phynexis-deps/OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
9,717 Commits 60 Branches 70 Tags
371663f0c26bc4384406c65e18e1066a5ab89f7e
Commit Graph
9717 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Jameson Nash 371663f0c2 fix define for YIELDING 
The intent is to define this as nop, but previously it was then
immediately overriding it for various architectures, causing a compiler
warning on Windows.
 2025-12-23 13:59:29 -05:00
Martin Kroeker 68ff451ecc Merge pull request #5558 from ErnstPeng/fix-LA 
Fix floating point registers ld/st bug of Loongarch
 2025-12-03 16:02:06 +01:00
pengxu f6533ccea0 Fix floating point registers ld/st bug of Loongarch 2025-12-03 10:52:59 +08:00
Martin Kroeker d6b25c43c6 Merge pull request #5542 from abhishek-iitmadras/abhishek_new_tt_a64fx 
[A64FX]: add tt for a64fx dot
 2025-11-23 22:55:51 +01:00
Martin Kroeker 5b79d01424 Merge pull request #5434 from ywwry66/mixed_openmp_warning 
CMake: Demote the OpenMP mixed linkage check to NOTICE
 2025-11-23 21:25:28 +01:00
Martin Kroeker 48e33f23e8 Merge pull request #5543 from ayappanec/AIX-compiler-checks 
Skip C and Fortran compiler combination checks in AIX if NO_FORTRAN or ONLY_CBLAS is set
 2025-11-23 19:16:12 +01:00
Martin Kroeker 7cef9524f7 Merge pull request #5550 from martin-frbg/flangppc 
Fix PPC compilation with flang and gmake
 2025-11-23 18:01:39 +01:00
Martin Kroeker 88c1899b88 Merge pull request #5549 from mayeut/warn-bfloat16 
fix(warning): taking the absolute value of 'bfloat16' has no effect
 2025-11-23 17:53:38 +01:00
Martin Kroeker 0d5bf7b760 flang does not understand -frecursive 2025-11-23 10:09:43 +01:00
Martin Kroeker 93d0d195a0 Merge pull request #5547 from martin-frbg/oryon_cachesizes 
Report proper cache sizes for Qualcomm Oryon in WoA
 2025-11-23 10:06:27 +01:00
mayeut c5e1967ddb fix(warning): taking the absolute value of 'bfloat16' has no effect 
The compinv function is invalid when building for BFLOAT16 and leads to the following warning:
`taking the absolute value of unsigned type 'bfloat16' (aka 'unsigned short') has no effect`.
Update pre-processor conditions to remove its definition when building for BFLOAT16.
 2025-11-23 09:40:04 +01:00
Martin Kroeker 58ee3c0761 Merge pull request #5544 from mayeut/rpcc-aarch64 
fix: rpcc on linux aarch64
 2025-11-22 22:28:44 +01:00
Martin Kroeker fa0403bd17 Report proper cache sizes for Qualcomm Oryon in WoA 2025-11-22 18:46:44 +01:00
Martin Kroeker 29fab2b912 Merge pull request #5546 from martin-frbg/issue5545 
Fix compilation of the PPC SBGEMM kernels with LLVM
 2025-11-22 17:36:15 +01:00
Martin Kroeker f7b7296bff Fix compilation with LLVM 2025-11-22 16:07:34 +01:00
mayeut a367f5f58b fix: rpcc on linux aarch64 
The inline assembly code seems ill-formed and gcc/clang are not generating the same thing.
This also removes hundreds of `warning: value size does not match register size specified by the constraint and modifier` when building with clang.
 2025-11-22 09:40:18 +01:00
Ayappan Perumal 64b9600724 Skip C and Fortran compiler combination checks in AIX if NO_FORTRAN or ONLY_CBLAS is set 2025-11-21 03:17:00 -06:00
Abhishek Kumar a14caf464f add tt for a64fx dot 
Signed-off-by: Abhishek Kumar <abhishek.r.kumar@fujitsu.com>
 2025-11-20 12:14:17 +05:30
Martin Kroeker 28eeef5bbe Merge pull request #5538 from CheryDan/riscv/rot 
Optimize ZROT_RVV for the unit-stride case (inc_x = inc_y = 1)
 2025-11-19 07:33:08 +01:00
Martin Kroeker a51a1b8e1f Merge pull request #5540 from Thyre/support-flang-new-integer-8 
Makefile: Recognize `-fdefault-integer-8` for LLVMs flang
 2025-11-19 00:13:31 +01:00
Martin Kroeker 17f2e94260 Merge pull request #5539 from FRosner/arm64-dot-kernel-refactoring 
Refactoring: ARM64 dot Kernel: don't call num_cpu_avail twice
 2025-11-18 23:25:51 +01:00
Martin Kroeker 75ceb6c69f Merge pull request #5536 from mayeut/clang-sve 
fix: dot_kernel_sve "n" usage & clobber list
