pool/onednn
SHA256
3
0
Fork 2
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Accepting request 1235691 from science:machinelearning

Browse Source 
OBS-URL: https://build.opensuse.org/request/show/1235691
OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/onednn?expand=0&rev=17
This commit is contained in:
Ana Guerrero 2025-01-09 14:05:59 +00:00 committed by Git OBS Bridge
commit 03ed886f24
5 changed files with 53 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
_service Normal file
View File

@ -0,0 +1,3 @@
<services>
<service name="download_files" mode="manual" />
</services>

BIN
oneDNN-3.6.2.tar.gz (Stored with Git LFS) Normal file
View File

Binary file not shown.

3
oneDNN-3.6.tar.gz
View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:20c4a92cc0ae0dc19d3d2beca0e357b1d13a5a3af9890a2cc3e41a880e4a0302
size 13782760

48
onednn.changes
View File

@ -1,3 +1,9 @@
-------------------------------------------------------------------
Fri Jan 3 23:23:08 UTC 2025 - Eyad Issa <eyadlorenzo@gmail.com>
- Update to 3.6.2:
* https://github.com/oneapi-src/oneDNN/releases/tag/v3.6.2
------------------------------------------------------------------- -------------------------------------------------------------------
Thu Oct 17 11:42:58 UTC 2024 - Guillaume GARDET <guillaume.gardet@opensuse.org> Thu Oct 17 11:42:58 UTC 2024 - Guillaume GARDET <guillaume.gardet@opensuse.org>
@ -24,27 +30,27 @@ Mon Sep 23 10:04:43 UTC 2024 - Guillaume GARDET <guillaume.gardet@opensuse.org>
Fri Apr 19 17:27:48 UTC 2024 - Alessandro de Oliveira Faria <cabelo@opensuse.org> Fri Apr 19 17:27:48 UTC 2024 - Alessandro de Oliveira Faria <cabelo@opensuse.org>
- Update to 3.4.1: - Update to 3.4.1:
* Fixed an issue with caching and serialization of primitives in * Fixed an issue with caching and serialization of primitives in
deterministic mode (7ed604a) deterministic mode (7ed604a)
* Introduced memory descriptor serialization API * Introduced memory descriptor serialization API
(4cad420, 929a27a, 9b848c8) (4cad420, 929a27a, 9b848c8)
* Fixed incorrect results in fp64 convolution and deconvolution * Fixed incorrect results in fp64 convolution and deconvolution
on Intel GPUs based on Xe-LPG architecture (ebe77b5, 0b399ac, on Intel GPUs based on Xe-LPG architecture (ebe77b5, 0b399ac,
d748d64, 9f4f3d5, 21a8cae) d748d64, 9f4f3d5, 21a8cae)
* Fixed incorrect results in reorder with large sizes on * Fixed incorrect results in reorder with large sizes on
Intel CPUs and GPUs (69a111e, 4b72361, 74a343b) Intel CPUs and GPUs (69a111e, 4b72361, 74a343b)
* Reduced creation time for deconvolution primitive on * Reduced creation time for deconvolution primitive on
Intel CPUs (bec487e, 1eab005) Intel CPUs (bec487e, 1eab005)
* Fixed performance regression in deconvolution on * Fixed performance regression in deconvolution on
Intel CPUs (fbe5b97, 1dd3c6a) Intel CPUs (fbe5b97, 1dd3c6a)
* Removed dangling symblols from static builds * Removed dangling symblols from static builds
(e92c404, 6f5621a) (e92c404, 6f5621a)
* Fixed crash during platform detection on some * Fixed crash during platform detection on some
AArch64-based systems (406a079) AArch64-based systems (406a079)
* Fixed performance regression in int8 deconvolution on * Fixed performance regression in int8 deconvolution on
Intel CPUs (7e50e15) Intel CPUs (7e50e15)
* Fixed handling of zero points for matmul in verbose * Fixed handling of zero points for matmul in verbose
logs converter (15c7916) logs converter (15c7916)
------------------------------------------------------------------- -------------------------------------------------------------------
Fri Dec 1 04:33:49 UTC 2023 - Alessandro de Oliveira Faria <cabelo@opensuse.org> Fri Dec 1 04:33:49 UTC 2023 - Alessandro de Oliveira Faria <cabelo@opensuse.org>
@ -279,38 +285,38 @@ Wed Feb 26 10:36:26 UTC 2020 - Tomáš Chvátal <tchvatal@suse.com>
