OSchip
/
OpenBLAS
mirror of https://github.com/xianyi/OpenBLAS.git
0
0
Fork 2
Code Issues Packages Projects Releases Wiki Activity
9,676 Commits 58 Branches 70 Tags 121 MiB
Commit Graph

2619 Commits

Author SHA1 Message Date
pengxu ba9569e382 Loongarch64: fixed dot_lasx 2025-04-30 16:41:48 +08:00
pengxu dc5fa29851 Loongarch64: fixed cscal_lasx 2025-04-30 16:41:39 +08:00
pengxu a98dd6d911 Loongarch64: fixed copy_lasx 2025-04-30 16:41:28 +08:00
pengxu d49319c2d2 Loongarch64: fixed cnrm2_lasx 2025-04-30 16:41:18 +08:00
pengxu 74c97ef814 Loongarch64: fixed cdot_lasx 2025-04-30 16:41:05 +08:00
pengxu be525521ad Loongarch64: fixed asum_lasx 2025-04-30 16:40:55 +08:00
pengxu 0cd5ca5527 Loongarch64: fixed amax_lasx 2025-04-30 16:40:44 +08:00
guoyuanplct 11ffc8680e Format the code 2025-04-25 00:27:27 +08:00
guoyuanplct 7616c42095 Optimized RVV_ZVL256B Implementation of zgemv_n 
The implementation of zgemv_n using RVV_ZVL256B has been optimized.
Compared to the previous implementation, it has achieved a 1.5x
performance improvement.
 2025-04-25 00:05:15 +08:00
abhishek-fujitsu 9c02cdb073 optimise dot using thread throttling for NEOVERSE V1 2025-04-23 22:35:05 +05:30
Martin Kroeker d0e8fd6d40
Merge pull request #5239 from annop-w/gemv_n_sve 
Use SVE kernel for S/DGEMVN for SVE machines
 2025-04-22 10:19:49 -07:00
Iha, Taisei 08b5c18d70 fixed a potential out-of-bounds on gemv. 2025-04-22 19:56:44 +09:00
Annop Wongwathanarat e11744a411 Use SVE kernel for S/DGEMVN for SVE machines 2025-04-22 09:40:13 +00:00
Martin Kroeker db0abfa907
Merge pull request #5238 from martin-frbg/revert5125 
remove non-vectorized SGEMV transpose reduce path for POWER8, restoring optimizations frpm PR4880
 2025-04-22 02:12:19 -07:00
Martin Kroeker 7389b6c483
Merge pull request #5237 from martin-frbg/revert5219 
Fix and reinstate the Cooper Lake/Sapphire Rapids microkernel for non-transpose SBGEMV
 2025-04-21 23:36:23 -07:00
Martin Kroeker 4ec62d7f73
remove non-vectorized code path for power8, restoring PR4880 2025-04-21 23:14:10 +02:00
Martin Kroeker 1df8738f27
Merge pull request #5235 from quickwritereader/issue_unaligned_ppc64le 
Explicit unaligned vector load/stores in PPC64LE GEMV kernels
 2025-04-21 14:03:56 -07:00
Martin Kroeker 99d9f1ff38
Fix conditional 2025-04-21 22:55:45 +02:00
Martin Kroeker 96d80801bc
Reinstate the CooperLake microkernel 2025-04-21 22:53:26 +02:00
Martin Kroeker 2e4309315c
Merge pull request #5219 from martin-frbg/sbgemvn_cooper 
Temporarily disable the Cooper Lake/Sapphire Rapids microkernel for non-transpose SBGEMV
 2025-04-20 07:29:20 -07:00
Ubuntu 0cc2485594 Explicit unaligned vector load/stores in PPC64LE GEMV kernels 2025-04-20 08:00:29 +00:00
Martin Kroeker dd38b4e811
Merge pull request #5225 from annop-w/gemv_n 
Improve performance for SGEMVN on NEONVERSEN1
 2025-04-17 01:54:10 -07:00
Martin Kroeker 0241d516f6
Merge pull request #5220 from iha-taisei/sdgemv_n_unroll 
Further performance improvements to non-transposed [SD]GEMV kernels for A64FX and Neoverse V1.
 2025-04-16 12:55:55 -07:00
Annop Wongwathanarat d535728803 Improve performance for SGEMVN on NEONVERSEN1 2025-04-16 09:54:30 +00:00
Usui, Tetsuzo d711906e3e Add symv kernels for arm64 2025-04-11 20:39:52 +09:00
Iha, Taisei f1e628b889 Further performance improvements to [SD]GEMV. 2025-04-11 20:00:33 +09:00
Martin Kroeker 211dfd0754
disable the CooperLake microkernel as it produces wrong results 2025-04-10 22:21:57 +02:00
Martin Kroeker b30dc9701f
Merge pull request #5215 from annop-w/gemv_t 
Use SVE kernel for S/DGEMVT for SVE machines
 2025-04-10 13:06:07 -07:00
Martin Kroeker 2893d0add4
Merge pull request #5211 from guoyuanplct/develop 
Optimizing the Implementation of GEMV on the RISC-V V Extension
 2025-04-10 09:43:03 -07:00
Annop Wongwathanarat ec146157d3 Use SVE kernel for S/DGEMVT for SVE machines 2025-04-09 20:38:14 +00:00
Martin Kroeker 70865a894e
Merge pull request #5180 from ywwry66/openmp_use_cmake 
CMake: Pass `OpenMP` compiler and linker flags through CMake targets
 2025-04-08 13:16:07 -07:00
lglglglgy 1ff303f36e Optimizing the Implementation of GEMV on the RISC-V V Extension 
Specialized some scenarios, performed loop unrolling, and reduced the
number of multiplications.
 2025-04-08 21:18:00 +08:00
ColumbusAI 7bf848454d
Update zsum.c -- fixed spelling error to successfully compile 
spelling error where zsum_kernel is used and it should be zasum_kernel. Will not compile without fix.
 2025-04-05 09:57:53 -07:00
Vaisakh K V 04915be829 Add vector registers to clobber list to prevent compiler optimization. 
SME based SGEMMDIRECT kernel uses the vector registers (z) and adding
    clobber list informs compiler not to optimize these registers.
 2025-04-03 12:18:43 +05:30
Egbert Eich ea6515c4b3 On zarch don't produce objects from assembler with a writable stack section 
On z-series, the current version of the GNU toolchain produces warnings
such as:
```
/usr/lib64/gcc/[...]/s390x-suse-linux/bin/ld: warning: ztrmm_kernel_RC_Z14.o: missing .note.GNU-stack section implies
executable stack
/usr/lib64/[...]/s390x-suse-linux/bin/ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker
```
To prevent this message and make sure we are future proof, add
```
	.section        .note.GNU-stack,"",@progbits
```
Also add the `.size` bit to give the asm defined functions a proper size
in the symbol table.

