Commit Graph

  • e9c32ed165
    Merge pull request #4384 from yetist/develop Martin Kroeker 2023-12-27 14:05:01 +0100
  • e7a895e714
    Add Apple M as NeoverseN1 Martin Kroeker 2023-12-25 12:36:05 +0100
  • 474ce0ace9
    Merge pull request #4393 from martin-frbg/pr4389-2 Martin Kroeker 2023-12-25 12:30:56 +0100
  • 1106460bb3
    remove redundant targets from the default ARM64 DYNAMIC_ARCH list Martin Kroeker 2023-12-25 12:29:56 +0100
  • 236acee706
    Merge pull request #4389 from Mousius/reduce-dynamic-targets Martin Kroeker 2023-12-25 12:27:42 +0100
  • d2f4f1b28a CI: update toolchains for LoongArch64 Xiaotian Wu 2023-12-20 14:13:04 +0800
  • 0baf462dbc Fix: build failed on LoongArch Wu Xiaotian 2023-12-20 10:34:47 +0800
  • 63a83939a1
    Merge pull request #4390 from Mousius/reduce-kernel-duplication Martin Kroeker 2023-12-24 18:04:26 +0100
  • dba404055d
    Merge pull request #4392 from martin-frbg/lapack959 Martin Kroeker 2023-12-24 10:44:15 +0100
  • c6fa921027
    Add tests for ?GEDMD (Reference-LAPACK PR 959) Martin Kroeker 2023-12-23 23:39:53 +0100
  • 283713e4c5
    Add tests for ?GEDMD (Reference-LAPACK PR 959) Martin Kroeker 2023-12-23 23:32:45 +0100
  • 201f22f49a
    Fix issues related to ?GEDMD (Reference-LAPACK PR 959) Martin Kroeker 2023-12-23 23:27:38 +0100
  • 05dde8ef04
    Merge pull request #4391 from martin-frbg/lapack942 Martin Kroeker 2023-12-23 23:11:46 +0100
  • 45ef0d7361
    Handle corner cases of LWORK (Reference-LAPACK PR 942) Martin Kroeker 2023-12-23 20:16:33 +0100
  • c082669ad4
    Handle corner cases of LWORK (Reference-LAPACK PR 942) Martin Kroeker 2023-12-23 20:05:03 +0100
  • 29d6024ec5
    Handle corner cases of LWORK (Reference-LAPACK PR 942) Martin Kroeker 2023-12-23 19:44:11 +0100
  • 0814491d96
    Handle corner cases of LWORK (Reference-LAPACK PR 942) Martin Kroeker 2023-12-23 19:37:03 +0100
  • 5c11b2ff41
    Handle corner cases of LWORK (Reference-LAPACK PR 942) Martin Kroeker 2023-12-23 19:27:20 +0100
  • 8ce44c18a0
    Handle corner cases of LWORK (Reference-LAPACK PR 942) Martin Kroeker 2023-12-23 19:24:10 +0100
  • dc20a78188 Use functionally equivalent dynamic targets Chris Sidebottom 2023-12-23 12:19:33 +0000
  • ecae1389df Reduce duplication in kernel definitions Chris Sidebottom 2023-12-23 12:21:48 +0000
  • 68ef2328eb
    Merge pull request #4388 from martin-frbg/issue4387 Martin Kroeker 2023-12-21 22:21:44 +0100
  • a7ed60bfe9
    Add lower limit for multithreading Martin Kroeker 2023-12-21 20:05:23 +0100
  • 67779177b9
    Merge pull request #4383 from martin-frbg/fixlapatest Martin Kroeker 2023-12-20 14:01:59 +0100
  • e67a0eaaf9
    Restore OpenBLAS-specific build rule changes Martin Kroeker 2023-12-19 23:15:11 +0100
  • bb8b91e9f2
    restore OpenBLAS-specific test paths Martin Kroeker 2023-12-19 23:13:02 +0100
  • fa220b2969
    Merge pull request #4382 from Mousius/sve-dot-again Martin Kroeker 2023-12-19 18:46:18 +0100
  • 3f46d0c79a
    Merge pull request #4381 from darshanp4/issue_4323 Martin Kroeker 2023-12-19 16:53:53 +0100
  • 60e66725e4 Use numeric labels to allow repeated inlining Chris Sidebottom 2023-12-19 13:11:06 +0000
  • 7a4fef4f60 Tweak SVE dot kernel Chris Sidebottom 2023-12-15 12:50:48 +0000
  • dab0da8243 Update GEMM param for NEOVERSEV1 Darshan Patel 2023-12-19 13:56:55 +0530
  • 5bdde6299c
    test loading numpy/openblas on neoversen1 Martin Kroeker 2023-12-17 18:42:30 +0100
  • 3b520a56a9
    Merge pull request #4378 from martin-frbg/issue3871 Martin Kroeker 2023-12-15 21:58:56 +0100
  • 563daadc92
