OpenBLAS

OpenBLAS copied to clipboard

Build error with CMake + DYNAMIC_ARCH=OFF + FMA3: _mm256_fmadd_ps compiled without -mfma (target specific option mismatch)

2

Step to reproduce build error: Host: modern x86_64 with AVX2 + FMA3. Build: CMake, DYNAMIC_ARCH=OFF (e.g. vcpkg). Results in GCC errors in sdot_k / _mm256_fmadd_ps due to missing -mfma. My...

toblil

Hi @martin-frbg , I wanted to know if there's any tentative date for release / branchcut for 0.31.0 ? I was referring to the milestone here: [Milestone-0.31.0](https://github.com/OpenMathLib/OpenBLAS/milestone/50)/

aditew01

Updated SGEMV ramps.

1

Significant performance improvements are gained by the proposed changes on both c7g (NEOVERSEV1) and c8g (NEOVERSEV2) instances. To reproduce these values you need to run with OMP_ADAPTIVE=1. The plots below...

almayne

Setting optimized `[SD]GEMM_DEFAULT_[PQR]` parameters for `A64FX`

2

Resolves #5553. The parameters `[SD]GEMM_DEFAULT_[PQR]` have been tuned to obtain the performance improvement in `[SD]GEMM` under the multi-process evaluation using all cores of `A64FX`. This change improves the performance of...

hideaki-motoki

`BIGNUMA` and `NUM_THREADS>256` on 2×192-core AmpereOne (AArch64)

3

Hi, I’d like clarification on using OpenBLAS on a 2×192-core AmpereOne (384 cores total), AArch64 Linux. Planned build: ```bash make TARGET=ARMV8 USE_OPENMP=1 NUM_THREADS=384 BIGNUMA=1 ``` Docs mention a default 256-core...

DanielWicz

build tests test/dblat1 and ctest/xdcblat1 fail on OpenIndiana SPARC

5

while building OpenBLAS-0.3.30 on OpenIndiana SPARC the following error happens in directory: test OPENBLAS_NUM_THREADS=1 OMP_NUM_THREADS=1 ./dblat1 Real BLAS Test Program Results ... Test of subprogram number 7 DNRM2 Program received...

klausz65

The parameters `[SD]GEMM_DEFAULT_[PQR]` are already set in `param.h` for several CPUs, but those values do not appear to be fine-tuned for `A64FX`. I am willing to resolve this issue.

hideaki-motoki

Revert "CMake: Pass `OpenMP` compiler and linker flags through CMake targets"

3

Reverts OpenMathLib/OpenBLAS#5180 , fixes #5412

martin-frbg

ci: add build with clang on ppc64le

1

Add a CI run for clang on ppc64le in order to prevent build/tests regressions. related to #5545

mayeut

cblas_sgemm has wrong result on apple M4

1

0.3.30 version It seems that cblas_sgemm() always output the zero result. ``` #include #include #include #include #include void generate_random_matrix(float *matrix, int rows, int cols) { for (int i = 0;...

kon0740