Signed-off-by: Egbert Eich <eich@suse.com>
 2025-03-28 18:47:48 +01:00
Ruiyang Wu 02fd1df10b CMake: Pass `OpenMP` compiler and linker flags through CMake targets 
Using `OpenMP::OpenMP_LANG` targets for CMake is less error-prone than
passing the compiler and linker flags manually. Furthermore, it allows
the user to customize those flags by setting `OpenMP_LANG_FLAGS`,
`OpenMP_LANG_LIB_NAMES`, and `OpenMP_omp_LIBRARY`.
 2025-03-26 23:09:54 -04:00
Ye Tao f27ba5efd1 fix bugs in aarch64 sbgemv_n kernel 2025-03-14 17:55:40 +00:00
Annop Wongwathanarat edef2e4441 Fix bug in ARM64 sbgemv_t 2025-03-13 20:55:31 +00:00
Martin Kroeker b55ca71d5b
Merge pull request #5182 from annop-w/sgemm_ncopy 
Optimize aarch64 sgemm_ncopy
 2025-03-13 16:04:39 +01:00
Martin Kroeker 2f778554b8
Merge pull request #5181 from taoye9/change_sbgemn_cast_bf16 
replace customize bf16_to_fp32 with arm neon vcvtah_f32_bf16
 2025-03-13 13:50:26 +01:00
Annop Wongwathanarat 9807f56580 Optimize aarch64 sgemm_ncopy 2025-03-13 10:17:43 +00:00
Martin Kroeker a3e7b16072
Merge pull request #5157 from manaalmj/feature 
Optimize gemv_n_sve kernel
 2025-03-12 21:08:23 +01:00
Ye Tao 4c00099ed6 replace customize bf16_to_fp32 with arm neon vcvtah_f32_bf16 2025-03-12 16:20:15 +00:00
Annop Wongwathanarat a085b6c9ec Fix aarch64 sbgemv_t compilation error for GCC < 13 2025-03-12 14:52:42 +00:00
manjam01 5c4e38ab17 Optimize gemv_n_sve kernel 2025-03-10 16:39:20 +00:00
Martin Kroeker 1d5ed5c46b
Merge pull request #5168 from taoye9/add_sbgemvn_on_neonversen2 
Add dispatch of SBGEMVNKERNEL for NEOVERSEN2 and NEOVERSEV2
 2025-03-04 16:39:22 +01:00
Ye Tao 6b8b35cdf2 fix minior issues of redeclaration of float x0,x1 in sbgemv_n_neon.c 2025-03-03 11:55:27 +00:00
Ye Tao 38ee7c9301 Add dispatch of SBGEMVNKERNEL for NEOVERSEN2 and NEOVERSEV2 2025-03-03 11:32:05 +00:00
Martin Kroeker 2b941c44b5
Merge branch 'develop' into sbgemv_n_neon 2025-03-02 22:39:32 +01:00
Ye Tao 35bdbca153 Add sbgemv_n_neon kernel for arm64. 2025-02-28 14:37:06 +00:00
Annop Wongwathanarat edaf51dd99 Add sbgemv_t_bfdot kernel for ARM64 
This improves performance for sbgemv_t by up to 100x on NEOVERSEV1.
The geometric mean speedup is ~61x for M=N=[2,512].
 2025-02-28 12:31:50 +00:00
Martin Kroeker 77fba0f400
Fix "dummy2" flag handling 2025-02-22 20:09:21 +01:00
Martin Kroeker eb84aac7ad
Merge pull request #5084 from quic/topic/sgemm_direct_sme1 
Support for SGEMM_DIRECT Kernel based on SME1
 2025-02-19 10:56:49 +01:00
Martin Kroeker b9ae246f20
define USE_TRMM for RISCV64 targets as well 2025-02-16 23:18:04 +01:00
Vaisakh K V f66ca05b31
Merge branch 'develop' into topic/sgemm_direct_sme1 2025-02-13 14:54:37 +05:30
Vaisakh K V d23eb3b93e Support for SME1 based sgemm_direct kernel for cblas_sgemm level 3 API 
* Added ARMV9SME target
* Added SGEMM_DIRECT kernel based on SME1
 2025-02-13 14:51:21 +05:30
Martin Kroeker 8d487ef6eb
Merge pull request #5124 from XiWeiGu/LoongArch64-LA264-lapack-fixed 
LoongArch64: Fixed lapack test for LA264
 2025-02-12 14:58:30 +01:00
Martin Kroeker 81eed868b6
Restore the non-vectorized code from before PR4880 for POWER8 2025-02-12 09:07:20 +01:00
Martin Kroeker 98b5ef929c
Restore the non-vectorized code from before PR4880 for POWER8 2025-02-12 09:04:22 +01:00
gxw 2c4a5cc6e6 LoongArch64: Fixed snrm2_lsx.S and cnrm2_lsx.S 
When the data type is single-precision real or single-precision complex,
converting it to double precision does not prevent overflow (as exposed in LAPACK tests).
The only solution is to follow C's approach: find the maximum value in the
array and divide each element by that maximum to avoid this issue
 2025-02-12 15:48:01 +08:00
gxw 9e75d6b3d1 LoongArch64: Fixed swap_lsx.S 
Fixed the error when the stride is zero
 2025-02-12 14:57:35 +08:00
gxw e8c740368c LoongArch64: Fixed rot_lsx.S ane crot_lsx.S 
Do not check whether the input parameters c and s are zero,
as this may cause errors with special values (same as scal).
Although OpenBLAS's own test suite doesn't catch this, it will
cause LAPACK test cases to fail.
 2025-02-12 14:52:49 +08:00
Hao Chen c2212d0abd LoongArch64: Fixed copy_lsx.S 
Fixed incorrect store operation

