OSchip
/
OpenBLAS
Not watched
1
0
Fork 0
Code
Releases 66 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
3620 Commits
51 Branches
78 MB
250 Download
 
 
 
 
 
 
Tree: 100d94f94e
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '100d94f94e'
${ noResults }
OpenBLAS/kernel/power
Martin Kroeker 706dfe263b
Add POWER implementation of ?sum 		6 years ago
..
KERNEL modified KERNEL for power, to use the generic DSDOT-KERNEL 10 years ago
KERNEL.CELL Remove all trailing whitespace except lapack-netlib 11 years ago
KERNEL.POWER3 Import GotoBLAS2 1.13 BSD version codes. 15 years ago
KERNEL.POWER4 Import GotoBLAS2 1.13 BSD version codes. 15 years ago
KERNEL.POWER5 Remove all trailing whitespace except lapack-netlib 11 years ago
KERNEL.POWER6 Use generic zrot.c on ppc64/POWER6 to work around utest failure from … (#1535) 7 years ago
KERNEL.POWER8 sgemv cgemv pairs 7 years ago
KERNEL.POWER9 power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
KERNEL.PPC440 Remove all trailing whitespace except lapack-netlib 11 years ago
KERNEL.PPC440FP2 Import GotoBLAS2 1.13 BSD version codes. 15 years ago
KERNEL.PPC970 Remove all trailing whitespace except lapack-netlib 11 years ago
KERNEL.PPCG4 Remove all trailing whitespace except lapack-netlib 11 years ago
Makefile Import GotoBLAS2 1.13 BSD version codes. 15 years ago
amax.S Remove all trailing whitespace except lapack-netlib 11 years ago
amax_cell.S Remove all trailing whitespace except lapack-netlib 11 years ago
amax_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
amax_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
amin.S Remove all trailing whitespace except lapack-netlib 11 years ago
amin_cell.S Remove all trailing whitespace except lapack-netlib 11 years ago
amin_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
amin_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
asum.S Remove all trailing whitespace except lapack-netlib 11 years ago
asum_cell.S Remove all trailing whitespace except lapack-netlib 11 years ago
asum_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
asum_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
axpy.S ppc64le platform support (ELF ABI v2) 10 years ago
axpy_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
axpy_ppc440.S ppc64le platform support (ELF ABI v2) 10 years ago
cabs.S Import GotoBLAS2 1.13 BSD version codes. 15 years ago
casum.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
casum_microk_power8.c Optimise casum for POWER9 8 years ago
caxpy.c Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin}, 7 years ago
ccopy.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
ccopy_microk_power8.c Optimise ccopy for POWER9 8 years ago
cdot.c Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin}, 7 years ago
cgemm_kernel_8x4_power8.S Save and restore VSX registers 8 years ago
cgemm_logic_8x4_power8.S updated optimized cgemm- and ctrmm-kernel for POWER8 9 years ago
cgemm_macros_8x4_power8.S updated optimized cgemm- and ctrmm-kernel for POWER8 9 years ago
cgemm_tcopy_8_power8.S power8 ?gemm_tcopy save/restore 8 years ago
cgemm_tcopy_logic_8_power8.S added cgemm_tcopy_8_power8.S 9 years ago
cgemm_tcopy_macros_8_power8.S added cgemm_tcopy_8_power8.S 9 years ago
cgemv_n.c sgemv cgemv pairs 7 years ago
cgemv_t.c sgemv cgemv pairs 7 years ago
cnrm2.S Remove all trailing whitespace except lapack-netlib 11 years ago
cnrm2_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
cnrm2_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
copy.S Remove all trailing whitespace except lapack-netlib 11 years ago
copy_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
crot.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
cswap.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
cswap_microk_power8.c Optimise cswap for POWER9 8 years ago
ctrmm_kernel_8x4_power8.S Save and restore VSX registers 8 years ago
ctrmm_logic_8x4_power8.S updated optimized cgemm- and ctrmm-kernel for POWER8 9 years ago
ctrmm_macros_8x4_power8.S updated optimized cgemm- and ctrmm-kernel for POWER8 9 years ago
dasum.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
dasum_microk_power8.c Power8 inline assembly fixes 9 years ago
daxpy.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
daxpy_microk_power8.c Power8 inline assembly fixes 9 years ago
