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

[SYCL][DOC][CUDA][HIP] Update getStartedGuide.md #10669

Merged
merged 12 commits into from
Aug 28, 2023
Merged

[SYCL][DOC][CUDA][HIP] Update getStartedGuide.md #10669

Changes from 1 commit
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
17633f4
Updated nvidia and hip docs in getStartedGuide.md
Aug 2, 2023
b176f08
Moved text to appropriate location.
Aug 2, 2023
7be2d75
Emphasize that amd requires target arch.
Aug 11, 2023
01f0ba5
Update sycl/doc/GetStartedGuide.md
JackAKirk Aug 21, 2023
83fb9bc
Update sycl/doc/GetStartedGuide.md
JackAKirk Aug 21, 2023
41dd918
Update sycl/doc/GetStartedGuide.md
JackAKirk Aug 21, 2023
fdf9ec5
Update sycl/doc/GetStartedGuide.md
JackAKirk Aug 21, 2023
f969e43
Update sycl/doc/GetStartedGuide.md
JackAKirk Aug 21, 2023
f521051
Merge branch 'sycl' into update-getStarted-cuda
Aug 21, 2023
dc409b5
Remove toc and get started headers
Aug 21, 2023
c015aa8
Use 80-char line limit.
Aug 21, 2023
ada674c
Updated discussion of cuda toolkit support.
JackAKirk Aug 24, 2023
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
Prev Previous commit
Updated discussion of cuda toolkit support. 
Signed-off-by: JackAKirk <jack.kirk@codeplay.com>
  • Loading branch information
@JackAKirk
JackAKirk committed Aug 24, 2023
commit ada674ccd37105ffd0d533033f05bf8b7c19c091
12 changes: 8 additions & 4 deletions sycl/doc/GetStartedGuide.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,12 +178,11 @@ Windows DPC++ toolchain, but add the `--cuda` flag to `configure.py`. Note, the
CUDA backend has Windows support; Windows Subsystem for Linux (WSL) is not
needed to build and run the CUDA backend.

Enabling this flag requires an installation of at least
[CUDA 11.5](https://developer.nvidia.com/cuda-11-5-0-download-archive) on
the system, refer to
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)
for CUDA toolkit installation instructions.

Errors may occur if DPC++ is built with a toolkit version which is higher than
the CUDA driver version. In order to check that the CUDA driver and toolkits
Expand All @@ -197,11 +196,16 @@ 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)).

**_NOTE:_** CUDA toolkit versions earlier than 11.0 are not regularly tested,
but should work for appropriate devices. Note that for example some oneapi
extensions that require sm_80 and later architectures also require at least CUDA
11.0.

The CUDA backend should work on Windows or Linux operating systems with any GPU
with compute capability (SM version) sm_50 or above. The default SM version for
the NVIDIA CUDA backend is sm_50. Users of sm_3X devices can attempt to specify
the target architecture [ahead of time](#aot-target-architectures), provided
that they use a 11.X CUDA Runtime version, but some features may not be
that they use a 11.X or earlier CUDA toolkit version, but some features may not be
supported. The CUDA backend has been tested with different Ubuntu Linux
distributions and a selection of supported CUDA toolkit versions and GPUs.
The backend is tested by a relevant device/toolkit prior to a ONEAPI plugin release.
Expand Down