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

cpu: aarch64: hot fix for segfault in cached winograd gradient convolution #2150

Closed
wants to merge 245 commits into from
Closed

cpu: aarch64: hot fix for segfault in cached winograd gradient convolution #2150

wants to merge 245 commits into from

Conversation

taoye9
Copy link
Contributor

@taoye9 taoye9 commented Oct 4, 2024 •
edited by Radu2k
Loading

Description

Same PR as #2149 but to backport to rls-v3.6

Checklist

General

  • Do all unit and benchdnn tests (make test and make test_benchdnn_*) pass locally for each commit?
  • Have you formatted the code using clang-format?

vpirogov and others added 30 commits September 6, 2024 18:03
@vpirogov
build: bumped version to v3.7.0
1206acb
@dzarukin
benchdnn: matmul: reduce threshold to 0
a8b478b
@atkassen
xe: binary: ensure reads/writes stay within a page
96f3503
@xuxinzen
cpu: x64: matmul: correct assertion condition for copy_b_transpose
9d3da3d
@karasjoh000
common: broadcast: add per_oc_d broadcast strategy
3378101
@karasjoh000
cpu: x64: matmul: add oc_d broadcast strategy
0af8478
@karasjoh000
cpu: x64: injectors: add oc_d broadcast for binary post ops
8746381
@karasjoh000
gtests: internals: add test for broadcast per_oc_d
626a213
@avmanerikar
cmake: add protection flags against dll injection
a2bbbf1
@mgouicem
x64: matmul: brgemm: reenable f32 scales for non integral dt
2b10ea1
@mgouicem
gpu: generic: sycl: build fix
9a3bf4f
@mgouicem
fixup: gpu: generic: sycl: build fix
6152604
@mgouicem
fixup: gpu: generic: sycl: build fix
038bc87
@mgouicem
doc: various warning fixes
0aa7015
@dzarukin
cpu: x64: io_injector: add a multi_dt f8 interface for initialization
b2ef884
@dzarukin
cpu: x64: jit_generator: allow NaN propagation in saturation call
04d9bb5
@dzarukin
cpu: x64: jit_reorder: separate direct_copy implementation
0a99e17 
Dedicated implementation simplifies the balancing on equal parts and
allows easy supporting for other features.
@dzarukin
cpu: x64: jit_reorder: remove direct_copy path
64fcb06 
In favor of a dedicated implementation.
@dzarukin
common: ittnotify: update to version 3.24.6
0cc9b48
@dzarukin
gpu: intel: ocl: mdapi: remove copyright header added by mistake
e9bfdf6
@dzarukin
gpu: intel: ocl: mdapi: update to version 1.13.176
6b34fed
@rjoursler
xe: jit: v2: conv: fix c++20 build
7837fa4
@densamoilov
xpu: ocl, xpu: sycl: make device usm default
f836db4
@densamoilov
xpu: ocl, xpu: sycl: use service stream for mapping when required
a9a7c65
@dzarukin
benchdnn: update mem_map entry if it was present but not identical
d3ef608
@avmanerikar
common: memory: add support for coo sparse memory
1e2c36b
@avmanerikar
cpu: matmul: update reference impl for coo sparse matmul
6504dbd
@avmanerikar
examples: add example for coo sparse matmul
f15e596
@avmanerikar
benchdnn: matmul: add benchdnn tests for coo sparse matmul
12471a9
@avmanerikar
gtest: add test for coo sparse matmul
1c77c24
@taoye9 taoye9 requested review from a team as code owners October 4, 2024 18:01
@taoye9 taoye9 closed this Oct 4, 2024
@taoye9 taoye9 deleted the rls-v3.6 branch October 4, 2024 18:02
@github-actions github-actions bot added documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64 platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64 platform:gpu-nvidia Codeowner: @oneapi-src/onednn-gpu-nvidia platform:gpu-amd Codeowner: @oneapi-src/onednn-gpu-amd platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel devops Github automation platform:gpu-generic Codeowner: @oneapi-src/onednn-gpu-generic governance backport labels Oct 8, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
backport devops Github automation documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc governance platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64 platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64 platform:gpu-amd Codeowner: @oneapi-src/onednn-gpu-amd platform:gpu-generic Codeowner: @oneapi-src/onednn-gpu-generic platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel platform:gpu-nvidia Codeowner: @oneapi-src/onednn-gpu-nvidia
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.