Signed-off-by: gxw <guxiwei-hf@loongson.cn>
 2025-02-12 14:52:20 +08:00
Hao Chen 7f1ebc7ae6 LoongArch64: Fixed iamax_lsx.S 
Fixed index retrieval issue when there are
identical maximum absolute values

Signed-off-by: Hao Chen <chenhao@loongson.cn>
Signed-off-by: gxw <guxiwei-hf@loongson.cn>
 2025-02-12 14:44:44 +08:00
Hao Chen 31d326f895 LoongArch64: Fixed dot_lsx.S 
Fixed incorrect register usage in instructions

Signed-off-by: gxw <guxiwei-hf@loongson.cn>
 2025-02-12 14:44:11 +08:00
Hao Chen 5d6356bc16 LoongArch64: Fixed amax_lsx.S 
Fixed register zeroing operation

Signed-off-by: Hao Chen <chenhao@loongson.cn>
Signed-off-by: gxw <guxiwei-hf@loongson.cn>
 2025-02-12 14:39:29 +08:00
Ye Tao c748e6a338 optimized sbgemm kernel for neoverse-v1 (sve-256) 
Signed-off-by: Ye Tao <ye.tao@arm.com>
 2025-02-05 10:06:37 +00:00
Aditya Tewari 4379a6fbe3 * checkpoint sbgemm for SVE-256 2025-02-03 12:49:49 +00:00
Martin Kroeker d7036cfd74
Remove trailing blanks that break the cmake parser 2025-01-27 09:32:17 +01:00
Martin Kroeker 6e393a5599
Merge branch 'develop' into gemv_t 2025-01-25 12:54:04 +01:00
Martin Kroeker 876ba58e28
Merge pull request #5091 from goplanid/develop 
Small gemm kernel improvements for AArch64
 2025-01-24 10:59:16 +01:00
Martin Kroeker 180ba5e7d0
Merge pull request #5069 from tingboliao/dev_rotm_20250107 
Further rearranged the rotm kernel for the different architectures.
 2025-01-23 10:16:43 +01:00
Deeksha Goplani d1bfa979f7 small gemm kernel packing modifications 2025-01-23 09:41:45 +05:30
Martin Kroeker 1a6a9fb22f
add another generator line for rotm 2025-01-23 00:17:04 +01:00
Martin Kroeker 4924319c50
fix position of srotm, qrotm 2025-01-22 16:07:35 +01:00
Martin Kroeker b58cba9eb6
fix qrotm build rules 2025-01-22 15:51:49 +01:00
gxw 2da86b80c9 LoongArch64: Fixed scalar version of cscal and zscal 2025-01-22 14:32:20 +08:00
gxw 5392f6df69 LoongArch64: Fixed LASX version of cscal and zscal 2025-01-22 14:15:27 +08:00
tingbo.liao 3c8df6358f Further rearranged the rotm kernel for the different architectures. 
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com>
 2025-01-22 11:41:12 +08:00
Annop Wongwathanarat c0318cea6e Simplify gemv_t_sve_v1x3 kernel 2025-01-21 13:40:17 +00:00
gxw b2117bb2ca LoongArch64: Fixed LSX version of cscal and zscal 2025-01-21 14:49:44 +08:00
gxw e114880dc4 kernel/generic: Fixed cscal and zscal 2025-01-21 11:44:22 +08:00
Martin Kroeker 87083fdbf6
[WIP] Work around assembler limitations in current LLVM for Windows on Arm (#5076) 
* Protect align directives in assembly files that are currently problematic with LLVM on WoA

* use the armv8 zdot on WoA to work around other LLVM issues
 2025-01-18 16:45:56 +01:00
tingbo.liao ef7f54b357 Optimized the gemm_tcopy_8_rvv to be compatible with the vlens 128 and 256. 
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com>
 2025-01-15 11:31:28 +08:00
gxw e0a8216554 LoongArch64: Update dsymv LSX version 2025-01-14 19:45:42 +08:00
gxw a9070ba3f9 LoongArch64: Update ssymv LSX version 2025-01-14 09:06:59 +00:00
Xi Ruoyao af10c132b8
LoongArch64: Fix dsymv and ssymv LASX version 
"fmov.d $f2, $f4" leaves all the bits higher than the 63-th bit
unpredictable but it's obvious that the following code uses the value of
those high bits.  We actually want to replicate the lower 64 bits here,
so we should use xvreplve0.d instead.

LA464 (Loongson 3[A-Z]-5000) happens to replicate them for us due to
some uarch internal details so the issue was not detected, but for LA664
(Loongson 3[A-Z]-6000) and future uarch we need to do things correctly
or we end up getting a lot of test failures.