dcopy.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
dcopy_microk_power8.c Power8 inline assembly fixes 9 years ago
ddot.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
ddot_microk_power8.c Power8 inline assembly fixes 9 years ago
def_vsx.h added dgemm-, dtrmm-, zgemm- and ztrmm-kernel for power8 10 years ago
dgemm_kernel_16x4_power8.S Save and restore VSX registers 8 years ago
dgemm_kernel_power9.S power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
dgemm_logic_16x4_power8.S optimized dgemm and dgetrf for POWER8 9 years ago
dgemm_logic_power9.S power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
dgemm_macros_16x4_power8.S optimized dgemm for 20 threads 9 years ago
dgemm_macros_power9.S power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
dgemm_ncopy_4_power8.S dgemm_ncopy_4_ save/restore 8 years ago
dgemm_ncopy_logic_4_power8.S optimized dgemm for POWER8 9 years ago
dgemm_ncopy_macros_4_power8.S dgemm_ncopy_4_ save/restore 8 years ago
dgemm_tcopy_16_power8.S power8 ?gemm_tcopy save/restore 8 years ago
dgemm_tcopy_logic_16_power8.S optimized dgemm and dgetrf for POWER8 9 years ago
dgemm_tcopy_macros_16_power8.S power8 ?gemm_tcopy save/restore 8 years ago
dgemv_n.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
dgemv_n_microk_power8.c Power8 inline assembly tweaks 8 years ago
dgemv_t.c sgemv cgemv pairs 7 years ago
dnrm2_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
dnrm2_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
dot.S Remove all trailing whitespace except lapack-netlib 11 years ago
dot_cell.S Remove all trailing whitespace except lapack-netlib 11 years ago
dot_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
dot_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
drot.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
drot_microk_power8.c Power8 inline assembly fixes 9 years ago
dscal.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
dscal_microk_power8.c Power8 inline assembly fixes 9 years ago
dswap.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
dswap_microk_power8.c Power8 inline assembly fixes 9 years ago
dtrmm_kernel_16x4_power8.S Save and restore VSX registers 8 years ago
dtrmm_logic_16x4_power8.S Modified assembly label name, so that they are hidden. 10 years ago
dtrmm_macros_16x4_power8.S optimized dgemm for POWER8 9 years ago
dtrsm_kernel_LT_16x4_power8.S Save and restore VSX registers 8 years ago
dtrsm_logic_LT_16x4_power8.S optimized dtrsm_logic_LT_16x4_power8.S and dtrsm_macros_LT_16x4_power8.S 9 years ago
dtrsm_macros_LT_16x4_power8.S optimized dtrsm_logic_LT_16x4_power8.S and dtrsm_macros_LT_16x4_power8.S 9 years ago
exfunc.S Remove all trailing whitespace except lapack-netlib 11 years ago
gemm_beta.S Fix out-of-bounds memory access in gemm_beta 7 years ago
gemm_kernel.S ppc64le platform support (ELF ABI v2) 10 years ago
gemm_kernel_altivec.S ppc64le platform support (ELF ABI v2) 10 years ago
gemm_kernel_altivec_cell.S ppc64le platform support (ELF ABI v2) 10 years ago
gemm_kernel_altivec_g4.S ppc64le platform support (ELF ABI v2) 10 years ago
gemm_kernel_cell.S ppc64le platform support (ELF ABI v2) 10 years ago
gemm_kernel_g4.S ppc64le platform support (ELF ABI v2) 10 years ago
gemm_kernel_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
gemm_kernel_power3.S ppc64le platform support (ELF ABI v2) 10 years ago
gemm_kernel_power6.S ppc64le platform support (ELF ABI v2) 10 years ago
gemm_kernel_ppc440.S ppc64le platform support (ELF ABI v2) 10 years ago
gemm_ncopy_4.S added dgemm-, dtrmm-, zgemm- and ztrmm-kernel for power8 10 years ago
gemm_ncopy_hummer_4.S Remove all trailing whitespace except lapack-netlib 11 years ago
gemm_ncopy_hummer_8.S Remove all trailing whitespace except lapack-netlib 11 years ago
gemm_tcopy_4.S added dgemm-, dtrmm-, zgemm- and ztrmm-kernel for power8 10 years ago
gemm_tcopy_hummer_4.S Remove all trailing whitespace except lapack-netlib 11 years ago
gemm_tcopy_hummer_8.S Remove all trailing whitespace except lapack-netlib 11 years ago
gemv_hummer_n.S Remove all trailing whitespace except lapack-netlib 11 years ago
gemv_n.S enabled gemv assembly on power8 10 years ago
gemv_n_ppc440.S ppc64le platform support (ELF ABI v2) 10 years ago
gemv_t.S enabled gemv assembly on power8 10 years ago
gemv_t_ppc440.S ppc64le platform support (ELF ABI v2) 10 years ago
