..
KERNEL
modified KERNEL for power, to use the generic DSDOT-KERNEL
2016-03-06 09:07:24 +01:00
KERNEL.CELL
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
KERNEL.POWER3
Import GotoBLAS2 1.13 BSD version codes.
2011-01-24 14:54:24 +00:00
KERNEL.POWER4
Import GotoBLAS2 1.13 BSD version codes.
2011-01-24 14:54:24 +00:00
KERNEL.POWER5
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
KERNEL.POWER6
Use generic zrot.c on ppc64/POWER6 to work around utest failure from … ( #1535 )
2018-04-23 19:05:49 +02:00
KERNEL.POWER8
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
KERNEL.POWER9
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
KERNEL.PPC440
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
KERNEL.PPC440FP2
Import GotoBLAS2 1.13 BSD version codes.
2011-01-24 14:54:24 +00:00
KERNEL.PPC970
Define alternate kernels for big-endian PPC970
2019-11-17 15:19:39 +01:00
KERNEL.PPCG4
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
Makefile
Import GotoBLAS2 1.13 BSD version codes.
2011-01-24 14:54:24 +00:00
amax.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
amax_cell.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
amax_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
amax_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
amin.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
amin_cell.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
amin_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
amin_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
asum.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
asum_cell.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
asum_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
asum_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
axpy.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
axpy_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
axpy_ppc440.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
cabs.S
Import GotoBLAS2 1.13 BSD version codes.
2011-01-24 14:54:24 +00:00
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
2019-03-29 15:49:40 +00:00
casum_microk_power8.c
Optimise casum for POWER9
2017-06-14 17:00:07 +10:00
caxpy.c
caxpy and cdot are using vec_vsx_ld
2019-08-30 04:09:15 +00:00
caxpy_power8.S
Fix mis-edits in the gcc-derived power8 caxpy kernel
2019-09-27 00:44:26 +02:00
caxpy_power9.S
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
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
2019-03-29 15:49:40 +00:00
ccopy_microk_power8.c
Optimise ccopy for POWER9
2017-06-14 16:58:59 +10:00
cdot.c
caxpy and cdot are using vec_vsx_ld
2019-08-30 04:09:15 +00:00
cdot_power9.S
Fix prologue of power9 assembly cdot(c) kernel to provide cdotc
2019-09-27 00:47:18 +02:00
cgemm_kernel_8x4_power8.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
cgemm_kernel_power9.S
cgemm/ctrmm power9
2019-07-01 14:07:54 +00:00
cgemm_logic_8x4_power8.S
updated optimized cgemm- and ctrmm-kernel for POWER8
2016-04-04 09:12:08 +02:00
cgemm_logic_power9.S
cgemm/ctrmm power9
2019-07-01 14:07:54 +00:00
cgemm_macros_8x4_power8.S
updated optimized cgemm- and ctrmm-kernel for POWER8
2016-04-04 09:12:08 +02:00
cgemm_macros_power9.S
cgemm/ctrmm power9
2019-07-01 14:07:54 +00:00
cgemm_tcopy_8_power8.S
power8 ?gemm_tcopy save/restore
2018-02-16 23:36:46 +00:00
cgemm_tcopy_logic_8_power8.S
added cgemm_tcopy_8_power8.S
2016-04-23 07:37:18 +02:00
cgemm_tcopy_macros_8_power8.S
added cgemm_tcopy_8_power8.S
2016-04-23 07:37:18 +02:00
cgemv_n.c
fix uninitialized variables i
2019-08-30 11:14:55 +00:00
cgemv_t.c
fix uninitialized variables i
2019-08-30 11:14:55 +00:00
cnrm2.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
cnrm2_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
cnrm2_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
copy.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
copy_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
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
2019-03-29 15:49:40 +00:00
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
2019-03-29 15:49:40 +00:00
cswap_microk_power8.c
Optimise cswap for POWER9
2017-06-14 16:59:53 +10:00
ctrmm_kernel_8x4_power8.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ctrmm_logic_8x4_power8.S
updated optimized cgemm- and ctrmm-kernel for POWER8
2016-04-04 09:12:08 +02:00
ctrmm_macros_8x4_power8.S
updated optimized cgemm- and ctrmm-kernel for POWER8
2016-04-04 09:12:08 +02:00
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
2019-03-29 15:49:40 +00:00
dasum_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
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
2019-03-29 15:49:40 +00:00
daxpy_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
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
2019-03-29 15:49:40 +00:00
dcopy_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
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
2019-03-29 15:49:40 +00:00
ddot_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
def_vsx.h
added dgemm-, dtrmm-, zgemm- and ztrmm-kernel for power8
2016-03-01 07:33:56 +01:00
dgemm_kernel_16x4_power8.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
dgemm_kernel_power9.S
sgemm pipeline improved, zgemm rewritten without inner packs, ABI lxvx v20 fixed with vs52
2019-06-04 07:11:30 +00:00
dgemm_logic_16x4_power8.S
optimized dgemm and dgetrf for POWER8
2016-05-17 14:45:27 +02:00
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
2019-03-29 15:49:40 +00:00
dgemm_macros_16x4_power8.S
optimized dgemm for 20 threads
2016-05-16 14:14:25 +02:00
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
2019-03-29 15:49:40 +00:00
dgemm_ncopy_4_power8.S
dgemm_ncopy_4_ save/restore
2018-02-18 01:30:17 +00:00
dgemm_ncopy_logic_4_power8.S
optimized dgemm for POWER8
2016-04-29 12:52:47 +02:00
dgemm_ncopy_macros_4_power8.S
dgemm_ncopy_4_ save/restore
2018-02-18 01:30:17 +00:00
