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 2022/08/12 06:19:45 UTC
[GitHub] [tvm] avquicinc opened a new pull request, #12397: Auto-vectorization (fp16) for v68
avquicinc opened a new pull request, #12397:
URL: https://github.com/apache/tvm/pull/12397
Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from [Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers) by @ them in the pull request thread.
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] kparzysz-quic merged pull request #12397: [HEXAGON] Auto-vectorization (fp16) for v68
Posted by GitBox <gi...@apache.org>.
kparzysz-quic merged PR #12397:
URL: https://github.com/apache/tvm/pull/12397
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] cconvey commented on a diff in pull request #12397: [HEXAGON] Auto-vectorization (fp16) for v68
Posted by GitBox <gi...@apache.org>.
cconvey commented on code in PR #12397:
URL: https://github.com/apache/tvm/pull/12397#discussion_r948022433
##########
python/tvm/target/target.py:
##########
@@ -724,6 +724,12 @@ def create_llvm_options(cpu_ver, config): # pylint: disable=unused-argument
llvm_options = config["llvm_options"]
+ # To enable auto-vectorization for v68 target added the below llvm-option by default
+ if arch_version == 68:
+ if not llvm_options:
+ llvm_options = ""
+ llvm_options += " -force-hvx-float"
+
Review Comment:
Also, are there any potential downsides or other side-effects of using this flag? Asking because with compiler flags, the word "force" sometimes implies that the resulting behavior isn't always a good idea.
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] masahi commented on pull request #12397: [HEXAGON] Auto-vectorization (fp16) for v68
Posted by GitBox <gi...@apache.org>.
masahi commented on PR #12397:
URL: https://github.com/apache/tvm/pull/12397#issuecomment-1217838691
@tvm-bot rerun
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] avquicinc commented on pull request #12397: [HEXAGON] Auto-vectorization (fp16) for v68
Posted by GitBox <gi...@apache.org>.
avquicinc commented on PR #12397:
URL: https://github.com/apache/tvm/pull/12397#issuecomment-1212771973
Hi @kparzysz-quic,
Created this PR to add the change needed for enabling auto-vectorization for v68.
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] kparzysz-quic commented on pull request #12397: [HEXAGON] Auto-vectorization (fp16) for v68
Posted by GitBox <gi...@apache.org>.
kparzysz-quic commented on PR #12397:
URL: https://github.com/apache/tvm/pull/12397#issuecomment-1218122207
> @tvm-bot rerun
Let me see if the bot is still confused...
@tvm-bot rerun
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] masahi commented on pull request #12397: [HEXAGON] Auto-vectorization (fp16) for v68
Posted by GitBox <gi...@apache.org>.
masahi commented on PR #12397:
URL: https://github.com/apache/tvm/pull/12397#issuecomment-1219214243
@tvm-bot rerun
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] kparzysz-quic commented on a diff in pull request #12397: [HEXAGON] Auto-vectorization (fp16) for v68
Posted by GitBox <gi...@apache.org>.
kparzysz-quic commented on code in PR #12397:
URL: https://github.com/apache/tvm/pull/12397#discussion_r948025119
##########
python/tvm/target/target.py:
##########
@@ -724,6 +724,12 @@ def create_llvm_options(cpu_ver, config): # pylint: disable=unused-argument
llvm_options = config["llvm_options"]
+ # To enable auto-vectorization for v68 target added the below llvm-option by default
+ if arch_version == 68:
+ if not llvm_options:
+ llvm_options = ""
+ llvm_options += " -force-hvx-float"
+
Review Comment:
It will work with any LLVM version that supports v69. It's fine to use it.
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] cconvey commented on a diff in pull request #12397: [HEXAGON] Auto-vectorization (fp16) for v68
Posted by GitBox <gi...@apache.org>.
cconvey commented on code in PR #12397:
URL: https://github.com/apache/tvm/pull/12397#discussion_r948019685
##########
python/tvm/target/target.py:
##########
@@ -724,6 +724,12 @@ def create_llvm_options(cpu_ver, config): # pylint: disable=unused-argument
llvm_options = config["llvm_options"]
+ # To enable auto-vectorization for v68 target added the below llvm-option by default
+ if arch_version == 68:
+ if not llvm_options:
+ llvm_options = ""
+ llvm_options += " -force-hvx-float"
+
Review Comment:
Does this flag impose any new requirements regarding which LLVM versions TVM needs?
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] kparzysz-quic closed pull request #12397: [HEXAGON] Auto-vectorization (fp16) for v68
Posted by GitBox <gi...@apache.org>.
kparzysz-quic closed pull request #12397: [HEXAGON] Auto-vectorization (fp16) for v68
URL: https://github.com/apache/tvm/pull/12397
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org