Closes: https://bbs.aosc.io/t/topic/302
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
 2025-01-13 22:16:00 +08:00
Martin Kroeker d74eb02954
Merge pull request #5057 from martin-frbg/issue5050 
Replace while loop in generic C/ZGEMM_BETA to avoid going out of bounds
 2025-01-11 11:33:56 -08:00
Martin Kroeker 30f7a4120b
Merge pull request #5056 from tingboliao/dev_omatcopy_20250108 
Optimize the omatcopy_cn/zomatcopy_cn kernels with RVV 1.0 intrinsic.
 2025-01-11 09:42:57 -08:00
gxw 20a8e48f25 LoongArch64: Update ssymv LASX version 2025-01-10 16:02:54 +08:00
gxw e0748588b8 LoongArch64: Update dsymv LASX version 2025-01-10 14:52:57 +08:00
Martin Kroeker d91d4fa6e9
convert the beta=0 branch to a for loop as well 2025-01-09 23:11:26 +01:00
Martin Kroeker 09e75f1588
fix absurd typo 2025-01-09 00:52:14 +01:00
Martin Kroeker 2891fd8d6d
Replace while loop with for 2025-01-08 23:17:45 +01:00
tingbo.liao 0a5dbf13d3 Optimize the omatcopy_cn and zomatcopy_cn kernels with RVV 1.0 intrinsic. 
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com>
 2025-01-08 11:00:35 +08:00
Sergey Fedorov 229efa42ff scal.S: use r11 on 32-bit Darwin on powerpc 2025-01-05 00:31:27 +08:00
Sergey Fedorov 81e1be8d90 Revert "temporarily disable the default S/DSCAL kernel" 
This reverts commit 9b9c0aa5c9.
 2025-01-04 22:54:54 +08:00
Martin Kroeker 9b9c0aa5c9
temporarily disable the default S/DSCAL kernel 2025-01-03 21:36:46 +01:00
tingbo.liao c37509c213 Optimize the nrm2_rvv function to further improve performance. 
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com>
 2024-12-31 08:46:55 +08:00
tingbo.liao 0bea1cfd9d Optimize the zgemm_tcopy_4_rvv function to be compatible with the situations where the vector lengths(vlens) are 128 and 256. 
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com>
 2024-12-24 10:33:27 +08:00
tingbo.liao d00cc400b1 Replaced the __riscv_vid_v_i32m2 and __riscv_vid_v_i64m2 with __riscv_vid_v_u32m2 and __riscv_vid_v_u64m2 for riscv64-unknown-linux-gnu-gcc compiling. 
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com>
 2024-12-18 08:38:30 +08:00
Martin Kroeker 229d8a025e
Merge pull request #4959 from CDAC-Bengaluru/level-1-sve 
SVE Implementation for Level-1 BLAS Routines
 2024-12-13 05:20:51 -08:00
SushilPratap04 3368a4e697
Update swap_kernel_sve.c 2024-12-13 16:47:58 +05:30
CDAC-SSDG dd71e4234a
Added Updated swap and rot sve kernels. 2024-12-13 11:15:29 +05:30
CDAC-SSDG 06ffd411a5
Update KERNEL.ARMV8SVE 2024-12-13 11:05:47 +05:30
CDAC-SSDG 765850194e
Delete kernel/arm64/swap_kernel_sve.c 2024-12-13 11:02:01 +05:30
CDAC-SSDG c17c19fbcf
Delete kernel/arm64/swap_kernel_c.c 2024-12-13 11:01:46 +05:30
CDAC-SSDG f6416c0e37
Delete kernel/arm64/swap.c 2024-12-13 11:01:32 +05:30
CDAC-SSDG 3b7b74664c
Delete kernel/arm64/scal_kernel_sve.c 2024-12-13 11:01:03 +05:30
CDAC-SSDG 95a97012e8
Delete kernel/arm64/scal_kernel_c.c 2024-12-13 11:00:45 +05:30
CDAC-SSDG 5540f2121e