dgemm_tcopy_16_power8.S
power8 ?gemm_tcopy save/restore
2018-02-16 23:36:46 +00:00
dgemm_tcopy_logic_16_power8.S
optimized dgemm and dgetrf for POWER8
2016-05-17 14:45:27 +02:00
dgemm_tcopy_macros_16_power8.S
power8 ?gemm_tcopy save/restore
2018-02-16 23:36:46 +00:00
dgemv_n.c
aligned
2019-08-29 23:22:23 +00:00
dgemv_n_microk_power8.c
Power8 inline assembly tweaks
2017-04-04 23:13:54 +09:30
dgemv_t.c
aligned
2019-08-29 23:22:23 +00:00
dnrm2_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
dnrm2_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
dot.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
dot_cell.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
dot_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
dot_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
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
2019-03-29 15:49:40 +00:00
drot_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
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
2019-03-29 15:49:40 +00:00
dscal_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
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
2019-03-29 15:49:40 +00:00
dswap_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
dtrmm_kernel_16x4_power8.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
dtrmm_logic_16x4_power8.S
Modified assembly label name, so that they are hidden.
2016-03-05 10:27:27 +01:00
dtrmm_macros_16x4_power8.S
optimized dgemm for POWER8
2016-04-27 14:01:08 +02:00
dtrsm_kernel_LT_16x4_power8.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
dtrsm_logic_LT_16x4_power8.S
optimized dtrsm_logic_LT_16x4_power8.S and dtrsm_macros_LT_16x4_power8.S
2016-05-23 11:20:41 +02:00
dtrsm_macros_LT_16x4_power8.S
optimized dtrsm_logic_LT_16x4_power8.S and dtrsm_macros_LT_16x4_power8.S
2016-05-23 11:20:41 +02:00
exfunc.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
gemm_beta.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_kernel.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_kernel_altivec.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_kernel_altivec_cell.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_kernel_altivec_g4.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_kernel_cell.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_kernel_g4.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_kernel_hummer.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_kernel_power3.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_kernel_power6.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_kernel_ppc440.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemm_ncopy_4.S
added dgemm-, dtrmm-, zgemm- and ztrmm-kernel for power8
2016-03-01 07:33:56 +01:00
gemm_ncopy_hummer_4.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
gemm_ncopy_hummer_8.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
gemm_tcopy_4.S
added dgemm-, dtrmm-, zgemm- and ztrmm-kernel for power8
2016-03-01 07:33:56 +01:00
gemm_tcopy_hummer_4.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
gemm_tcopy_hummer_8.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
gemv_hummer_n.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
gemv_n.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemv_n_ppc440.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemv_t.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
gemv_t_ppc440.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ger.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
iamax.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
iamax_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
iamax_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
iamin.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
iamin_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
iamin_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
icamax.c
conflict resolve
2019-05-01 19:36:22 +00:00
icamax_power8.S
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
icamax_power9.S
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
icamin.c
conflict resolve
2019-05-01 19:36:22 +00:00
icamin_power8.S
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
icamin_power9.S
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
idamax.c
The assembly microkernel is not safe to use on ELFv1
2019-11-03 22:37:27 +01:00
idamin.c
The assembly microkernel is not safe to use on ELFv1
2019-11-03 22:39:06 +01:00
imax.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
imax_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
imax_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
imin.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
imin_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
imin_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
isamax.c
Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin},
2019-01-16 15:16:21 +00:00
isamax_power8.S
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
isamax_power9.S
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
isamin.c
Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin},
2019-01-16 15:16:21 +00:00
isamin_power8.S
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
isamin_power9.S
Replace several POWER8/9 C kernels with their gcc7-generated assembly versions ( #2263 )
2019-09-22 22:35:22 +02:00
izamax.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
izamax.c
The assembly microkernel is not safe to use on ELFv1
2019-11-03 22:42:46 +01:00
izamax_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
izamax_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
izamin.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
izamin.c
The assembly microkernel is not safe to use on ELFv1
2019-11-03 22:41:19 +01:00
izamin_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
izamin_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
lock.c
Import GotoBLAS2 1.13 BSD version codes.
