8000 Add x86-simd-sort accelerated sorting by sterrettm2 · Pull Request #149362 · pytorch/pytorch · GitHub
[go: up one dir, main page]
Skip to content

Add x86-simd-sort accelerated sorting #149362

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
wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Add x86-simd-sort accelerated sorting #149362

Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
a85db84
Adds support for accelerating sorting with x86-simd-sort
sterrettm2 Apr 22, 2024
77fbb0c
Disabled OpenMP for MSVC due to lack of tasks support
sterrettm2 Sep 3, 2024
32dc367
Changed from vector to c10::SmallBuffer
sterrettm2 Sep 4, 2024
9f9599b
Set reference_in_float to False for the inductor testing
sterrettm2 Sep 6, 2024
3642ebe
Added x86-simd-sort's license to NOTICE
sterrettm2 Sep 19, 2024
86e6f39
Replace deprecated C10_UNUSED
sterrettm2 Mar 18, 2025
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
Replace deprecated C10_UNUSED
  • Loading branch information
@sterrettm2
sterrettm2 committed May 6, 2025
commit 86e6f398f37a9dd9c1c175d2dd5c0bed007d32d2
2 changes: 1 addition & 1 deletion aten/src/ATen/native/cpu/SortingKernel.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -233,7 +233,7 @@ static void xss_sort_kernel(
}

if (values_dim_stride == 1 && indices_dim_stride == 1){
for (const auto i C10_UNUSED : c10::irange(n)) {
for (const auto i [[maybe_unused]] : c10::irange(n)) {
x86simdsortStatic::keyvalue_qsort<scalar_t, index_t>(
reinterpret_cast<scalar_t*>(values_data_bytes),
reinterpret_cast<index_t*>(indices_data_bytes),
Expand Down
Loading
0