OpenBLAS 0.3.13 Released With A RISC-V Port, POWER10 Optimizations
OpenBLAS 0.3.13 was released today as the newest update to this leading open-source BLAS (and LAPACK) implementation.
With OpenBLAS 0.3.13 some of the release highlights include:
- Detection for the Fujitsu Fortran compiler.
- A RISC-V port for the C910V has been added. This initial OpenBLAS RISC-V target is catering to the RISC-V Vector Extension 0.7.1. This is the first RISC-V port by OpenBLAS.
- IBM POWER10 optimizations are underway for OpenBLAS with seeing various POWER10 optimized kernels, specific DGEMM performance improvements on POWER10, and also some STRSM/DTRSM performance optimizations that also benefit POWER9.
- A variety of optimizations for the x86_64 kernels.
- Improving the kernels for Loongson 3A/3B hardware.
- A generic BFloat16 SBGEMV kernel has been added.
- Various other fixes.
OpenBLAS 0.3.13 downloads and the full change-log via GitHub.
With OpenBLAS 0.3.13 some of the release highlights include:
- Detection for the Fujitsu Fortran compiler.
- A RISC-V port for the C910V has been added. This initial OpenBLAS RISC-V target is catering to the RISC-V Vector Extension 0.7.1. This is the first RISC-V port by OpenBLAS.
- IBM POWER10 optimizations are underway for OpenBLAS with seeing various POWER10 optimized kernels, specific DGEMM performance improvements on POWER10, and also some STRSM/DTRSM performance optimizations that also benefit POWER9.
- A variety of optimizations for the x86_64 kernels.
- Improving the kernels for Loongson 3A/3B hardware.
- A generic BFloat16 SBGEMV kernel has been added.
- Various other fixes.
OpenBLAS 0.3.13 downloads and the full change-log via GitHub.
8 Comments