Skip to content

[SYCL][CUDA][DOC] GettingStartedGuide.md to recommend cuda 11.6 #5917

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

Merged
pvchupin merged 6 commits into from
Mar 30, 2022
Merged

[SYCL][CUDA][DOC] GettingStartedGuide.md to recommend cuda 11.6 #5917

Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
0fc7374
GettingStartedGuide.md to recommend cuda 11.6.
Mar 29, 2022
9dc8813
format
Mar 29, 2022
455a536
format
Mar 29, 2022
8188475
format
Mar 29, 2022
d44454b
Removed outdated sentences.
Mar 30, 2022
83e9f54
Clarified minimum CUDA toolkit version.
Mar 30, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion sycl/doc/GetStartedGuide.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,9 +177,13 @@ the system, refer to
[NVIDIA CUDA Installation Guide for Linux](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html)
or
[NVIDIA CUDA Installation Guide for Windows](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html)

**_NOTE:_** An installation of at least [CUDA 11.6](https://developer.nvidia.com/cuda-downloads) is recommended because there is a known issue with some math builtins when using -O1/O2/O3 Optimization options for CUDA toolkits prior to 11.6 (This is due to a bug in earlier versions of the CUDA toolkit: see [this issue](https://forums.developer.nvidia.com/t/libdevice-functions-causing-ptxas-segfault/193352).
Comment thread
JackAKirk marked this conversation as resolved.
Outdated

An installation of at least
[CUDA 11.0](https://developer.nvidia.com/cuda-11.0-download-archive)
is required for fully utilize Turing (SM 75) devices.
is required to fully utilize Turing (SM 75) devices and to enable Ampere (SM 80)
core features.

Currently, the only combination tested is Ubuntu 18.04 with CUDA 10.2 using

@pvchupin pvchupin Mar 29, 2022

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This looks a bit outdated. Let's remove first sentence?

@JackAKirk JackAKirk Mar 29, 2022

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OK. I could just remove the sentence.

I know that DPC++ has been tested with SM61, SM70, SM71, SM80 using toolkit 11.0, 11.2, 11.3, 11.4, 11.6.

@bader bader Mar 29, 2022

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There is another follow-up note.
The last sentence in this section looks outdated as well - "Windows CUDA support is experimental as it is not currently tested on the CI". We test CUDA backend on Windows platform in CI, but I don't know if it changes the status from "experimental".

@JackAKirk JackAKirk Mar 30, 2022 •
edited
Loading

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We think that the CUDA Windows support should be considered broadly speaking on the same level as the Linux support now that there is the Windows CI and tests are passing: I've gone ahead and removed the reference to experimental Windows support.

a Titan RTX GPU (SM 71). The CUDA backend should work on Windows or Linux
Expand Down