onednn/oneDNN-3.3.3.tar.gz at 8605c33de1c04583868f6d819f4e167e7af02d0cc9247f7283805a3e005f34b1 - onednn - openSUSE Gitea

rpm/onednn

SHA256

forked from pool/onednn

Files

Guillaume GARDET b32a1fac15 Accepting request 1135202 from home:cabelo:branches:science:machinelearning

- Update to 3.3.3:
- This is a patch release containing the following changes to v3.3.2:
  * Fixed performance regression in int8 convolutions on processors with Intel AVX-512 and Intel DL Boost support (a00661f)
  * Fixed race condition during library initialization on Intel Data Center GPU Max Series (7dfcd11)
  * Fixed accuracy issue in experimental Graph Compiler with LLVM code generator (8892e7e)
  * Disabled int8 RNN implementation for cases with non-trivial strides (2195e4b)
  * Fixed incorrect results in bfloat16 convolution implementation on processors with Intel AMX support (9f00af9)
  * Fixed incorrect results in fp16 and int8 convolution on Intel Core Ultra integrated GPUs (69cef84, 79bc6cc, c9c0b09)

OBS-URL: https://build.opensuse.org/request/show/1135202
OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/onednn?expand=0&rev=26

2024-01-08 08:16:13 +00:00

4 lines

133 B

Plaintext

Raw Blame History

	`version https://git-lfs.github.com/spec/v1`
	`oid sha256:ad0d801d0800bd2d650cbe5fff6e0cc33d885e945a6e910f2de03cc722d38d54`
	`size 11984920`