Delete kernel/arm64/scal.c 2024-12-13 11:00:12 +05:30
CDAC-SSDG f62519cc87
Delete kernel/arm64/rot_kernel_sve.c 2024-12-13 10:59:35 +05:30
CDAC-SSDG 10857c9df4
Delete kernel/arm64/rot_kernel_c.c 2024-12-13 10:58:51 +05:30
CDAC-SSDG b9f51a5cf7
Delete kernel/arm64/rot.c 2024-12-13 10:58:06 +05:30
Martin Kroeker 81666de4ef
Merge pull request #5007 from martin-frbg/issue5006 
Revert the NRM2 kernels for NeoverseN2 and ARMV8SVE targets to the generic NEON version
 2024-12-05 14:43:03 -08:00
Martin Kroeker 3345007d8f
retire the thunderx2 NRM2 kernels due to reported inaccuracies and NAN 2024-12-05 21:12:06 +01:00
Martin Kroeker 5fe983db29
retire the thunderx2 nrm2 kernels for now due to NAN and inaccuracies 2024-12-05 21:09:53 +01:00
Iha, Taisei 4918beecbe Loop-unrolled transposed [SD]GEMV kernels for A64FX and Neoverse V1 2024-12-02 18:46:00 +09:00
Juliya32 3b2421cba0
Add files via upload 2024-10-30 14:23:42 +05:30
Juliya32 012fe4da36
Delete kernel/arm64/rot_kernel_sve.c 2024-10-30 14:23:15 +05:30
Juliya32 d90ee00f85
Delete kernel/arm64/rot_kernel_c.c 2024-10-30 14:22:51 +05:30
Juliya32 668e28adc4
Delete kernel/arm64/rot.c 2024-10-30 14:22:31 +05:30
SushilPratap04 fa880ab1cf
Update KERNEL.ARMV8SVE 
updated KERNEL.ARMV8SVE for level 1 sve (swap, rot and scal) kernels.
 2024-10-30 14:09:37 +05:30
SushilPratap04 7822ae9617
Added sve kernels for rot routine. 2024-10-30 14:05:21 +05:30
SushilPratap04 b8bc2a752e
Added sve optimized kernels for swap routine 2024-10-30 14:02:57 +05:30
CDAC-SSDG 0667cf6c92
Added optimized scal routine files 2024-10-30 14:01:09 +05:30
gxw 73c6a28073 x86_64: opt somatcopy_ct with AVX 2024-10-29 07:06:15 +00:00
Ayappan Perumal 020cce1068 Fix build issues with gcc compiler as well 2024-10-23 04:24:06 -05:00
Ayappan Perumal b6ec73e77c Fix AIX build 2024-10-21 07:38:03 -05:00
Martin Kroeker 016bdb9b0b
Merge pull request #4946 from XiWeiGu/la64_omatcopy_lasx 
LoongArch64: Opt somatcopy with LASX
 2024-10-18 14:03:06 +02:00
Chip Kerchner ab71a1edf2 Better VSX. 2024-10-17 08:25:02 -05:00
gxw bb31bbef52 LoongArch64: Opt somatcopy_ct with LASX 2024-10-17 11:45:13 +00:00
gxw b37129341b LoongArch64: Opt somatcopy_cn with LASX 2024-10-17 11:27:55 +00:00
gxw acf6cab304 LoongArch64: Opt somatcopy_rn with LASX 2024-10-17 09:50:02 +00:00
gxw 15edb441bf LoongArch64: Opt somatcopy_rt with LASX 2024-10-17 09:15:42 +00:00
Chip Kerchner 36bd3eeddf Vectorize BF16 GEMV (VSX & MMA). Use GEMM_GEMV_FORWARD_BF16 (for Power). 2024-10-13 13:46:11 -05:00
Martin Kroeker e52d9b4cf1
Merge pull request #4928 from austinpagan/czgemm_in_c 
CGEMM & ZGEMM using C code, Power only, P10 only.
 2024-10-09 20:26:21 +02:00
Gordon Fossum 0b7fb5c791 CGEMM & ZGEMM using C code. 2024-10-09 09:42:23 -05:00
Martin Kroeker 9783dd07ab
Rename KERNEL.LOONGSONGENERIC to KERNEL.LA64_GENERIC 2024-10-06 22:43:11 +02:00
Martin Kroeker c9e92348a6
Handle inf/nan if dummy2 flag is set 2024-10-06 19:57:17 +02:00