ger.S ppc64le platform support (ELF ABI v2) 10 years ago
iamax.S Remove all trailing whitespace except lapack-netlib 11 years ago
iamax_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
iamax_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
iamin.S Remove all trailing whitespace except lapack-netlib 11 years ago
iamin_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
iamin_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
icamax.c sgemv cgemv pairs 7 years ago
icamin.c Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin}, 7 years ago
idamax.c power8:Added initial zgemv_(t|n) ,i(d|z)amax,i(d|z)amin,dgemv_t(transposed),zrot 7 years ago
idamin.c Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin}, 7 years ago
imax.S Remove all trailing whitespace except lapack-netlib 11 years ago
imax_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
imax_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
imin.S Remove all trailing whitespace except lapack-netlib 11 years ago
imin_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
imin_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
isamax.c Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin}, 7 years ago
isamin.c Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin}, 7 years ago
izamax.S Remove all trailing whitespace except lapack-netlib 11 years ago
izamax.c power8:Added initial zgemv_(t|n) ,i(d|z)amax,i(d|z)amin,dgemv_t(transposed),zrot 7 years ago
izamax_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
izamax_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
izamin.S Remove all trailing whitespace except lapack-netlib 11 years ago
izamin.c Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin}, 7 years ago
izamin_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
izamin_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
lock.c Import GotoBLAS2 1.13 BSD version codes. 15 years ago
lsame.S Import GotoBLAS2 1.13 BSD version codes. 15 years ago
max.S Remove all trailing whitespace except lapack-netlib 11 years ago
max_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
max_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
min.S Remove all trailing whitespace except lapack-netlib 11 years ago
min_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
min_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
nrm2.S Remove all trailing whitespace except lapack-netlib 11 years ago
rot.S Remove all trailing whitespace except lapack-netlib 11 years ago
rot_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
sasum.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
sasum_microk_power8.c Optimise sasum for POWER9 8 years ago
saxpy.c Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin}, 7 years ago
scal.S Remove all trailing whitespace except lapack-netlib 11 years ago
scal_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
scal_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
scopy.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
scopy_microk_power8.c Optimise scopy for POWER9 8 years ago
sdot.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
sdot_microk_power8.c Optimise sdot for POWER9 8 years ago
sgemm_kernel_16x8_power8.S Save and restore VSX registers 8 years ago
sgemm_logic_16x8_power8.S Optimized sgemm and dgemm and tested again. 9 years ago
sgemm_macros_16x8_power8.S Optimized sgemm and dgemm and tested again. 9 years ago
sgemm_tcopy_8_power8.S power8 ?gemm_tcopy save/restore 8 years ago
sgemm_tcopy_16_power8.S power8 ?gemm_tcopy save/restore 8 years ago
sgemm_tcopy_logic_8_power8.S added sgemm_tcopy_8_power8.S 9 years ago
sgemm_tcopy_logic_16_power8.S Optimized sgemm and dgemm and tested again. 9 years ago
sgemm_tcopy_macros_8_power8.S added sgemm_tcopy_8_power8.S 9 years ago
sgemm_tcopy_macros_16_power8.S Optimized sgemm and dgemm and tested again. 9 years ago
sgemv_n.c NBMAX=4096 for gemvn, added sgemvn 8x8 for future 7 years ago
sgemv_n_8.c Note for unused kernels 7 years ago
sgemv_t.c sgemv cgemv pairs 7 years ago
sgemv_t_8.c Note for unused kernels 7 years ago
snrm2.S Remove all trailing whitespace except lapack-netlib 11 years ago
snrm2_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
snrm2_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
srot.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
