OpenMathLib/OpenBLAS - CodSpeed

OpenBLAS

Blog Docs Changelog

Performance History

Latest Results

Unroll inner loop - 2 rows at a time. Up to 1.5X faster.

ChipKerchner:fasterRVVGEMV

1 day ago

Merge pull request #5824 from mathomp4/bugfix/5823-fix-for-nag Fix shared lib build with NAG Fortran on macOS

develop

4 days ago

cmake: fix shared lib build with NAG Fortran on macOS On Apple, the shared library link rule for Fortran used GCC-specific flags: -x f95-cpp-input (GCC preprocessing flag; NAG does not support it) -Wl,-shared (Linux linker flag; macOS needs -dynamiclib) The fix is NAG-specific — other non-GNU compilers (Intel, flang, Cray, etc.) are left alone since they may handle the existing code paths fine. Fix in two places (both already inside if(APPLE) / if(APPLE AND BUILD_STATIC_LIBS)): 1. Before add_library() (affects the main CMake Fortran shared lib rule): For NAG Fortran, substitute CMAKE_C_CREATE_SHARED_LIBRARY so the C compiler link rule is used instead. 2. Inside the APPLE AND BUILD_STATIC_LIBS block (the static->shared conversion trick for long argument lists): add an elseif(NAG) branch that uses the C compiler with -dynamiclib and auto-detects the NAG Fortran runtime (libf72rts) from the compiler's directory so that NAGf90_* symbols resolve. Tested with NAG 7.2.7243 on macOS/arm64.

mathomp4:bugfix/5823-fix-for-nag

5 days ago

optimize zgemm lsx kernel for 2k3000 cpu

ErnstPeng:la-dev

6 days ago

docs: clarify RISC-V RVV target selection and GCC 14+ requirement for ZVL128B/ZVL256B Add two notes to the RISC-V section before the per-target entries: 1. RISCV64_GENERIC is intentionally scalar — Makefile.riscv64 appends a scalar march override that takes precedence over any user-supplied -march=rv64gcv. Correct targets for RVV 1.0 are RISCV64_ZVL128B and RISCV64_ZVL256B (see #3808 for design rationale). 2. GCC 14+ required for _rvv.c kernels on current OpenBLAS. GCC 13 builds complete and produce a library but routines using segmented load/store intrinsics (__riscv_vsseg*) fall back to scalar silently. Functional tests pass; only disassembly detects this. Verified on OpenBLAS 0.3.33: GCC 13 (scalar fallback), GCC 14 (~12,691 RVV opcodes), GCC 15 (~14,355 RVV opcodes). Co-authored-by: Vaibhav805 <Vaibhav805@users.noreply.github.com>

trg-rgb:docs/riscv-zvl-target-selection

9 days ago

Merge pull request #5820 from martin-frbg/issue5818 Fix misoptimization of C/ZGETF2 by Clang on Apple M

develop

10 days ago

Make temp1 volatile to keep Clang on AppleM from optimizing out the division guards

martin-frbg:issue5818

10 days ago

Merge pull request #5803 from Sid-MB/develop Makefile.install: fix PKGFILE expression so it works with paths with spaces

develop

10 days ago

Latest Branches

0%

Faster GEMV for RVV#5826

1 day ago

6a23c36

ChipKerchner:fasterRVVGEMV

0%

Fix shared lib build with NAG Fortran on macOS#5824

5 days ago

7a2b8b5

mathomp4:bugfix/5823-fix-for-nag

0%

optimize zgemm lsx kernel for 2k3000 cpu#5822

6 days ago

6731dac

ErnstPeng:la-dev

© 2026 CodSpeed Technology

Home Terms Privacy Docs