[go: nahoru, domu]
Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

OpenMP/OpenACC support for tensorflow #12434

Closed
abidmalikwaterloo opened this issue Aug 20, 2017 · 4 comments
Closed

OpenMP/OpenACC support for tensorflow #12434

abidmalikwaterloo opened this issue Aug 20, 2017 · 4 comments

Comments

@abidmalikwaterloo
Copy link

Is there any effort in porting the Tensorflow using OpenMP or OpenACC?
@yaroslavvb
Copy link
Contributor

@andydavis1 and @benoitsteiner looked at it a while back. There were two issues

  1. TensorFlow already has its own set of primitives for parallelizing work-loads
  2. It was hard to make it build: compiling with -fopenmp made some seemingly unrelated parts of TensorFlow work incorrectly

@ali01
Copy link
ali01 commented Aug 28, 2017

Thank you, Yaroslav. Closing for now.

@ali01 ali01 closed this as completed Aug 28, 2017
@ali01 ali01 added type:feature Feature requests and removed type:feature Feature requests labels Aug 28, 2017
@masoodmortazavi
Copy link
masoodmortazavi commented Sep 15, 2017 •
edited
Loading

In the exploration of this issue, was attention paid to using Eigen in multi-threaded applications?

Please see the note on calling Eigen::initParallel() before creating application threads, in the following:
https://eigen.tuxfamily.org/dox/TopicMultiThreading.html

@alexkreidler
Copy link

@yaroslavvb Could OpenACC be used to optimize parallel tasks like matmuls and convolutions (IDK if you use a library) on a wider range of accelerators (like AMD GPUs), that the CUDA kernels and CPU-oriented code are not targeting? I think that this could complement the existing Tensorflow primitives for parallelization.

copybara-service bot pushed a commit that referenced this issue May 14, 2024
@sergachev @tensorflower-gardener
PR #12434: [GPU] Fix OSS compilation problems in a previously disable…
699f6c6 
…d test.

Imported from GitHub PR openxla/xla#12434

Copybara import of the project:

--
723c9bb29adfcc33c015b74f90ce8024c2f79255 by Ilia Sergachev <isergachev@nvidia.com>:

[GPU] Fix OSS compilation problems in a previously disabled test.

Merging this change closes #12434

FUTURE_COPYBARA_INTEGRATE_REVIEW=openxla/xla#12434 from openxla:fix_triton_test 723c9bb29adfcc33c015b74f90ce8024c2f79255
PiperOrigin-RevId: 633509548
@copybara-service copybara-service bot mentioned this issue May 14, 2024
Closed
copybara-service bot pushed a commit that referenced this issue May 14, 2024
@sergachev @tensorflower-gardener
PR #12434: [GPU] Fix OSS compilation problems in a previously disable…
74c6fe6 
…d test.

Imported from GitHub PR openxla/xla#12434

Copybara import of the project:

--
723c9bb29adfcc33c015b74f90ce8024c2f79255 by Ilia Sergachev <isergachev@nvidia.com>:

[GPU] Fix OSS compilation problems in a previously disabled test.

Merging this change closes #12434

FUTURE_COPYBARA_INTEGRATE_REVIEW=openxla/xla#12434 from openxla:fix_triton_test 723c9bb29adfcc33c015b74f90ce8024c2f79255
PiperOrigin-RevId: 633509548
copybara-service bot pushed a commit that referenced this issue May 14, 2024
@sergachev @tensorflower-gardener
PR #12434: [GPU] Fix OSS compilation problems in a previously disable…
055675b 
…d test.

Imported from GitHub PR openxla/xla#12434

Copybara import of the project:

--
723c9bb29adfcc33c015b74f90ce8024c2f79255 by Ilia Sergachev <isergachev@nvidia.com>:

[GPU] Fix OSS compilation problems in a previously disabled test.

Merging this change closes #12434

PiperOrigin-RevId: 633533757
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

PR #12434: [GPU] Fix OSS compilation problems in a previously disabled test. tensorflow/tensorflow
5 participants
@yaroslavvb @ali01 @masoodmortazavi @abidmalikwaterloo @alexkreidler