phynexis-deps/OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
f6d4fe703b0148c0ffe45eea7f9290be2ce32257
OpenBLAS/kernel
T
History
Murray Steele f6d4fe703b Fix incorrect cast from BF16 to FP32 in SBGEMM 
This change fixes a regression in SBGEMM where C is assumed to be BF16,
and so unconditionally casts the output to FP32 resulting in incorrect
outputs when beta=1.
2026-03-26 12:10:52 +00:00
..
alpha
Further rearranged the rotm kernel for the different architectures.
2025-01-22 11:41:12 +08:00
arm
Enable DSUM SIMD path for WASM128_GENERIC
2026-03-20 18:39:53 +09:00
arm64
Declare result as volatile to keep compilers from optimizing it out
2026-03-20 11:32:23 +01:00
csky
Further rearranged the rotm kernel for the different architectures.
2025-01-22 11:41:12 +08:00
e2k
Further rearranged the rotm kernel for the different architectures.
2025-01-22 11:41:12 +08:00
generic
Fix incorrect cast from BF16 to FP32 in SBGEMM
2026-03-26 12:10:52 +00:00
ia64
Further rearranged the rotm kernel for the different architectures.
2025-01-22 11:41:12 +08:00
loongarch64
Fix floating point registers ld/st bug of Loongarch
2025-12-03 10:52:59 +08:00
mips
resync with the generic arm version for inf/nan handling
2025-06-13 00:54:27 -07:00
mips64
fix path
2025-06-13 13:37:15 +02:00
power
Add pragma to limit optimization level
2026-02-22 13:42:41 +01:00
riscv64
Optimize ZROT_RVV for the non-unit-stride case
2026-03-16 14:22:54 +08:00
simd
Add WASM SIMD widening path for DSDOT
2026-03-19 14:16:18 +09:00
sparc
Use the generic C kernel for DNRM2
2026-01-11 21:58:31 +01:00
wasm
Use generic DDOT kernel for WASM128_GENERIC
2026-03-19 14:15:32 +09:00
x86
override CDOT and ZDOT with the generic C kernel
2025-06-17 22:41:40 +02:00
x86_64
Merge pull request #5685 from teddygood/wasm-intrin-backend-exp
2026-03-18 21:49:53 +01:00
zarch
Add dummy2 flag handling
2025-05-25 14:47:06 -07:00
CMakeLists.txt
set USE_TRMM for WASM
2026-03-15 23:07:16 +01:00
Makefile
typo
2026-01-15 00:03:24 +01:00
Makefile.L1
Add infrastructure for bgemv/bscal
2025-07-15 14:48:57 +01:00
Makefile.L2
Add Infrastructure for SHGEMV
2025-10-07 15:03:24 +00:00
Makefile.L3
set USE_TRMM for WASM
2026-03-15 23:07:16 +01:00
Makefile.LA
Support NO_LAPACK=1 to build the lib without LAPACK functions.
2011-03-04 11:51:32 +08:00
setparam-ref.c
Add GEMM_DIVIDE_RATE and GEMM_PREFERRED_SIZE to parameters
2026-03-20 15:32:06 +01:00