment:
That's a good point, we could use `lscpu` to display the model name of the CPU, although I don't think there is an easy way to determine the architecture directly.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] tqchen merged pull request #6170: [BYOC][ACL] Improve installation tutorial
Posted by GitBox <gi...@apache.org>.
tqchen merged pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6170: [BYOC][ACL] Improve installation tutorial
Posted by GitBox <gi...@apache.org>.
comaniac commented on a change in pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#discussion_r462434528
##########
File path: docs/deploy/arm_compute_lib.rst
##########
@@ -26,6 +26,24 @@ and GPU's. Currently the integration offloads operators to ACL to use hand-craft
routines in the library. By offloading select operators from a relay graph to ACL we can achieve
a performance boost on such devices.
+Installing Arm Compute Library
+------------------------------
+
+We recommend two different ways to build and install ACL:
+
+* Use the script located at `docker/install/ubuntu_install_arm_compute_library.sh`. You can use this
+ script for building ACL from source natively or for cross-compiling the library on an x86 machine.
+ You may need to change the architecture of the device you wish to compile for by altering the
+ `target_arch` variable. Binaries will be built from source and installed to the location denoted by
+ `install_path`.
+* Alternatively, you can download and use pre-built binaries from:
+ https://github.com/ARM-software/ComputeLibrary/releases. When using this package, you will need to
+ select the binaries for the architecture you require and make sure they are visible to cmake.
Review comment:
Need to be more specific, like replace `lib` with `lib/<target-archi>`.
##########
File path: docs/deploy/arm_compute_lib.rst
##########
@@ -26,6 +26,24 @@ and GPU's. Currently the integration offloads operators to ACL to use hand-craft
routines in the library. By offloading select operators from a relay graph to ACL we can achieve
a performance boost on such devices.
+Installing Arm Compute Library
+------------------------------
+
+We recommend two different ways to build and install ACL:
+
+* Use the script located at `docker/install/ubuntu_install_arm_compute_library.sh`. You can use this
+ script for building ACL from source natively or for cross-compiling the library on an x86 machine.
+ You may need to change the architecture of the device you wish to compile for by altering the
+ `target_arch` variable. Binaries will be built from source and installed to the location denoted by
Review comment:
Any suggestion/command about how to know the target architecture of the current machine?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] zhiics commented on a change in pull request #6170: [BYOC][ACL] Improve installation tutorial
Posted by GitBox <gi...@apache.org>.
zhiics commented on a change in pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#discussion_r462526176
##########
File path: docs/deploy/arm_compute_lib.rst
##########
@@ -26,6 +26,24 @@ and GPU's. Currently the integration offloads operators to ACL to use hand-craft
routines in the library. By offloading select operators from a relay graph to ACL we can achieve
a performance boost on such devices.
+Installing Arm Compute Library
+------------------------------
+
+We recommend two different ways to build and install ACL:
+
+* Use the script located at `docker/install/ubuntu_install_arm_compute_library.sh`. You can use this
+ script for building ACL from source natively or for cross-compiling the library on an x86 machine.
+ You may need to change the architecture of the device you wish to compile for by altering the
+ `target_arch` variable. Binaries will be built from source and installed to the location denoted by
+ `install_path`.
+* Alternatively, you can download and use pre-built binaries from:
+ https://github.com/ARM-software/ComputeLibrary/releases. When using this package, you will need to
+ select the binaries for the architecture you require and make sure they are visible to cmake.
Review comment:
Yeah, I think it would be nicer it we can just provide some simple commands.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] lhutton1 commented on a change in pull request #6170: [BYOC][ACL] Improve installation tutorial
Posted by GitBox <gi...@apache.org>.
lhutton1 commented on a change in pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#discussion_r462844943
##########
File path: docs/deploy/arm_compute_lib.rst
##########
@@ -26,6 +26,24 @@ and GPU's. Currently the integration offloads operators to ACL to use hand-craft
routines in the library. By offloading select operators from a relay graph to ACL we can achieve
a performance boost on such devices.
+Installing Arm Compute Library
+------------------------------
+
+We recommend two different ways to build and install ACL:
+
+* Use the script located at `docker/install/ubuntu_install_arm_compute_library.sh`. You can use this
+ script for building ACL from source natively or for cross-compiling the library on an x86 machine.
+ You may need to change the architecture of the device you wish to compile for by altering the
+ `target_arch` variable. Binaries will be built from source and installed to the location denoted by
+ `install_path`.
+* Alternatively, you can download and use pre-built binaries from:
+ https://github.com/ARM-software/ComputeLibrary/releases. When using this package, you will need to
+ select the binaries for the architecture you require and make sure they are visible to cmake.
Review comment:
Yep I can add this, my intention was to leave it a bit more open as this may change in the future, although this can always be updated
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] comaniac commented on pull request #6170: [BYOC][ACL] Improve installation tutorial
Posted by GitBox <gi...@apache.org>.
comaniac commented on pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#issuecomment-665772285
Also cc @zhiics
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [incubator-tvm] leandron commented on a change in pull request #6170: [BYOC][ACL] Improve installation tutorial
Posted by GitBox <gi...@apache.org>.
leandron commented on a change in pull request #6170:
URL: https://github.com/apache/incubator-tvm/pull/6170#discussion_r462844056
##########
File path: docs/deploy/arm_compute_lib.rst
##########
@@ -42,6 +60,19 @@ to compile an ACL module on an x86 machine and then run the module on a remote A
need to use USE_ARM_COMPUTE_LIB=ON on the x86 machine and USE_ARM_COMPUTE_LIB_GRAPH_RUNTIME=ON on the remote
AArch64 device.
+Using USE_ARM_COMPUTE_LIB_GRAPH_RUNTIME=ON will mean that ACL binaries are searched for by cmake in the
+default locations (see https://cmake.org/cmake/help/v3.4/command/find_library.html). In addition to this,
+/path-to-tvm-project/acl/ will also be searched. It is likely that you will need to set your own path to
+locate ACL. This can be done by specifying a path in the place of ON.
+
+These flags should be set in your config.cmake file. For example:
Review comment:
Minor suggestion: might worth reinforcing here that default value for `USE_ARM_COMPUTE_LIB` is `OFF`.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org