OpenBLAS

Tree: f90eff306d

History

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		11 months ago
..
KERNEL	Further rearranged the rotm kernel for the different architectures.	1 year ago

KERNEL.LA64_GENERIC	Rename KERNEL.LOONGSONGENERIC to KERNEL.LA64_GENERIC	1 year ago

KERNEL.LA264	LoongArch64: Rename core	1 year ago

KERNEL.LA464	LoongArch64: Opt somatcopy_ct with LASX	1 year ago

KERNEL.generic	Further rearranged the rotm kernel for the different architectures.	1 year ago

Makefile	Add support for LOONGARCH64	4 years ago

amax.S	Add support for LOONGARCH64	4 years ago

amax_lasx.S	loongarch64: Refine amax,amin,max,min optimization.	2 years ago

amax_lsx.S	LoongArch64: Fixed amax_lsx.S	11 months ago

amin.S	Add support for LOONGARCH64	4 years ago

amin_lasx.S	loongarch: Fixed {s/d/sc/dz}amin LASX opt	1 year ago

amin_lsx.S	loongarch: Fixed {s/d/sc/dz}amin LSX opt	1 year ago

asum.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

asum_lasx.S	loongarch64: Add and Refine asum optimization functions.	2 years ago

asum_lsx.S	loongarch64: Add and Refine asum optimization functions.	2 years ago

axpby_lasx.S	loongarch: Fixed {s/d/c/z}axpby LASX opt	1 year ago

axpby_lsx.S	loongarch: Fixed {s/d}axpby LSX opt	1 year ago

axpy_lasx.S	loongarch64: Refine and add axpy optimization functions.	2 years ago

axpy_lsx.S	loongarch64: Refine and add axpy optimization functions.	2 years ago

camax_lasx.S	loongarch: Fixed dzamax	1 year ago

camax_lsx.S	loongarch: Fixed dzamax	1 year ago

camin_lasx.S	loongarch: Fixed {s/d/sc/dz}amin LASX opt	1 year ago

camin_lsx.S	loongarch: Fixed {s/d/sc/dz}amin LSX opt	1 year ago

casum_lasx.S	loongarch64: Add and Refine asum optimization functions.	2 years ago

casum_lsx.S	loongarch64: Add and Refine asum optimization functions.	2 years ago

caxpby_lasx.S	loongarch: Fixed {s/d/c/z}axpby LASX opt	1 year ago

caxpby_lsx.S	LoongArch64: Opt {c/z}axpby	2 years ago

caxpy_lasx.S	loongarch64: Refine and add axpy optimization functions.	2 years ago

caxpy_lsx.S	loongarch64: Refine and add axpy optimization functions.	2 years ago

ccopy_lasx.S	loongarch64: Add c/zcopy optimization functions.	2 years ago

ccopy_lsx.S	loongarch64: Add c/zcopy optimization functions.	2 years ago

cdot_lasx.S	loongarch64: Add c/zdot optimization functions.	2 years ago

cdot_lsx.S	loongarch64: Add c/zdot optimization functions.	2 years ago

cgemm_kernel_2x2_lasx.S	loongarch64: Add zgemm and cgemm optimization	2 years ago

cgemm_kernel_2x2_lsx.S	loongarch64: Add zgemm and cgemm optimization	2 years ago

cgemm_kernel_8x4_lsx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

cgemm_kernel_16x4_lasx.S	expressly use fld.d/fst.d for floating point registers instead of LD/ST macros	1 year ago

cgemm_ncopy_2_lasx.S	loongarch64: Add zgemm and cgemm optimization	2 years ago

cgemm_ncopy_2_lsx.S	loongarch64: Add zgemm and cgemm optimization	2 years ago

cgemm_ncopy_4_lasx.S	Optimized cgemm kernel 16x4 LASX for LoongArch	1 year ago

cgemm_ncopy_4_lsx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

cgemm_ncopy_8_lsx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

cgemm_ncopy_16_lasx.S	Optimized cgemm kernel 16x4 LASX for LoongArch	1 year ago

cgemm_tcopy_2_lasx.S	loongarch64: Add zgemm and cgemm optimization	2 years ago

cgemm_tcopy_2_lsx.S	loongarch64: Add zgemm and cgemm optimization	2 years ago

cgemm_tcopy_4_lasx.S	Optimized cgemm kernel 16x4 LASX for LoongArch	1 year ago

cgemm_tcopy_4_lsx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

cgemm_tcopy_8_lsx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

cgemm_tcopy_16_lasx.S	Optimized cgemm kernel 16x4 LASX for LoongArch	1 year ago

cgemv_n_4_lsx.S	loongarch64: Fixed clang compilation issues	1 year ago

cgemv_n_8_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

cgemv_t_4_lsx.S	loongarch64: Fixed clang compilation issues	1 year ago

cgemv_t_8_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

cnrm2.S	Allow negative INCX (API change from version 3.10 of the reference implementation)	2 years ago