------------------------------------------------------------------- -------------------------------------------------------------------
Thu Feb 20 10:26:52 UTC 2020 - Christian Goll <cgoll@suse.com> Thu Feb 20 10:26:52 UTC 2020 - Christian Goll <cgoll@suse.com>
- enabled tests - enabled tests
------------------------------------------------------------------- -------------------------------------------------------------------
Thu Jan 30 14:20:22 UTC 2020 - Christian Goll <cgoll@suse.com> Thu Jan 30 14:20:22 UTC 2020 - Christian Goll <cgoll@suse.com>
- packaged separate benchnn packae with its input files - packaged separate benchnn packae with its input files
- updated to v1.1.3 which includes - updated to v1.1.3 which includes
* Fixed the mean and variance memory descriptors in layer * Fixed the mean and variance memory descriptors in layer
normalization (65f1908) normalization (65f1908)
* Fixed the layer normalization formula (c176ceb) * Fixed the layer normalization formula (c176ceb)
------------------------------------------------------------------- -------------------------------------------------------------------
Wed Jan 8 15:21:54 UTC 2020 - Christian Goll <cgoll@suse.com> Wed Jan 8 15:21:54 UTC 2020 - Christian Goll <cgoll@suse.com>
- updated to v1.1.2 - updated to v1.1.2
* Fixed threading over the spatial in bfloat16 batched * Fixed threading over the spatial in bfloat16 batched
normalization (017b6c9) normalization (017b6c9)
* Fixed read past end-of-buffer error for int8 convolution (7d6f45e) * Fixed read past end-of-buffer error for int8 convolution (7d6f45e)
* Fixed condition for dispatching optimized channel blocking in * Fixed condition for dispatching optimized channel blocking in
fp32 backward convolution on Intel Xeon Phi(TM) processor (846eba1) fp32 backward convolution on Intel Xeon Phi(TM) processor (846eba1)
* Fixed fp32 backward convolution for shapes with spatial strides * Fixed fp32 backward convolution for shapes with spatial strides
over the depth dimension (002e3ab) over the depth dimension (002e3ab)
* Fixed softmax with zero sizes on GPU (936bff4) * Fixed softmax with zero sizes on GPU (936bff4)
* Fixed int8 deconvolution with dilation when ih <= dh (3e3bacb) * Fixed int8 deconvolution with dilation when ih <= dh (3e3bacb)
* Enabled back fp32 -> u8 reorder for RNN (a2c2507) * Enabled back fp32 -> u8 reorder for RNN (a2c2507)
* Fixed segmentation fault in bfloat16 backward convolution from * Fixed segmentation fault in bfloat16 backward convolution from
kd_padding=0 computation (52d476c) kd_padding=0 computation (52d476c)
* Fixed segmentation fault in bfloat16 forward convolution due * Fixed segmentation fault in bfloat16 forward convolution due
to push/pop imbalance (4f6e3d5) to push/pop imbalance (4f6e3d5)
* Fixed library version for OS X build (0d85005) * Fixed library version for OS X build (0d85005)
* Fixed padding by channels in concat (a265c7d) * Fixed padding by channels in concat (a265c7d)
* Added full text of third party licenses and * Added full text of third party licenses and
copyright notices to LICENSE file (79f204c) copyright notices to LICENSE file (79f204c)
* Added separate README for binary packages (28f4c96) * Added separate README for binary packages (28f4c96)
* Fixed computing per-oc mask in RNN (ff3ffab) * Fixed computing per-oc mask in RNN (ff3ffab)
@ -324,7 +330,7 @@ Mon Feb 11 16:35:48 UTC 2019 - cgoll@suse.com
------------------------------------------------------------------- -------------------------------------------------------------------
Tue Feb 5 07:45:53 UTC 2019 - Christian Goll <cgoll@suse.com> Tue Feb 5 07:45:53 UTC 2019 - Christian Goll <cgoll@suse.com>
- Initial checking of the Intel(R) Math Kernel Library for - Initial checking of the Intel(R) Math Kernel Library for
Deep Neural Networks which can be used by: Deep Neural Networks which can be used by:
* tensorflow * tensorflow
* Caffee * Caffee