Martin Kroeker d714013ab9
change sgemm kernel to 4x4 as the 16x4 altivec goes out of bounds 2024-10-03 22:04:20 +02:00
Martin Kroeker de421b7764
Merge pull request #4904 from XiWeiGu/la64_cross_cmake 
LoongArch64: Enable cmake cross-compilation
 2024-10-03 15:53:57 +02:00
gxw 30af9278dc LoongArch64: Enable cmake cross-compilation 2024-09-29 10:13:30 +08:00
gxw 48698b2b1d LoongArch64: Rename core 
Use microarchitecture name instead of meaningless strings to name the core,
the legacy core is still retained.
1. Rename LOONGSONGENERIC to LA64_GENERIC
2. Rename LOONGSON3R5 to LA464
3. Rename LOONGSON2K1000 to LA264
 2024-09-29 09:35:21 +08:00
Deeksha Goplani 4894c54055 Improve TN case with further unrolling 2024-09-02 22:22:49 +05:30
Martin Kroeker e05d98d00a
expressly use fld.d/fst.d for floating point registers instead of LD/ST macros 2024-08-15 22:14:29 +02:00
Chip Kerchner a0aeba631d Merge branch 'develop' into betterPowerGEMVTail 2024-08-15 08:00:00 -05:00
Chip Kerchner 083faf7556 Merge branch 'develop' into betterPowerGEMVTail 2024-08-14 15:56:03 -05:00
Chip Kerchner 75472b830a Merge branch 'develop' into betterPowerGEMVTail 2024-08-14 10:52:46 -05:00
Henry Chen ef94b96530 Use ldc1 and sdc1 for the prologue and epilogue on LOONGSON3A 
This fix is similar to
2d8064174c.
 2024-08-14 18:05:11 +08:00
Martin Kroeker 7ca835a82c
address clang array overflow warning 2024-08-10 13:44:56 +02:00
Martin Kroeker 46e331a917
remove the unworkable GEMM3M restriction from GENERIC again 2024-08-07 19:41:10 +02:00
Martin Kroeker ccc23338d7
have the dummy GEMM3M kernel at least forward to regular GEMM 2024-08-07 19:39:02 +02:00
Martin Kroeker f1c9803f9a
add proper return statement 2024-08-04 00:14:31 +02:00
Martin Kroeker 60abcc3991
add proper return statement 2024-08-04 00:13:31 +02:00
Chip Kerchner 1a7b8c650d Merge branch 'develop' into betterPowerGEMVTail 2024-08-01 14:59:12 -05:00
Martin Kroeker 9afd0c8afd
Merge pull request #4814 from Mousius/gemv-proxy 
Forward GEMM to GEMV when one argument is actually a vector
 2024-07-31 23:18:01 +02:00
Martin Kroeker edbf093c98
Update zarch SCAL kernels to handle INF and NAN arguments (#4829) 
* handle INF and NAN in input (for S/D only if DUMMY2 argument is set)
 2024-07-31 19:45:15 +02:00
Chris Sidebottom ba2e989c67 Add accumulators to AArch64 GEMV Kernels 
This helps to reduce values going missing as we accumulate.
 2024-07-31 13:09:14 +01:00
Martin Kroeker a875304eb0
fix inverted conditional for NAN handling 2024-07-26 09:50:20 +02:00
Martin Kroeker 24acdd6bbb
correct offset 2024-07-26 09:49:24 +02:00
Martin Kroeker fb7c53c5e5
Merge pull request #4807 from martin-frbg/scalfixes 
[WIP]Make NAN handling in the SCAL kernels depend on the dummy2 parameter
 2024-07-25 23:42:50 +02:00
Martin Kroeker 15c53dd2e0
Merge pull request #4794 from XiWeiGu/Fixed_Numpy_CI_Test 
Try to fixed numpy ci test failures
 2024-07-25 23:42:13 +02:00
Martin Kroeker a4e56e0452