cnrm2_lasx.S	loongarch64: Add c/znrm2 optimization functions.	2 years ago

cnrm2_lsx.S	LoongArch64: Fixed snrm2_lsx.S and cnrm2_lsx.S	11 months ago

copy.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

copy_lasx.S	loongarch64: Refine copy,swap,nrm2,sum optimization.	2 years ago

copy_lsx.S	LoongArch64: Fixed copy_lsx.S	11 months ago

crot_lasx.S	loongarch64: Add c/zrot optimization functions.	2 years ago

crot_lsx.S	LoongArch64: Fixed rot_lsx.S ane crot_lsx.S	11 months ago

cscal_lasx.S	LoongArch64: Handle NAN and INF	2 years ago

cscal_lsx.S	LoongArch64: Handle NAN and INF	2 years ago

csum_lasx.S	loongarch: Fixed {s/d/c/z}sum LASX opt	1 year ago

csum_lsx.S	loongarch64: Add {c/z}swap and {c/z}sum optimization	2 years ago

cswap_lasx.S	loongarch64: Add {c/z}swap and {c/z}sum optimization	2 years ago

cswap_lsx.S	loongarch64: Add {c/z}swap and {c/z}sum optimization	2 years ago

dgemm_kernel_8x4.S	Add dgemm_kernel_8x4.S file.	2 years ago

dgemm_kernel_16x4.S	expressly use fld.d/fst.d for floating point registers instead of LD/ST macros	1 year ago

dgemm_kernel_16x6.S	loongarch64: Update dgemm_kernel_16x4 to dgemm_kernel_16x6	1 year ago

dgemm_ncopy_4.S	loongarch64: Optimize dgemm_kernel	4 years ago

dgemm_ncopy_4_lsx.S	Optimize copy functions with lsx.	2 years ago

dgemm_ncopy_8_lsx.S	loongarch64: Fixed utest fork:safety	1 year ago

dgemm_ncopy_16.S	loongarch64: Fixed utest fork:safety	1 year ago

dgemm_small_kernel_nn_lasx.S	LoongArch: DGEMM small matrix opt	1 year ago

dgemm_small_kernel_nt_lasx.S	LoongArch: DGEMM small matrix opt	1 year ago

dgemm_small_kernel_tn_lasx.S	LoongArch: DGEMM small matrix opt	1 year ago

dgemm_small_kernel_tt_lasx.S	LoongArch: DGEMM small matrix opt	1 year ago

dgemm_small_matrix_permit.c	LoongArch: DGEMM small matrix opt	1 year ago

dgemm_tcopy_4.S	loongarch64: Optimize dgemm_kernel	4 years ago

dgemm_tcopy_4_lsx.S	loongarch64: Fixed clang compilation issues	1 year ago

dgemm_tcopy_6.S	loongarch64: Update dgemm_kernel_16x4 to dgemm_kernel_16x6	1 year ago

dgemm_tcopy_8_lsx.S	loongarch64: Fixed clang compilation issues	1 year ago

dgemm_tcopy_16.S	loongarch64: Optimize dgemm_kernel	4 years ago

dgemv_n_8_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

dgemv_n_lsx.S	Optimized sgemv and dgemv kernel LSX for LoongArch	1 year ago

dgemv_t_8_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

dgemv_t_lsx.S	Optimized sgemv and dgemv kernel LSX for LoongArch	1 year ago

dnrm2.S	Allow negative INCX (API change from version 3.10 of the reference implementation)	2 years ago