srot_microk_power8.c Optimise srot for POWER9 8 years ago
sscal.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
sscal_microk_power8.c Optimise sscal for POWER9 8 years ago
sswap.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
sswap_microk_power8.c Optimise sswap for POWER9 8 years ago
staticbuffer.S Import GotoBLAS2 1.13 BSD version codes. 15 years ago
strmm_kernel_16x8_power8.S Save and restore VSX registers 8 years ago
strmm_logic_16x8_power8.S updated sgemm- and strmm-kernel for POWER8 9 years ago
strmm_macros_16x8_power8.S updated sgemm- and strmm-kernel for POWER8 9 years ago
sum.S Add POWER implementation of ?sum 6 years ago
swap.S ppc64le platform support (ELF ABI v2) 10 years ago
swap_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
symv_L.S ppc64le platform support (ELF ABI v2) 10 years ago
symv_U.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_LN.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_LT.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_RT.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_cell_LN.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_cell_LT.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_cell_RT.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_hummer_LN.S Remove all trailing whitespace except lapack-netlib 11 years ago
trsm_kernel_hummer_LT.S Remove all trailing whitespace except lapack-netlib 11 years ago
trsm_kernel_hummer_RT.S Remove all trailing whitespace except lapack-netlib 11 years ago
trsm_kernel_power6_LN.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_power6_LT.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_power6_RT.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_ppc440_LN.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_ppc440_LT.S ppc64le platform support (ELF ABI v2) 10 years ago
trsm_kernel_ppc440_RT.S ppc64le platform support (ELF ABI v2) 10 years ago
zamax.S Remove all trailing whitespace except lapack-netlib 11 years ago
zamax_cell.S Remove all trailing whitespace except lapack-netlib 11 years ago
zamax_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
zamax_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
zamin.S Remove all trailing whitespace except lapack-netlib 11 years ago
zamin_cell.S Remove all trailing whitespace except lapack-netlib 11 years ago
zamin_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
zamin_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
zasum.S Remove all trailing whitespace except lapack-netlib 11 years ago
zasum.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
zasum_cell.S Remove all trailing whitespace except lapack-netlib 11 years ago
zasum_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
zasum_microk_power8.c Power8 inline assembly fixes 9 years ago
zasum_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
zaxpy.S ppc64le platform support (ELF ABI v2) 10 years ago
zaxpy.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
zaxpy_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
zaxpy_microk_power8.c Power8 inline assembly fixes 9 years ago
zaxpy_ppc440.S ppc64le platform support (ELF ABI v2) 10 years ago
zcopy.S Remove all trailing whitespace except lapack-netlib 11 years ago
zcopy.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
zcopy_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
zcopy_microk_power8.c Power8 inline assembly fixes 9 years ago
zdot.S Remove all trailing whitespace except lapack-netlib 11 years ago
zdot.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
zdot_cell.S Remove all trailing whitespace except lapack-netlib 11 years ago
zdot_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
zdot_microk_power8.c Power8 inline assembly fixes 9 years ago
zdot_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
zgemm_beta.S Fix out-of-bounds memory access in gemm_beta 7 years ago
zgemm_kernel.S ppc64le platform support (ELF ABI v2) 10 years ago
zgemm_kernel_8x2_power8.S Save and restore VSX registers 8 years ago
zgemm_kernel_altivec.S ppc64le platform support (ELF ABI v2) 10 years ago
zgemm_kernel_altivec_cell.S ppc64le platform support (ELF ABI v2) 10 years ago
zgemm_kernel_altivec_g4.S ppc64le platform support (ELF ABI v2) 10 years ago
zgemm_kernel_cell.S ppc64le platform support (ELF ABI v2) 10 years ago
