Skip to content

Pull requests: uxlfoundation/oneDNN

New pull request New
92 Open 1,564 Closed
92 Open 1,564 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

src: gpu: intel: jit: ir: add restrictions on conv-based precomputed zps platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3033 opened Apr 5, 2025 by hidefromkgb Loading…
2
common: fixing minor Coverity issues component:api Codeowner: @oneapi-src/onednn-arch component:examples component:tests Codeowner: @oneapi-src/onednn-arch
#3032 opened Apr 5, 2025 by spalicki • Draft
@spalicki
xe: jit: ir: normalize IR reorder layouts platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3031 opened Apr 4, 2025 by atkassen Loading…
2 of 3 tasks
@atkassen
Bug fixes, relax matmul weights decompressions condition for a single group component:tests Codeowner: @oneapi-src/onednn-arch platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#3030 opened Apr 4, 2025 by dzarukin Loading…
1
xe: conv: avoid reorder with NCHW when possible platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3029 opened Apr 4, 2025 by echeresh Loading…
4
cpu: x64: brdgmm: enable sum with different data type platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#3028 opened Apr 4, 2025 by xuxinzen Loading…
1
cpu: x64: matmul: update set_or_check_B_tag bug A confirmed library bug platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#3027 opened Apr 4, 2025 by xuxinzen Loading…
2
cpu: aarch64: enable jit conv for 128 platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#3022 opened Apr 4, 2025 by jondea • Draft
3 tasks
[rls-v3.8-pc] xe: jit: utils: prefer incrementing tiles by a factor of 2 backport platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3018 opened Apr 3, 2025 by atkassen Loading…
@atkassen
generic: sycl: RNN Vanilla BWD platform:gpu-generic Codeowner: @oneapi-src/onednn-gpu-generic
#3015 opened Apr 3, 2025 by ShanoToni Loading…
3
benchdnn: inputs: graph: add more cases using f32 intermediate component:tests Codeowner: @oneapi-src/onednn-arch
#3013 opened Apr 3, 2025 by wzt1997 Loading…
@wzt1997
1
xe: jit: utils: prefer incrementing tiles by a factor of 2 platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3011 opened Apr 2, 2025 by atkassen Loading…
3 tasks done
@atkassen
2
[GPU] xe: binary: enable support for select algorithm component:tests Codeowner: @oneapi-src/onednn-arch platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3010 opened Apr 2, 2025 by yehudaorel Loading…
2 tasks done
21
github: workflows: added component:common and third_party labels devops Github automation
#3008 opened Apr 2, 2025 by vpirogov Loading…
xe: jit: gemm: fix zero pool memory leak under SYCL when not recording platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3005 opened Apr 2, 2025 by petercad Loading…
4
api: make md queries return const object component:api Codeowner: @oneapi-src/onednn-arch
#3002 opened Apr 2, 2025 by mgouicem • Draft
graph: backend: dnnl: dispatch select to binary primitive component:graph-api Codeowner: @oneapi-src/onednn-graph
#3001 opened Apr 2, 2025 by gyhintel Loading…
@gyhintel
6
src: gpu: intel: jit: gemm: add optional mode matching, restrict fpmath backport platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#2993 opened Apr 1, 2025 by hidefromkgb Loading…
10
cpu: aarch64: Update ACL reorder API component:build documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#2992 opened Apr 1, 2025 by Ryo-not-rio • Draft
6
[WiP] gpu: intel: sycl: add support for kernel compilation component:api Codeowner: @oneapi-src/onednn-arch component:build documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#2988 opened Mar 31, 2025 by spalicki • Draft
3
cpu: aarch64: Add BF16 support for eltwise JIT via reordering to FP32 platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#2982 opened Mar 31, 2025 by aditew01 Loading…
15
common: use is_trivially_copyable
#2981 opened Mar 31, 2025 by cyyever Loading…
benchdnn: graph: support input displace for scalar component:graph-api Codeowner: @oneapi-src/onednn-graph component:tests Codeowner: @oneapi-src/onednn-arch
#2980 opened Mar 31, 2025 by wzt1997 Loading…
@wzt1997
18
graph: interface: op: softmax to support safe mode component:api Codeowner: @oneapi-src/onednn-arch component:examples component:graph-api Codeowner: @oneapi-src/onednn-graph component:tests Codeowner: @oneapi-src/onednn-arch documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#2979 opened Mar 29, 2025 by TaoLv Loading…
1
doc: graph: enhance fusion pattern document for post-ops fusions component:graph-api Codeowner: @oneapi-src/onednn-graph documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#2972 opened Mar 28, 2025 by ElaineBao Loading…
@ElaineBao
38
ProTip! no:milestone will show everything without a milestone.