dnrm2_lasx.S	loongarch64: Refine copy,swap,nrm2,sum optimization.	2 years ago

dnrm2_lsx.S	loongarch64: Refine copy,swap,nrm2,sum optimization.	2 years ago

dot.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

dot_lasx.S	remove stray comma	1 year ago

dot_lsx.S	LoongArch64: Fixed dot_lsx.S	11 months ago

dscal_lasx.S	loongarch64: Add optimizations for scal.	2 years ago

dscal_lsx.S	loongarch64: Add optimizations for scal.	2 years ago

dsymv_L_lasx.S	LoongArch64: Fix dsymv and ssymv LASX version	1 year ago

dsymv_L_lsx.S	LoongArch64: Update dsymv LSX version	1 year ago

dsymv_U_lasx.S	LoongArch64: Fix dsymv and ssymv LASX version	1 year ago

dsymv_U_lsx.S	LoongArch64: Update dsymv LSX version	1 year ago

dtrsm_kernel_LN_16x4_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

dtrsm_kernel_LT_16x4_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

dtrsm_kernel_RN_16x4_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

dtrsm_kernel_RT_16x4_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

dtrsm_kernel_macro.S	LoongArch64: Add dtrsm kernel	2 years ago

gemm_kernel.S	Add support for LOONGARCH64	4 years ago

gemm_ncopy_6.prefx.c	loongarch64: Update dgemm_kernel_16x4 to dgemm_kernel_16x6	1 year ago

gemv_n.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

gemv_t.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

iamax.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

iamax_lasx.S	loongarch64: Add and refine iamax optimization functions.	2 years ago

iamax_lsx.S	LoongArch64: Fixed iamax_lsx.S	11 months ago

iamin.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

iamin_lasx.S	loongarch: Fixed i{s/c/z}amin LASX opt	1 year ago

iamin_lsx.S	loongarch64: Refine iamin optimization.	2 years ago

icamax_lasx.S	loongarch64: Add and refine iamax optimization functions.	2 years ago

icamax_lsx.S	loongarch64: Fixed icamax_lsx	1 year ago

icamin_lasx.S	loongarch: Fixed i{s/c/z}amin LASX opt	1 year ago

icamin_lsx.S	loongarch: Fixed i{c/z}amin LSX opt	1 year ago

imax_lasx.S	loongarch64: Refine imax optimization.	2 years ago

imax_lsx.S	loongarch64: Refine imax optimization.	2 years ago

imin_lasx.S	loongarch64: Refine imin optimization.	2 years ago

imin_lsx.S	loongarch64: Refine imin optimization.	2 years ago

izamax.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

izamin.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

loongarch64_asm.S	loongarch64: Fixed clang compilation issues	1 year ago

max.S	Add support for LOONGARCH64	4 years ago

max_lasx.S	loongarch64: Refine amax,amin,max,min optimization.	2 years ago

max_lsx.S	loongarch64: Refine amax,amin,max,min optimization.	2 years ago

min.S	Add support for LOONGARCH64	4 years ago

min_lasx.S	loongarch64: Refine amax,amin,max,min optimization.	2 years ago

min_lsx.S	loongarch64: Refine amax,amin,max,min optimization.	2 years ago

rot_lasx.S	LoongArch64: Fixed utest kernel_regress:skx_avx	1 year ago

rot_lsx.S	LoongArch64: Fixed rot_lsx.S ane crot_lsx.S	11 months ago

scal.S	LoongArch: Fixed numpy CI failure	1 year ago

scal_lasx.S	LoongArch: Fixed numpy CI failure	1 year ago

scal_lsx.S	LoongArch: Fixed numpy CI failure	1 year ago

sgemm_kernel_16x8_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

sgemm_ncopy_8_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

sgemm_ncopy_16_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

sgemm_tcopy_8_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

sgemm_tcopy_16_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

sgemv_n_8_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

sgemv_n_lsx.S	Optimized sgemv and dgemv kernel LSX for LoongArch	1 year ago

sgemv_t_8_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

sgemv_t_lsx.S	Optimized sgemv and dgemv kernel LSX for LoongArch	1 year ago

snrm2.S	Allow negative INCX (API change from version 3.10 of the reference implementation)	2 years ago

snrm2_lasx.S	loongarch64: Refine copy,swap,nrm2,sum optimization.	2 years ago

snrm2_lsx.S	LoongArch64: Fixed snrm2_lsx.S and cnrm2_lsx.S	11 months ago

somatcopy_cn_lasx.c	LoongArch64: Opt somatcopy_cn with LASX	1 year ago

somatcopy_ct_lasx.c	LoongArch64: Opt somatcopy_ct with LASX	1 year ago

somatcopy_rn_lasx.c	LoongArch64: Opt somatcopy_rn with LASX	1 year ago

somatcopy_rt_lasx.c	LoongArch64: Opt somatcopy_rt with LASX	1 year ago

ssymv_L_lasx.S	LoongArch64: Fix dsymv and ssymv LASX version	1 year ago

ssymv_L_lsx.S	LoongArch64: Update ssymv LSX version	1 year ago

ssymv_U_lasx.S	LoongArch64: Fix dsymv and ssymv LASX version	1 year ago

ssymv_U_lsx.S	LoongArch64: Update ssymv LSX version	1 year ago

sum_lasx.S	loongarch: Fixed {s/d/c/z}sum LASX opt	1 year ago

sum_lsx.S	loongarch64: Refine copy,swap,nrm2,sum optimization.	2 years ago

swap.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

swap_lasx.S	loongarch64: Refine copy,swap,nrm2,sum optimization.	2 years ago

swap_lsx.S	LoongArch64: Fixed swap_lsx.S	11 months ago

trsm_kernel_LN.S	Add support for LOONGARCH64	4 years ago

trsm_kernel_LN_UNROLLN6.c	loongarch64: Update dgemm_kernel_16x4 to dgemm_kernel_16x6	1 year ago