Merge pull request #4806 from Mousius/small-gemm 
Small GEMM for AArch64 with SVE
 2024-07-25 21:50:04 +02:00
yamazaki-mitsufumi 88caf02f62 Fix ambiguous error on Mac OS 2024-07-25 22:43:13 +09:00
Martin Kroeker b613754143
Update scal..c 2024-07-24 14:31:29 +02:00
Martin Kroeker f5d04318e3
Merge branch 'OpenMathLib:develop' into scalfixes 2024-07-21 13:43:43 +02:00
Martin Kroeker 73f8866ffb
make NAN handling depend on DUMMY2 parameter 2024-07-21 13:42:47 +02:00
Martin Kroeker dfbc2348a8
fix NAN handling 2024-07-20 18:27:15 +02:00
Martin Kroeker c064319ecb
fix alpha=NAN case 2024-07-20 17:42:31 +02:00
Martin Kroeker c2ffd90e8c
make NAN handling depend on dummy2 parameter 2024-07-20 17:31:00 +02:00
Chris Sidebottom ea4ab3b310 Better header guard around bridge 2024-07-20 14:39:57 +01:00
Chris Sidebottom 7311d93016 Unroll TT further 2024-07-19 17:51:20 +01:00
Martin Kroeker a815594fd1
Merge pull request #4801 from markdryan/markdryan/riscv-dynamic-arch 
Add autodetection for riscv64
 2024-07-19 17:12:07 +02:00
Martin Kroeker dd6c33d34d
make NAN handling depend on dummy2 parameter 2024-07-19 16:14:55 +02:00
Hong Bo Peng db98f8753f Try to fix LAPACK testing failures on P7. 
1. Remove the FADD insn from the GEMV Transpose code.
  2. Remove the FADD insn from GEMM and ZGEMM code.
  3. Reorder the compution of the Imaginary part in ZGEMM code.
 2024-07-19 02:08:19 -04:00
Chris Sidebottom a9edddb695 Unroll TN further 2024-07-18 20:04:15 +01:00
Chris Sidebottom 9984c5ce9d Clean up k2 removal more and unroll SGEMM more 2024-07-18 18:35:43 +01:00
Chris Sidebottom b1c9fafabb Remove k2 loop from DGEMM TN and use a more conservative heuristic for SGEMM 2024-07-18 17:37:18 +01:00
Martin Kroeker 2020569705
fix NAN handling and make it depend on dummy2 parameter 2024-07-17 23:55:54 +02:00
Martin Kroeker 3870995f01
make NAN handling depend on dummy2 parameter 2024-07-17 23:54:24 +02:00
Martin Kroeker 7284c533b5
make NAN handling depend on dummy2 parameter 2024-07-17 23:50:40 +02:00
Martin Kroeker 73751218a4
make NAN handling depend on dummy2 parameter 2024-07-17 23:41:26 +02:00
Martin Kroeker b9bfc8ce09
make NAN handling depend on dummy2 parameter 2024-07-17 23:29:50 +02:00
Martin Kroeker eb4879e04c
make NAN handling depend on the dummy2 parameter 2024-07-17 23:24:19 +02:00
Martin Kroeker ee87cb90d0
Merge pull request #4803 from iha-taisei/SVESupportSDGEMV 
A64FX: Add support for SVE to SGEMV/DGEMV kernels.
 2024-07-17 23:14:21 +02:00
gxw 34b80ce03f mips64: Fixed numpy CI failure 2024-07-17 10:32:22 +08:00
gxw f6d6c14a96 mips: Fixed numpy CI failure 2024-07-17 10:31:49 +08:00
Chip Kerchner ba47c7f4f3 Vectorize reduction stage of sgemv_t. 2024-07-16 15:57:24 -05:00
iha fujitsu 0985fdc82b A64FX: Add support for SVE to SGEMV/DGEMV kernels. 2024-07-16 17:31:33 +09:00
Mark Ryan 67bf4b6998 Fix axpby_rvv kernels for cases where inc_y = 0 
The following openblas_utest tests fail when the RISCV64_ZVL128B is
enabled.