    Merge pull request #4379 from barracuda156/ppc970 Martin Kroeker 2023-12-15 20:03:44 +0100
  • 8c143331b0 PPC970: drop -mcpu=970 which seems to produce faulty code barracuda156 2023-12-15 22:55:52 +0800
  • d2f1594bca
    Merge pull request #4368 from martin-frbg/issue4073 Martin Kroeker 2023-12-15 14:49:52 +0100
  • 544cb86300
    Mention C906V instruction set limitation and update DYNAMIC_ARCH lists Martin Kroeker 2023-12-15 14:03:59 +0100
  • 8793601e86
    Merge pull request #4375 from martin-frbg/issue4352 Martin Kroeker 2023-12-15 13:35:18 +0100
  • f06b535566
    Use C kernel for dgemv_t due to limitations of the old assembly one Martin Kroeker 2023-12-15 09:58:44 +0100
  • 293131d6b9
    Merge pull request #4370 from barracuda156/unbreak_powerpc Martin Kroeker 2023-12-14 10:30:03 +0100
  • 981e315b30 cc.cmake: use -force_cpusubtype_ALL for Darwin PPC barracuda156 2023-12-14 12:01:31 +0800
  • d9653af018 KERNEL.PPC970, KERNEL.PPCG4: unbreak CMake parsing barracuda156 2023-12-13 19:23:50 +0800
  • 302ca7edc7
    Merge pull request #4371 from barracuda156/970 Martin Kroeker 2023-12-13 14:32:37 +0100
  • a8d3619f65 cc.cmake: add optflags for G5 and G4 kernels barracuda156 2023-12-13 19:42:56 +0800
  • aa46f1e4e7
    revert addition of MSVC-compatible complex (moved to lapacke_config.h) Martin Kroeker 2023-12-12 23:07:48 +0100
  • dcdc351272
    Add MSVC-compatible complex types Martin Kroeker 2023-12-12 23:06:22 +0100
  • 55a0718f72
    Merge pull request #4369 from ChipKerchner/power10Copies Martin Kroeker 2023-12-12 18:49:21 +0100
  • 93747fb377 Merge remote-tracking branch 'origin/develop' into power10Copies Chip-Kerchner 2023-12-12 09:32:49 -0600
  • dcf6999c4e
    remove extraneous endif Martin Kroeker 2023-12-12 11:27:17 +0100
  • 6bd7c54af5 introduce MT_TRACE to clean up SMP_DEBUG code Mark Seminatore 2023-12-11 15:13:04 -0800
  • 330101e0b3
    Add complex type definitions for MSVC Martin Kroeker 2023-12-11 21:52:00 +0100
  • d9f1478068
    Merge pull request #4367 from barracuda156/unbreak_powerpc Martin Kroeker 2023-12-11 21:38:32 +0100
  • 9dbc8129b3 cpuid_power.c: add CPU_SUBTYPE_POWERPC_7400 case barracuda156 2023-12-11 21:09:06 +0800
  • c732f275a2 system_check.cmake: fix arch detection for Darwin PowerPC barracuda156 2023-12-11 21:05:31 +0800
  • e60fb0f397
    Merge pull request #4359 from mseminatore/win_perf Martin Kroeker 2023-12-09 23:40:26 +0100
  • efa9515a23
    Merge branch 'OpenMathLib:develop' into win_perf Mark Seminatore 2023-12-09 10:09:49 -0800
  • 4e738e561a Replace two vector loads with one vector pair load and fix endianess of stores. Chip-Kerchner 2023-12-08 12:36:08 -0600
  • 1332f8a822
    Merge pull request #4159 from OMaghiarIMG/risc-v-tail-policy Martin Kroeker 2023-12-08 10:25:41 +0100
  • edac80d7e8 some cleanup, dynamically scale threads, add missing WIN_CASE defn Mark Seminatore 2023-12-07 14:59:27 -0800
  • 2d316c2920
    Merge pull request #4125 from OMaghiarIMG/risc-v Martin Kroeker 2023-12-07 14:50:58 +0100
  • 5b09833b1c
    Merge pull request #4019 from uniontech-lilinjie/develop Martin Kroeker 2023-12-07 14:46:17 +0100
  • 3193aa9c7e
    Merge pull request #4362 from yinshiyou/la-dev Martin Kroeker 2023-12-07 09:15:15 +0100
  • d32f38fb37 loongarch64: Add optimizations for nrm2. yancheng 2023-12-07 13:15:55 +0800
  • f9b468990e loongarch64: Add optimizations for rot. yancheng 2023-12-07 13:12:29 +0800
  • c80e7e27d1 loongarch64: Add optimizations for sum and asum. yancheng 2023-12-07 13:08:03 +0800