40
onednn.spec
View File

@ -1,7 +1,7 @@
# #
# spec file for package onednn # spec file for package onednn
# #
# Copyright (c) 2024 SUSE LLC # Copyright (c) 2025 SUSE LLC
# #
# All modifications and additions to the file contributed by third parties # All modifications and additions to the file contributed by third parties
# remain the property of their copyright owners, unless otherwise agreed # remain the property of their copyright owners, unless otherwise agreed
@ -16,27 +16,25 @@
# #
%define libname libdnnl3
%ifarch x86_64 %ifarch x86_64
%bcond_without opencl %bcond_without opencl
%else %else
# Build broken on non-x86, with openCL # Build broken on non-x86, with openCL
%bcond_with opencl %bcond_with opencl
%endif %endif
%ifarch aarch64 %ifarch aarch64
# Disable ACL until fixed upstream - https://github.com/oneapi-src/oneDNN/issues/2137 # Disable ACL until fixed upstream - https://github.com/oneapi-src/oneDNN/issues/2137
%bcond_with acl %bcond_with acl
%else %else
%bcond_with acl %bcond_with acl
%endif %endif
%define libname libdnnl3
Name: onednn Name: onednn
Version: 3.6 Version: 3.6.2
Release: 0 Release: 0
Summary: Intel Math Kernel Library for Deep Neural Networks Summary: oneAPI Deep Neural Network Library (oneDNN)
License: Apache-2.0 License: Apache-2.0
URL: https://01.org/onednn URL: https://github.com/oneapi-src/oneDNN
Source0: https://github.com/oneapi-src/oneDNN/archive/v%{version}/oneDNN-%{version}.tar.gz Source0: https://github.com/oneapi-src/oneDNN/archive/v%{version}/oneDNN-%{version}.tar.gz
BuildRequires: chrpath BuildRequires: chrpath
BuildRequires: cmake BuildRequires: cmake
@ -44,7 +42,12 @@ BuildRequires: doxygen
BuildRequires: fdupes BuildRequires: fdupes
BuildRequires: gcc-c++ BuildRequires: gcc-c++
BuildRequires: graphviz BuildRequires: graphviz
BuildRequires: ninja
BuildRequires: texlive-dvips-bin BuildRequires: texlive-dvips-bin
Provides: mkl-dnn = %{version}
Obsoletes: mkl-dnn <= %{version}
Provides: oneDNN = %{version}
ExclusiveArch: x86_64 aarch64 ppc64le
%if %{with acl} %if %{with acl}
BuildRequires: ComputeLibrary-devel >= 24.08.1 BuildRequires: ComputeLibrary-devel >= 24.08.1
%endif %endif
@ -53,17 +56,13 @@ BuildRequires: opencl-headers
BuildRequires: pkgconfig BuildRequires: pkgconfig
BuildRequires: pkgconfig(OpenCL) BuildRequires: pkgconfig(OpenCL)
%endif %endif
ExclusiveArch: x86_64 aarch64 ppc64le
Provides: mkl-dnn = %{version}
Obsoletes: mkl-dnn <= %{version}
Provides: oneDNN = %{version}
%description %description
Intel Math Kernel Library for Deep Neural Networks (Intel MKL-DNN) is an oneAPI Deep Neural Network Library (oneDNN) is an open-source cross-platform
open-source performance library for deep-learning applications. The library performance library of basic building blocks for deep learning applications.
accelerates deep-learning applications and frameworks on Intel architecture.
Intel MKL-DNN contains vectorized and threaded building blocks that you can use oneDNN project is part of the UXL Foundation and is an implementation of the
to implement deep neural networks (DNN) with C and C++ interfaces. oneAPI specification for oneDNN component.
%package -n benchdnn %package -n benchdnn
Summary: Header files of Intel Math Kernel Library Summary: Header files of Intel Math Kernel Library
@ -81,13 +80,13 @@ This package only includes the benchmark utility including its input files.
%package devel %package devel
Summary: Header files of Intel Math Kernel Library Summary: Header files of Intel Math Kernel Library
Requires: %{libname} = %{version} Requires: %{libname} = %{version}
Provides: mkl-dnn-devel = %{version}
Obsoletes: mkl-dnn-devel <= %{version}
Provides: oneDNN-devel = %{version}
%if %{with opencl} %if %{with opencl}
Requires: opencl-headers Requires: opencl-headers
Requires: pkgconfig(OpenCL) Requires: pkgconfig(OpenCL)
%endif %endif
Provides: mkl-dnn-devel = %{version}
Obsoletes: mkl-dnn-devel <= %{version}
Provides: oneDNN-devel = %{version}
%description devel %description devel
Intel Math Kernel Library for Deep Neural Networks (Intel MKL-DNN) is an Intel Math Kernel Library for Deep Neural Networks (Intel MKL-DNN) is an
@ -121,6 +120,7 @@ to implement deep neural networks (DNN) with C and C++ interfaces.
%autosetup -p1 -n oneDNN-%{version} %autosetup -p1 -n oneDNN-%{version}
%build %build
%define __builder ninja
%cmake \ %cmake \
-DCMAKE_INSTALL_LIBDIR=%{_lib} \ -DCMAKE_INSTALL_LIBDIR=%{_lib} \
-DMKLDNN_ARCH_OPT_FLAGS="" \ -DMKLDNN_ARCH_OPT_FLAGS="" \
@ -164,7 +164,7 @@ chrpath -d %{buildroot}/%{_bindir}/benchdnn
# do not use macro so we can exclude all gpu and cross (gpu and cpu) tests (they need gpu set up) # do not use macro so we can exclude all gpu and cross (gpu and cpu) tests (they need gpu set up)
pushd build pushd build
export LD_LIBRARY_PATH=%{buildroot}%{_libdir} export LD_LIBRARY_PATH=%{buildroot}%{_libdir}
ctest --output-on-failure --force-new-ctest-process %{_smp_mflags} -E '(gpu|cross)' ctest --output-on-failure --force-new-ctest-process %{?_smp_mflags} -E '(gpu|cross)'
popd popd
%post -n %{libname} -p /sbin/ldconfig %post -n %{libname} -p /sbin/ldconfig