From 5b96d272bfec2419d70cff4184b8d619615d45bcb04d859591b36c05fdd98778 Mon Sep 17 00:00:00 2001 From: Christian Goll Date: Fri, 1 Dec 2023 07:45:53 +0000 Subject: [PATCH] Accepting request 1130129 from home:cabelo:branches:science:machinelearning - Update to 3.3.1: - This is a patch release containing the following changes to v3.3: * Fixed int8 convolution accuracy issue on Intel GPUs (09c87c7) * Switched internal stream to in-order mode for NVIDIA and AMD GPUs to avoid synchronization issues (db01d62) * Fixed runtime error for avgpool_bwd operation in Graph API (d025ef6, 9e0602a, e0dc1b3) * Fixed benchdnn error reporting for some Graph API cases (98dc9db) * Fixed accuracy issue in experimental Graph Compiler for int8 MHA variant from StarCoder model (5476ef7) * Fixed incorrect results for layer normalization with trivial dimensions on Intel GPUs (a2ec0a0) * Removed redundant synchronization for out-of-order SYCL queues (a96e9b1) * Fixed runtime error in experimental Graph Compiler for int8 MLP subgraph from LLAMA model (595543d) * Fixed SEGFAULT in experimental Graph Compiler for fp32 MLP subgraph (4207105) * Fixed incorrect results in experimental Graph Compiler for MLP subgraph (57e14b5) * Fixed the issue with f16 inner product primitive with s8 output returning unimplemented on Intel GPUs (bf12207, 800b5e9, ec7054a) * Fixed incorrect results for int8 deconvolution with zero-points on processors with Intel AMX instructions support (55d2cec) OBS-URL: https://build.opensuse.org/request/show/1130129 OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/onednn?expand=0&rev=24 --- oneDNN-3.3.1.tar.gz | 3 +++ oneDNN-3.3.tar.gz | 3 --- onednn.changes | 18 ++++++++++++++++++ onednn.spec | 2 +- 4 files changed, 22 insertions(+), 4 deletions(-) create mode 100644 oneDNN-3.3.1.tar.gz delete mode 100644 oneDNN-3.3.tar.gz diff --git a/oneDNN-3.3.1.tar.gz b/oneDNN-3.3.1.tar.gz new file mode 100644 index 0000000..ae60b3b --- /dev/null +++ b/oneDNN-3.3.1.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4965f7f99a804a9028bcfeb31ca1b9ba11209e03deb90d69cd06caa27492d43e +size 11983586 diff --git a/oneDNN-3.3.tar.gz b/oneDNN-3.3.tar.gz deleted file mode 100644 index e43c197..0000000 --- a/oneDNN-3.3.tar.gz +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8d150a77025f38bff182aaef4dd643625563b2f311c635f86cf4b769b04d7b48 -size 11573780 diff --git a/onednn.changes b/onednn.changes index b6e5f9a..8531cea 100644 --- a/onednn.changes +++ b/onednn.changes @@ -1,3 +1,21 @@ +------------------------------------------------------------------- +Fri Dec 1 04:33:49 UTC 2023 - Alessandro de Oliveira Faria + +- Update to 3.3.1: +- This is a patch release containing the following changes to v3.3: + * Fixed int8 convolution accuracy issue on Intel GPUs (09c87c7) + * Switched internal stream to in-order mode for NVIDIA and AMD GPUs to avoid synchronization issues (db01d62) + * Fixed runtime error for avgpool_bwd operation in Graph API (d025ef6, 9e0602a, e0dc1b3) + * Fixed benchdnn error reporting for some Graph API cases (98dc9db) + * Fixed accuracy issue in experimental Graph Compiler for int8 MHA variant from StarCoder model (5476ef7) + * Fixed incorrect results for layer normalization with trivial dimensions on Intel GPUs (a2ec0a0) + * Removed redundant synchronization for out-of-order SYCL queues (a96e9b1) + * Fixed runtime error in experimental Graph Compiler for int8 MLP subgraph from LLAMA model (595543d) + * Fixed SEGFAULT in experimental Graph Compiler for fp32 MLP subgraph (4207105) + * Fixed incorrect results in experimental Graph Compiler for MLP subgraph (57e14b5) + * Fixed the issue with f16 inner product primitive with s8 output returning unimplemented on Intel GPUs (bf12207, 800b5e9, ec7054a) + * Fixed incorrect results for int8 deconvolution with zero-points on processors with Intel AMX instructions support (55d2cec) + ------------------------------------------------------------------- Tue Oct 10 05:53:25 UTC 2023 - Paolo Stivanin diff --git a/onednn.spec b/onednn.spec index 426b46d..cb5f513 100644 --- a/onednn.spec +++ b/onednn.spec @@ -32,7 +32,7 @@ %define libname libdnnl3 Name: onednn -Version: 3.3 +Version: 3.3.1 Release: 0 Summary: Intel Math Kernel Library for Deep Neural Networks License: Apache-2.0