2011-01-24 14:54:24 +00:00
lsame.S
Import GotoBLAS2 1.13 BSD version codes.
2011-01-24 14:54:24 +00:00
max.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
max_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
max_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
min.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
min_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
min_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
nrm2.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
rot.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
rot_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
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
2019-03-29 15:49:40 +00:00
sasum_microk_power8.c
Optimise sasum for POWER9
2017-06-14 17:02:10 +10:00
saxpy.c
Added missing Blas1 single fp {saxpy, caxpy, cdot, crot(refactored version of srot),isamax ,isamin, icamax, icamin},
2019-01-16 15:16:21 +00:00
scal.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
scal_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
scal_ppc440.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
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
2019-03-29 15:49:40 +00:00
scopy_microk_power8.c
Optimise scopy for POWER9
2017-06-14 16:59:13 +10:00
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
2019-03-29 15:49:40 +00:00
sdot_microk_power8.c
Optimise sdot for POWER9
2017-06-14 17:02:19 +10:00
sgemm_kernel_16x8_power8.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
sgemm_kernel_power9.S
sgemm pipeline improved, zgemm rewritten without inner packs, ABI lxvx v20 fixed with vs52
2019-06-04 07:11:30 +00:00
sgemm_logic_16x8_power8.S
Optimized sgemm and dgemm and tested again.
2016-04-21 11:37:57 +02:00
sgemm_logic_power9.S
trmm fix
2019-09-29 02:28:34 +00:00
sgemm_macros_16x8_power8.S
Optimized sgemm and dgemm and tested again.
2016-04-21 11:37:57 +02:00
sgemm_macros_power9.S
new sgemm 8x16
2019-06-17 15:33:38 +00:00
sgemm_tcopy_8_power8.S
power8 ?gemm_tcopy save/restore
2018-02-16 23:36:46 +00:00
sgemm_tcopy_16_power8.S
power8 ?gemm_tcopy save/restore
2018-02-16 23:36:46 +00:00
sgemm_tcopy_logic_8_power8.S
added sgemm_tcopy_8_power8.S
2016-04-23 10:04:41 +02:00
sgemm_tcopy_logic_16_power8.S
Optimized sgemm and dgemm and tested again.
2016-04-21 11:37:57 +02:00
sgemm_tcopy_macros_8_power8.S
added sgemm_tcopy_8_power8.S
2016-04-23 10:04:41 +02:00
sgemm_tcopy_macros_16_power8.S
Optimized sgemm and dgemm and tested again.
2016-04-21 11:37:57 +02:00
sgemv_n.c
aligned
2019-08-29 23:22:23 +00:00
sgemv_n_8.c
aligned
2019-08-29 23:22:23 +00:00
sgemv_t.c
aligned
2019-08-29 23:22:23 +00:00
sgemv_t_8.c
aligned
2019-08-29 23:22:23 +00:00
snrm2.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
snrm2_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
snrm2_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
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
2019-03-29 15:49:40 +00:00
srot_microk_power8.c
Optimise srot for POWER9
2017-06-14 17:02:35 +10:00
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
2019-03-29 15:49:40 +00:00
sscal_microk_power8.c
Optimise sscal for POWER9
2017-06-14 17:02:46 +10:00
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
2019-03-29 15:49:40 +00:00
sswap_microk_power8.c
Optimise sswap for POWER9
2017-06-14 16:59:13 +10:00
staticbuffer.S
Import GotoBLAS2 1.13 BSD version codes.