trsm_kernel_LT.S	Add support for LOONGARCH64	4 years ago

trsm_kernel_LT_UNROLLN6.c	loongarch64: Update dgemm_kernel_16x4 to dgemm_kernel_16x6	1 year ago

trsm_kernel_RN_UNROLLN6.c	loongarch64: Update dgemm_kernel_16x4 to dgemm_kernel_16x6	1 year ago

trsm_kernel_RT.S	Add support for LOONGARCH64	4 years ago

trsm_kernel_RT_UNROLLN6.c	loongarch64: Update dgemm_kernel_16x4 to dgemm_kernel_16x6	1 year ago

zamax.S	Add support for LOONGARCH64	4 years ago

zamin.S	Add support for LOONGARCH64	4 years ago

zasum.S	Add support for LOONGARCH64	4 years ago

zcopy.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

zdot.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

zgemm3m_kernel.S	Add support for LOONGARCH64	4 years ago

zgemm_kernel.S	Add support for LOONGARCH64	4 years ago

zgemm_kernel_2x2.S	loongarch64: Add zgemm and cgemm optimization	2 years ago

zgemm_kernel_2x2_lasx.S	loongarch64: Add zgemm and cgemm optimization	2 years ago

zgemm_kernel_4x4_lsx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

zgemm_kernel_8x4_lasx.S	expressly use fld.d/fst.d for floating point registers instead of LD/ST macros	1 year ago

zgemm_ncopy_2_lasx.S	loongarch64: Add zgemm and cgemm optimization	2 years ago

zgemm_ncopy_4_lasx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

zgemm_ncopy_4_lsx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

zgemm_ncopy_8_lasx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

zgemm_tcopy_2_lasx.S	loongarch64: Add zgemm and cgemm optimization	2 years ago

zgemm_tcopy_4_lasx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

zgemm_tcopy_4_lsx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

zgemm_tcopy_8_lasx.S	Optimized zgemm kernel 84 LASX, 44 LSX and cgemm kernel 8*4 LSX for LoongArch	2 years ago

zgemv_n.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

zgemv_n_2_lsx.S	loongarch64: Fixed clang compilation issues	1 year ago

zgemv_n_4_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

zgemv_t.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

zgemv_t_2_lsx.S	loongarch64: Fixed clang compilation issues	1 year ago

zgemv_t_4_lasx.S	loongarch64: Fixed clang compilation issues	1 year ago

znrm2.S	Allow negative INCX (API change from version 3.10 of the reference implementation)	2 years ago

znrm2_lasx.S	loongarch64: Add c/znrm2 optimization functions.	2 years ago

znrm2_lsx.S	loongarch64: Add c/znrm2 optimization functions.	2 years ago

zscal.S	Delete the macro instruction "li" and use "li.d" instead	4 years ago

ztrsm_kernel_LT.S	Add support for LOONGARCH64	4 years ago

ztrsm_kernel_RT.S	Add support for LOONGARCH64	4 years ago

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

C Fortran Motorola 68K Assembly Makefile Unix Assembly other

martin@ruby.chemie.uni-freiburg.de traits.zhang@gmail.com wernsaar@googlemail.com xianyi@iscas.ac.cn hank.p.anderson@gmail.com 52632443+wjc404@users.noreply.github.com guxiwei-hf@loongson.cn wangyang.guo@intel.com ashwin.sekhar@cavium.com isuruf@gmail.com chip.kerchner@ibm.com rajis@linux.ibm.com binebrank@gmail.com wangqian10@iscas.ac.cn arjan@linux.intel.com mhillen@linux.ibm.com m.tk1@hotmail.com 16061801+brada4@users.noreply.github.com ashwin@broadcom.com chris.sidebottom@arm.com ralf.gommers@gmail.com bradatajs@yahoo.com xianyi@perfxlab.com jeromerobert@gmx.com zaheer.chothia@gmail.com

Contributors (25+) All

Contributors (25+)
All