 2025-11-18 22:04:13 +01:00
Jan André Reuter ccef6ccde7 Recognize -fdefault-integer-8 for LLVMs flang 
Signed-off-by: Jan André Reuter <jan@zyten.de>
 2025-11-18 19:19:15 +01:00
Frank Rosner 762ed66c72 Refactoring: ARM64 dot Kernel: don't call num_cpu_avail twice 2025-11-18 15:34:51 +01:00
daichengrong 98a8230dee Optimize ZROT_RVV for the unit-stride case (inc_x = inc_y = 1) 2025-11-18 17:34:27 +08:00
mayeut 39d5e44723 fix: dot_kernel_sve "n" usage & clobber list 2025-11-17 21:53:51 +01:00
Martin Kroeker f6df9bebbb Merge pull request #5533 from martin-frbg/azure-osxgcc 
AzureCI: Update the obsolete OSX x86_64 gcc12 job to gcc15
 2025-11-08 15:31:53 +01:00
Martin Kroeker aa7e9abf52 Merge pull request #5531 from martin-frbg/issue5510 
Fix CYGWIN builds that use CMake
 2025-11-07 15:15:23 +01:00
Martin Kroeker bbb87aa5c2 Update OSX gcc12 job to gcc15 2025-11-07 14:51:52 +01:00
Martin Kroeker f00c0d0827 CYGWIN builds currently require blas_server_win32 2025-11-07 12:20:31 +01:00
Martin Kroeker 8a0b97e0d3 CYGWIN needs to be named OS_CYGWIN_NT in config.h 2025-11-07 12:18:22 +01:00
Martin Kroeker f2d010de12 Merge pull request #5512 from quic/topic/ssyrk_direct_sme1 
Support for SME1 based ssyrk_direct kernel for cblas_ssyrk level 3 API
 2025-11-06 14:06:43 -08:00
Martin Kroeker 65af1b1401 Merge pull request #5530 from martin-frbg/riscv_sbgemmCI 
CI: Add back the SBGEMM/SBGEMV tests on RISCV64_ZVL256B
 2025-11-06 08:06:25 -08:00
Martin Kroeker 7bdb3ac720 Add back the SBGEMM/SBGEMV tests 2025-11-06 14:38:20 +01:00
Martin Kroeker 123c25c748 Merge pull request #5527 from ChipKerchner/fixbfloat16Tobf16conversions 
Prevent possible conversion from bfloat16 to __bf16 - RISC-V
 2025-11-06 03:17:58 -08:00
Chip Kerchner 00a7336fc9 Missing one gemv conversion. 2025-11-04 22:27:53 +00:00
Chip Kerchner edf2e5900c Prevent possible conversion from bfloat16 to __bf16. 2025-11-04 21:00:37 +00:00
Chip Kerchner 7ca689b54f Merge remote-tracking branch 'refs/remotes/origin/develop' into develop 2025-11-04 13:55:15 +00:00
Martin Kroeker 3a9da520d5 RISCV64-CI: don't rely on dependency resolution for qemu-user (#5506) 
* install current qemu as the Ubuntu package is too old
* add shgemm and bgemm tests for zvl256b target - curiously, sbgemm&sbgemv tests fail in this configuration
 2025-11-04 12:18:24 +01:00
Chip Kerchner 93e89c09be Merge remote-tracking branch 'refs/remotes/origin/develop' into develop 2025-11-03 23:19:59 +00:00
Martin Kroeker 9c8626d73a Merge pull request #5522 from Smilyf/bugfix/issue-5521 
Fix #5521: add @SUFFIX64@ in OpenBLASConfig.cmake.in
 2025-11-02 03:00:04 -08:00
Martin Kroeker 2e7c667c11 Merge pull request #5526 from martin-frbg/fixcirrusxcode 
Update Xcode version in Cirrus CI
 2025-11-02 02:59:15 -08:00
Martin Kroeker 2b745f816d Update Xcode SDK versions as well 2025-11-02 10:01:46 +01:00
Martin Kroeker 716feb6704 Merge pull request #5525 from martin-frbg/issue5524 
CMake: Fix missing support for HFLOAT16 in Windows dll generation
 2025-11-02 01:58:36 -07:00
Martin Kroeker aa43496936 Update Xcode 2025-11-01 22:00:16 +01:00
Martin Kroeker 358c582ef9 Fix missing support for HFLOAT16 in Windows symbol renaming/dll generation 2025-11-01 19:27:56 +01:00
Yang Desheng 1da3b47163 Fix #5521: add @SUFFIX64@ in OpenBLASConfig.cmake.in 2025-11-01 20:42:48 +08:00
Martin Kroeker 18eb6a7f70 Merge pull request #5519 from martin-frbg/issue5517 
Introduce a minimum problem size requirement for multithreading in the hermitian operations
 2025-10-30 14:39:56 -07:00
Martin Kroeker ef6f97624b [WIP,Testing] remove the lock around the thread shutdown function again (#5479) 
* remove the lock around the thread shutdown function - server is locked already here
 2025-10-30 19:12:47 +01:00
Martin Kroeker 0c59ae0b45 Merge pull request #5453 from pratiklp00/dgemm_optimization 
Dgemm loop unroll and 4x1, 4x2 dgemv VSX implementation for power10.
 2025-10-28 16:51:41 -07:00