Skip to content

[DOC] Update sycl_ext_oneapi_num_compute_units.asciidoc (https://github.com/intel/llvm/issues/21408) #21429

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

Open
zjin-lcf wants to merge 5 commits into
base: sycl
Choose a base branch
from
+10 −4
Open

[DOC] Update sycl_ext_oneapi_num_compute_units.asciidoc (https://github.com/intel/llvm/issues/21408) #21429

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
e5b7311
Update sycl_ext_oneapi_num_compute_units.asciidoc
zjin-lcf Mar 3, 2026
25e406f
Merge branch 'intel:sycl' into sycl
zjin-lcf Mar 4, 2026
c664c7d
Update sycl_ext_oneapi_num_compute_units.asciidoc
zjin-lcf Mar 5, 2026
f538486
Change footnotes to links
gmlueck Mar 6, 2026
51b18b4
Merge branch 'intel:sycl' into sycl
zjin-lcf Mar 6, 2026
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
14 changes: 10 additions & 4 deletions sycl/doc/extensions/supported/sycl_ext_oneapi_num_compute_units.asciidoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,6 +142,10 @@ This section is non-normative and applies only to the {dpcpp} implementation.
The table below explains how {dpcpp} calculates the number of compute units for
different combinations of device and backend.

:intel-link: https://www.intel.com/content/www/us/en/docs/oneapi/optimization-guide-gpu/2025-2/intel-xe-gpu-architecture.html#INTEL-R-XE-GPU-BUILDING-BLOCKS
:nvidia-link: https://docs.nvidia.com/deeplearning/performance/dl-performance-gpu-background/index.html#gpu-arch
:amd-link: https://rocm.docs.amd.com/projects/HIP/en/latest/understand/hardware_implementation.html#hierarchical-organization

[%header,cols="1,5,10"]
|===
|Device Type
Expand All @@ -150,19 +154,21 @@ different combinations of device and backend.

|CPU
|OpenCL
|Number of logical cores.
|Number of logical cores

|Intel GPU
|Any
|Number of Xe cores.
|Number of Xe cores (link:{intel-link}[link])

|NVIDIA GPU
|Any
|Number of streaming multiprocessors (SMs).
|Number of streaming multiprocessors (SMs) (link:{nvidia-link}[link])

|AMD GPU
|Any
|Number of compute units (CUs) (link:{amd-link}[link])
|===


== Issues

None.