OpenBLAS 0.3.6 Boosts AMD Zen Performance For GEMM, Other CPU Optimizations
A new release of OpenBLAS is now available, the widely-used open-source BLAS implementation for optimized linear algebra kernels. With OpenBLAS 0.3.6, work has continued on maximizing the BLAS performance for a variety of CPU architectures.
OpenBLAS 0.3.6 is shipping with CMake build system improvements, various POWER optimizations, support for the HiSilicon TSV110 processors, disabling of the AVX-512 DGEMM kernel once again due to unsolved problems, auto-detection for Intel Denverton CPUs, auto-detection for Hygon Dhyana Zen CPUs, and improved GEMM performance on AMD Zen processors.
OpenBLAS 0.3.6 also carries a variety of fixes, IBM z13/z14 optimizations, and other improvements to this linear algebra library.
More details on the OpenBLAS 0.3.6 changes via the GitHub repository.
OpenBLAS 0.3.6 is shipping with CMake build system improvements, various POWER optimizations, support for the HiSilicon TSV110 processors, disabling of the AVX-512 DGEMM kernel once again due to unsolved problems, auto-detection for Intel Denverton CPUs, auto-detection for Hygon Dhyana Zen CPUs, and improved GEMM performance on AMD Zen processors.
OpenBLAS 0.3.6 also carries a variety of fixes, IBM z13/z14 optimizations, and other improvements to this linear algebra library.
More details on the OpenBLAS 0.3.6 changes via the GitHub repository.
3 Comments