OpenBLAS

OpenBLAS copied to clipboard

Make it work on general MIPS64 processors

3

This PR addressed some build failures for ARCH_MIPS64, also provide a MIPS64_GENERIC target so we should be able to use OpenBLAS on Cavium processors.

FlyGoat

GitHub Actions: Add cross compile tests

6

Add cross compile tests without running checks. Currently only mips64el and riscv64 is wired up. Just help us make sure those less popular CPUs are not messed up by changes....

FlyGoat

In the [User Manual](https://github.com/xianyi/OpenBLAS/wiki/User-Manual#install-to-the-directory-optional), it says: "Note that any flags passed to make during build should also be passed to make install to circumvent any install errors." This should also...

haanhvu

Add vcpkg installation instructions

2

OpenBLAS is available as a port in vcpkg. Adding installation instructions will help users get started by providing a single command they can use to build OpenBLAS and include it...

grdowns

LoongArch64: Rename targets

1

The existing targets naming convention for LoongArch64 is not appropriate(lack of microarchitecture-specific thoughts). Now I use LA464, LA264 to replace the original targets.

XiWeiGu

Fix build on new-world LoongArch

49

This is fix for https://bugs.gentoo.org/844013. The LoongArch port is tested only on old-world systems, and fails to build on new-world distros such as Gentoo. I can successfully build and test...

xen0n

Request GEMMT API

15

Intel MKL provides an additional GEMM variant, GEMMT, that updates only the upper or lower triangular part of the result matrix. This would be a great addition to OpenBLAS. https://software.intel.com/en-us/node/590047

edelsohn

OpenBLAS seg fault while building with gcc 10.2.0 & Fortran 2018

4

I'm using the latest version of OpenBLAS GCC/10.2.0 Fortran 2018 ```sh Program received signal SIGSEGV: Segmentation fault - invalid memory reference. Backtrace for this error: #0 0x2B1A0777C6D7 #1 0x2B1A0777CD1E #2...

RylanYancey

Above average kernel times causing slow performance

33

Hi! In comparing OpenBLAS performance with Intel MKL I've noticed that (at least in my particular case: real or hermitian eigenvalue problem, e.g. ZHEEV) OpenBLAS is consuming too much more...

bgeneto

No need to set OMP num_threads

13

No need to set num_threads, as num_threads(num) will cause more new threads' overhead in some scenarios. In openMP, if your required threads num is larger than your last used num,...

kangshan1157