  • d4c96a35a8 loongarch64: Add optimizations for axpy and axpby. yancheng 2023-12-07 13:02:03 +0800
  • 360acc0a41 loongarch64: Add optimizations for swap. yancheng 2023-12-07 12:57:05 +0800
  • 174c25766b loongarch64: Add optimizations for copy. yancheng 2023-12-07 12:15:46 +0800
  • 49829b2b7d loongarch64: Add optimizations for iamin. yancheng 2023-12-07 12:11:30 +0800
  • be83f5e4e0 loongarch64: Add optimizations for iamax. yancheng 2023-12-07 12:07:30 +0800
  • e3fb2b5afa loongarch64: Add optimizations for imin. yancheng 2023-12-07 12:01:05 +0800
  • e46b48e372 loongarch64: Add optimizations for imax. yancheng 2023-12-07 11:56:41 +0800
  • 702fc1d56d loongarch64: Add optimization for min. yancheng 2023-12-07 11:51:19 +0800
  • 346b384d1c loongarch64: Add optimization for max. yancheng 2023-12-07 11:30:02 +0800
  • ff2ecc6cda loongarch64: Add optimization for amin. yancheng 2023-12-07 11:08:09 +0800
  • 265b5f2e80 loongarch64: Add optimizations for amax. yancheng 2023-12-07 10:57:13 +0800
  • 993ede7c70 loongarch64: Add optimizations for scal. yancheng 2023-11-27 11:30:34 +0800
  • 4ebf814b42 fix bug failing to mark task as finished. Mark Seminatore 2023-12-05 23:28:37 -0800
  • 5f51811728 try at new threading model Mark Seminatore 2023-12-05 22:43:36 -0800
  • a8cb611157
    Merge pull request #4358 from martin-frbg/lapack954 Martin Kroeker 2023-12-05 22:20:15 +0100
  • 589f2b6466
    Fix search phrase used to count successful tests (Reference-LAPACK PR 954) Martin Kroeker 2023-12-05 20:10:20 +0100
  • 6aa5f53e26
    Merge pull request #4357 from martin-frbg/lapack953 Martin Kroeker 2023-12-05 20:03:21 +0100
  • effb7af2a2
    Fix memory leak (Reference-LAPACK PR 953) Martin Kroeker 2023-12-05 17:55:38 +0100
  • 5915a69734
    Merge pull request #4356 from martin-frbg/lapack736-2 Martin Kroeker 2023-12-05 17:48:42 +0100
  • 226a14c549
    Restore library path adjustments Martin Kroeker 2023-12-05 15:50:06 +0100
  • c5fa318add
    Add tests for DMD (Reference-LAPACK PR 736) Martin Kroeker 2023-12-05 15:45:59 +0100
  • fa03e5497a
    Add tests for the DMD functions (Reference-LAPACK PR 736) Martin Kroeker 2023-12-05 15:43:28 +0100
  • a53a79e059
    Add tests for the DMD functions (Reference-LAPACK PR 736) Martin Kroeker 2023-12-05 15:41:39 +0100
  • e3039fa7f6
    Merge pull request #4351 from catap/cmake-old-macos Martin Kroeker 2023-12-05 14:40:18 +0100
  • 4a12cf53ec [RISC-V] Improve RVV kernel generator LMUL usage Octavian Maghiar 2023-12-04 11:13:35 +0000
  • e4586e81b8 [RISC-V] Add RISC-V Vector 128-bit target Octavian Maghiar 2023-12-04 11:02:18 +0000
  • 2381132ada Darwin < 20: always write xerbla.c.o into archive Erik Bråthen Solem 2023-12-03 19:13:53 +0100
  • 89fa51d495 Revert 42b5e08 ("Allow weak linking on old macOS") Erik Bråthen Solem 2023-12-03 19:06:49 +0100
  • 08fde5ebd2
    Use 64bit build on `CMAKE_SYSTEM_PROCESSOR=i386` on Darwin Kirill A. Korinsky 2023-11-30 21:24:58 +0000
  • 39bf8ece20
    Merge pull request #4340 from yinshiyou/la-dev Martin Kroeker 2023-11-29 08:22:25 +0100
  • 42b5e081d8
    Merge pull request #4348 from catap/macos-undefinded-dynamic-lookup Martin Kroeker 2023-11-28 22:14:53 +0100
  • a1562e4bae
    Allow weak linking on old macOS Kirill A. Korinsky 2023-11-28 14:04:01 +0000
  • c4a622db9e
    Merge pull request #4346 from martin-frbg/issue4343 Martin Kroeker 2023-11-28 14:01:14 +0100
  • 9fe07d82fd loongarch: Add LSX optimization for dot. Shiyou Yin 2023-11-24 17:57:14 +0800
  • 13b8c44b44 loongarch: Add optimization for dsdot kernel. Shiyou Yin 2023-11-24 16:40:32 +0800