diff --git a/oneDNN-3.3.1.tar.gz b/oneDNN-3.3.1.tar.gz deleted file mode 100644 index ae60b3b..0000000 --- a/oneDNN-3.3.1.tar.gz +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4965f7f99a804a9028bcfeb31ca1b9ba11209e03deb90d69cd06caa27492d43e -size 11983586 diff --git a/oneDNN-3.3.3.tar.gz b/oneDNN-3.3.3.tar.gz new file mode 100644 index 0000000..18d37d6 --- /dev/null +++ b/oneDNN-3.3.3.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0d801d0800bd2d650cbe5fff6e0cc33d885e945a6e910f2de03cc722d38d54 +size 11984920 diff --git a/onednn.changes b/onednn.changes index 8531cea..7ad07b0 100644 --- a/onednn.changes +++ b/onednn.changes @@ -1,3 +1,18 @@ +------------------------------------------------------------------- +Tue Dec 26 21:32:41 UTC 2023 - Alessandro de Oliveira Faria + +------------------------------------------------------------------- +Fri Dec 1 04:33:49 UTC 2023 - Alessandro de Oliveira Faria + +- 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) + ------------------------------------------------------------------- Fri Dec 1 04:33:49 UTC 2023 - Alessandro de Oliveira Faria diff --git a/onednn.spec b/onednn.spec index cb5f513..799aeba 100644 --- a/onednn.spec +++ b/onednn.spec @@ -32,7 +32,7 @@ %define libname libdnnl3 Name: onednn -Version: 3.3.1 +Version: 3.3.3 Release: 0 Summary: Intel Math Kernel Library for Deep Neural Networks License: Apache-2.0