zgemm_kernel_g4.S ppc64le platform support (ELF ABI v2) 10 years ago
zgemm_kernel_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
zgemm_kernel_power3.S ppc64le platform support (ELF ABI v2) 10 years ago
zgemm_kernel_power6.S ppc64le platform support (ELF ABI v2) 10 years ago
zgemm_kernel_ppc440.S ppc64le platform support (ELF ABI v2) 10 years ago
zgemm_logic_8x2_power8.S Optimized zgemm and tested zgemm again 9 years ago
zgemm_macros_8x2_power8.S Optimized zgemm and tested zgemm again 9 years ago
zgemm_ncopy_hummer_2.S Remove all trailing whitespace except lapack-netlib 11 years ago
zgemm_ncopy_hummer_4.S Remove all trailing whitespace except lapack-netlib 11 years ago
zgemm_tcopy_8_power8.S power8 ?gemm_tcopy save/restore 8 years ago
zgemm_tcopy_hummer_2.S Remove all trailing whitespace except lapack-netlib 11 years ago
zgemm_tcopy_hummer_4.S Remove all trailing whitespace except lapack-netlib 11 years ago
zgemm_tcopy_logic_8_power8.S Optimized zgemm and tested zgemm again 9 years ago
zgemm_tcopy_macros_8_power8.S power8 ?gemm_tcopy save/restore 8 years ago
zgemv_n.S enabled gemv assembly on power8 10 years ago
zgemv_n_4.c sgemv cgemv pairs 7 years ago
zgemv_n_ppc440.S ppc64le platform support (ELF ABI v2) 10 years ago
zgemv_t.S enabled gemv assembly on power8 10 years ago
zgemv_t_4.c sgemv cgemv pairs 7 years ago
zgemv_t_ppc440.S ppc64le platform support (ELF ABI v2) 10 years ago
zger.S ppc64le platform support (ELF ABI v2) 10 years ago
znrm2.S Remove all trailing whitespace except lapack-netlib 11 years ago
znrm2_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
znrm2_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
zrot.S Remove all trailing whitespace except lapack-netlib 11 years ago
zrot.c power8:Added initial zgemv_(t|n) ,i(d|z)amax,i(d|z)amin,dgemv_t(transposed),zrot 7 years ago
zrot_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
zscal.S Remove all trailing whitespace except lapack-netlib 11 years ago
zscal.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
zscal_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
zscal_microk_power8.c Power8 inline assembly fixes 9 years ago
zscal_ppc440.S Remove all trailing whitespace except lapack-netlib 11 years ago
zsum.S Add POWER implementation of ?sum 6 years ago
zswap.S ppc64le platform support (ELF ABI v2) 10 years ago
zswap.c power9 makefile. dgemm based on power8 kernel with following changes : 32x unrolled 16x4 kernel and 8x4 kernel using (lxv stxv butterfly rank1 update). improvement from 17 to 22-23gflops. dtrmm cases were added into dgemm itself 6 years ago
zswap_hummer.S Remove all trailing whitespace except lapack-netlib 11 years ago
zswap_microk_power8.c Power8 inline assembly fixes 9 years ago
zsymv_L.S ppc64le platform support (ELF ABI v2) 10 years ago
zsymv_U.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrmm_kernel_8x2_power8.S Save and restore VSX registers 8 years ago
ztrmm_logic_8x2_power8.S Modified assembly label name, so that they are hidden. 10 years ago
ztrmm_macros_8x2_power8.S updated zgemm- and ztrmm-kernel for POWER8 9 years ago
ztrsm_kernel_LN.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_LT.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_RT.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_cell_LN.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_cell_LT.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_cell_RT.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_hummer_LN.S Remove all trailing whitespace except lapack-netlib 11 years ago
ztrsm_kernel_hummer_LT.S Remove all trailing whitespace except lapack-netlib 11 years ago
ztrsm_kernel_hummer_RT.S Remove all trailing whitespace except lapack-netlib 11 years ago
ztrsm_kernel_power6_LN.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_power6_LT.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_power6_RT.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_ppc440_LN.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_ppc440_LT.S ppc64le platform support (ELF ABI v2) 10 years ago
ztrsm_kernel_ppc440_RT.S ppc64le platform support (ELF ABI v2) 10 years ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

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

C Fortran Motorola 68K Assembly Makefile Unix Assembly other