TEST 89/103 axpby:zaxpby_inc_0 [FAIL]
TEST 92/103 axpby:caxpby_inc_0 [FAIL]
TEST 95/103 axpby:daxpby_inc_0 [FAIL]
TEST 98/103 axpby:saxpby_inc_0 [FAIL]

The issue is that the vectorized kernels do not work when inc_y == 0.
This patch updates the kernels to fall back to the scalar algorithms
when inc_y == 0, fixing the failing tests.

Signed-off-by: Mark Ryan <markdryan@rivosinc.com>
 2024-07-15 14:24:47 +00:00
Mark Ryan 3b715e6162 Add autodetection for riscv64 
Implement DYNAMIC_ARCH support for riscv64.  Three cpu types are
supported, riscv64_generic, riscv64_zvl256b, riscv64_zvl128b.
The two non-generic kernels require CPU support for RVV 1.0 to
function correctly.  Detecting that a riscv64 device supports
RVV 1.0 is a little complicated as there are some boards on the
market that advertise support for V via hwcap but only support
RVV 0.7.1, which is not binary compatible with RVV 1.0.  The
approach taken is to first try hwprobe.  If hwprobe is not
available, we fall back to hwcap + an additional check to distinguish
between RVV 1.0 and RVV 0.7.1.

Tested on a VM with VLEN=256, a CanMV K230 with VLEN=128 (with only
the big core enabled), a Lichee Pi with RVV 0.7.1 and a VF2 with no
vector.

A compiler with RVV 1.0 support must be used to build OpenBLAS for
riscv64 when DYNAMIC_ARCH=1.

Signed-off-by: Mark Ryan <markdryan@rivosinc.com>
 2024-07-15 14:24:22 +00:00
gxw 3f39c8f94f LoongArch: Fixed numpy CI failure 2024-07-15 11:43:08 +08:00
gxw f3cebb3ca3 x86: Fixed numpy CI failure when the target is ZEN. 2024-07-12 16:09:30 +08:00
Martin Kroeker 5d08ec7ff3
Merge pull request #4782 from martin-frbg/azurewincl 
Fix NAN handling in ARM/generic SCAL; have AzureCI Windows show errors on failure
 2024-07-11 23:55:15 +02:00
Chip Kerchner cb154832f8 Vectorize SBGEMM incopy - 4x faster. 2024-07-09 13:10:03 -05:00
Martin Kroeker a5c04e326a
Update scal.c 2024-07-04 22:28:01 +02:00
Martin Kroeker 536200bc9e
fix handling of INF or NAN 2024-07-04 17:47:19 +02:00
Martin Kroeker 3677b3886c
Merge pull request #4702 from bashimao/detect-nv-grace 
Correctly detect ARM Neoverse V2 CPUs.
 2024-06-30 22:48:48 +02:00
Martin Kroeker f3c364c2cc
temporarily(?) disable the alpha=0 branch as it fails to handle INF,NAN 2024-06-27 22:18:27 +02:00