2011-01-24 14:54:24 +00:00
strmm_kernel_16x8_power8.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
strmm_logic_16x8_power8.S
updated sgemm- and strmm-kernel for POWER8
2016-04-02 17:16:36 +02:00
strmm_macros_16x8_power8.S
updated sgemm- and strmm-kernel for POWER8
2016-04-02 17:16:36 +02:00
sum.S
Add POWER implementation of ?sum
2019-03-30 22:23:42 +01:00
swap.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
swap_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
symv_L.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
symv_U.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_LN.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_LT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_RT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_cell_LN.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_cell_LT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_cell_RT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_hummer_LN.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_hummer_LT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_hummer_RT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_power6_LN.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_power6_LT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_power6_RT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_ppc440_LN.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_ppc440_LT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
trsm_kernel_ppc440_RT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zamax.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zamax_cell.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zamax_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zamax_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zamin.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zamin_cell.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zamin_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zamin_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zasum.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
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
2019-03-29 15:49:40 +00:00
zasum_cell.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zasum_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zasum_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
zasum_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zaxpy.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
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
2019-03-29 15:49:40 +00:00
zaxpy_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zaxpy_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
zaxpy_ppc440.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zcopy.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
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
2019-03-29 15:49:40 +00:00
zcopy_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zcopy_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
zdot.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
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
2019-03-29 15:49:40 +00:00
zdot_cell.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zdot_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zdot_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
zdot_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zgemm_beta.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_8x2_power8.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_altivec.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_altivec_cell.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_altivec_g4.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_cell.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_g4.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_hummer.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_power3.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_power6.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_power9.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_kernel_ppc440.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemm_logic_8x2_power8.S
Optimized zgemm and tested zgemm again
2016-04-22 13:07:12 +02:00
zgemm_logic_power9.S
cgemm/ctrmm power9
2019-07-01 14:07:54 +00:00
zgemm_macros_8x2_power8.S
Optimized zgemm and tested zgemm again
2016-04-22 13:07:12 +02:00
zgemm_macros_power9.S
power9 zgemm ztrmm optimized
2019-06-05 20:07:16 +00:00
zgemm_ncopy_hummer_2.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zgemm_ncopy_hummer_4.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zgemm_tcopy_8_power8.S
power8 ?gemm_tcopy save/restore
2018-02-16 23:36:46 +00:00
zgemm_tcopy_hummer_2.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zgemm_tcopy_hummer_4.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zgemm_tcopy_logic_8_power8.S
Optimized zgemm and tested zgemm again
2016-04-22 13:07:12 +02:00
zgemm_tcopy_macros_8_power8.S
power8 ?gemm_tcopy save/restore
2018-02-16 23:36:46 +00:00
zgemv_n.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemv_n_4.c
aligned
2019-08-29 23:22:23 +00:00
zgemv_n_ppc440.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemv_t.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zgemv_t_4.c
aligned
2019-08-29 23:22:23 +00:00
zgemv_t_ppc440.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zger.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
znrm2.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
znrm2_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
znrm2_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zrot.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zrot.c
power8:Added initial zgemv_(t|n) ,i(d|z)amax,i(d|z)amin,dgemv_t(transposed),zrot
2018-03-27 14:54:41 +00:00
zrot_ppc440.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zscal.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
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
2019-03-29 15:49:40 +00:00
zscal_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zscal_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
zscal_ppc440.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zsum.S
Add POWER implementation of ?sum
2019-03-30 22:23:42 +01:00
zswap.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
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
2019-03-29 15:49:40 +00:00
zswap_hummer.S
Remove all trailing whitespace except lapack-netlib
2014-06-27 12:05:18 -07:00
zswap_microk_power8.c
Power8 inline assembly fixes
2017-02-13 23:38:50 +01:00
zsymv_L.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
zsymv_U.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrmm_kernel_8x2_power8.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrmm_logic_8x2_power8.S
Modified assembly label name, so that they are hidden.
2016-03-05 10:27:27 +01:00
ztrmm_macros_8x2_power8.S
updated zgemm- and ztrmm-kernel for POWER8
2016-04-08 09:05:37 +02:00
ztrsm_kernel_LN.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_LT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_RT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_cell_LN.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_cell_LT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_cell_RT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_hummer_LN.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_hummer_LT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_hummer_RT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_power6_LN.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_power6_LT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_power6_RT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_ppc440_LN.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_ppc440_LT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00
ztrsm_kernel_ppc440_RT.S
Fix build on FreeBSD/powerpc64.
2019-06-25 10:58:56 +02:00