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

Prebuilt binaries do not work with CPUs that do not have AVX instruction sets. #19584

Open
gunan opened this issue May 27, 2018 · 31 comments
Open

Prebuilt binaries do not work with CPUs that do not have AVX instruction sets. #19584

gunan opened this issue May 27, 2018 · 31 comments
Labels
stat:community support Status - Community Support type:feature Feature requests

Comments

@gunan
Copy link
Contributor

gunan commented May 27, 2018

As announced in release notes, TensorFlow release binaries version 1.6 and higher are prebuilt with AVX instruction sets. This means on any CPU that do not have these instruction sets either CPU or GPU version of TF will fail to load with any of the following errors:

  • ImportError: DLL load failed:
  • A crash with return code 132

Our recommendation is to build TF from sources on these systems.

System information

  • Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No
  • OS Platform and Distribution (e.g., Linux Ubuntu 16.04): ubuntu/windows/macos
  • TensorFlow installed from (source or binary): binary
  • TensorFlow version (use command below): 1.6 and up
  • Python version: 2.7, 3.3, 3.4, 3.5, 3.6 and any newer
  • Bazel version (if compiling from source): n/a
  • GCC/Compiler version (if compiling from source): n/a
  • CUDA/cuDNN version: any
  • GPU model and memory: any
  • Exact command to reproduce: python -c "import tensorflow as tf"
This was referenced May 27, 2018
Closed
Closed
@gunan gunan mentioned this issue May 28, 2018
Closed
@gunan gunan unassigned cy89 May 28, 2018
@gunan gunan added the stat:community support Status - Community Support label May 28, 2018
@gunan
Copy link
Contributor Author

gunan commented May 28, 2018

We encourage the community to build and share binaries for older CPU models.

@hadim
Copy link

hadim commented Jun 1, 2018

Any chance for you to make the build for the community?

@hadim
Copy link

hadim commented Jun 2, 2018

FYI, here is a Docker image that can build TensorFlow https://github.com/hadim/docker-tensorflow-builder. It can help to compile TF on a wide range of configurations as long as you have Docker installed on it.

@gunan
Copy link
Contributor Author

gunan commented Jun 2, 2018

We encourage community supported wheels because for the officially blessed binaries we would like to run rigorous tests.
For just building, we encourage the community to build and share.

@bhack
Copy link
Contributor

bhack commented Jun 13, 2018

@gunan Will this change with tensorflow/community#2?

@gunan
Copy link
Contributor Author

gunan commented Jun 14, 2018

In the short term that involves this immediate design, no.
However this design is a part of a larger effort that will bring back support for older CPUs.
That will likely take longer to implement.

This was referenced Jun 29, 2018
Closed
Closed
@waqarkhan3389 waqarkhan3389 mentioned this issue Jul 10, 2018
Closed
This was referenced Jul 13, 2018
Closed
Closed
@tatianashp tatianashp mentioned this issue Jul 13, 2018
Closed
@kingofthebongo2008
Copy link
Contributor

CMake version on the other side on windows does not have AVX at all. I needed to enable it explictly locally.

This was referenced Jul 29, 2018
Closed
Closed
Closed
Closed
Closed
@gunan gunan mentioned this issue Aug 20, 2018
Closed
@metral
Copy link

metral commented Sep 2, 2018 •
edited
Loading

I've gone ahead and compiled GPU only builds for Tensorflow v1.10.1 against CUDA 9.1 cuDNN 7.1, and CUDA 9.2 cuDNN 7.2 and made the wheels and build info available here.

Huge thanks to all of the contributors and the supporting open source community.

Special thanks to @hadim for making his docker-tensorflow-builder available - it served as a great basis to generate these wheels. 🎉

This was referenced Sep 5, 2018
Closed
Closed
@gunan gunan mentioned this issue Sep 26, 2018
Closed
@jsilter jsilter mentioned this issue Sep 27, 2018
Closed
@xuhdev xuhdev mentioned this issue Apr 22, 2020
Closed
@Saduf2019 Saduf2019 mentioned this issue Aug 16, 2020
Closed
@asmirnou asmirnou mentioned this issue Aug 22, 2020
Closed
@xuhdev xuhdev mentioned this issue Sep 21, 2020
Closed
@bhack bhack mentioned this issue Sep 24, 2020
Closed
@matjaz-elumina
Copy link

Check this repo for more unofficial wheels: https://github.com/yaroslavvb/tensorflow-community-wheels/issues
I found the right one for our server. YAY!

@cserpell
Copy link

Something really strange happened to me regarding this issue: I have an i5-3230M CPU, and I was using tensorflow 2 without any problem until yesterday, that I decided to reinstall ubuntu in the machine. As a result, now pip-installed tensorflow cannot be imported. Same machine, same CPU.

@cserpell cserpell mentioned this issue Dec 16, 2020
Closed
@ymodak ymodak mentioned this issue May 6, 2021
Closed
This was referenced Nov 8, 2021
Closed
Closed
@Waseh Waseh mentioned this issue Nov 22, 2021
Closed
@AmmarkoV AmmarkoV mentioned this issue Apr 12, 2022
Closed
@gadagashwini gadagashwini mentioned this issue May 24, 2022
Closed
@colindean colindean mentioned this issue Jun 7, 2022
Open
3 tasks
@tilakrayal tilakrayal mentioned this issue Aug 16, 2022
Closed
@SuryanarayanaY SuryanarayanaY mentioned this issue Jul 19, 2023
Closed
@SuryanarayanaY SuryanarayanaY mentioned this issue Sep 20, 2023
Closed
@phirestalker
Copy link

Does anyone know where we can track progress on the effort to support legacy CPUs mentioned earlier in this thread?

@tilakrayal tilakrayal added the type:feature Feature requests label May 28, 2024
@tawhidnazari57

This comment was marked as spam.

Sign in to view
This was referenced Dec 18, 2024
Closed
Closed
Closed
Closed
Closed
Closed
Closed
Closed
@mihaimaruseac
Copy link
Collaborator

Does anyone know where we can track progress on the effort to support legacy CPUs mentioned earlier in this thread?

There won't be support for these legacy CPUs.

Instead, we recommend using Colab as that is guaranteed to be an environment where TF works.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
stat:community support Status - Community Support type:feature Feature requests
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests