floraachy/OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
e1afb23811256b231c259ca57d7a5f6e81ac6da5
OpenBLAS/kernel/riscv64
History
kseniyazaytseva e1afb23811 Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets 
* Fixed bugs in dgemm, [a]min\max, asum kernels
* Added zero checks for BLAS kernels
* Added dsdot implementation for RVV 0.7.1
* Fixed bugs in _vector files for C910V and RISCV64_ZVL256B targets
* Added additional definitions for RISCV64_ZVL256B target
2024-01-23 19:01:31 +03:00
..
amax_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
amax_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
amax.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
amin_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
amin_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
amin.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
asum_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
asum_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
asum.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
axpby_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
axpby_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
axpby.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
axpy_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
axpy_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
axpy.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
cgemm_kernel_8x8_zvl256b.c
* update intrinsics to match latest spec at https://github.com/riscv-non-isa/rvv-intrinsic-doc (in particular, __riscv_ prefixes for rvv intrinsics)
2023-02-24 10:45:03 +00:00
copy_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
copy_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
copy.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
ctrmm_kernel_8x8_zvl256b.c
* update intrinsics to match latest spec at https://github.com/riscv-non-isa/rvv-intrinsic-doc (in particular, __riscv_ prefixes for rvv intrinsics)
2023-02-24 10:45:03 +00:00
dgemm_kernel_8x4_c910v.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
dgemm_kernel_8x8_zvl256b.c
* update intrinsics to match latest spec at https://github.com/riscv-non-isa/rvv-intrinsic-doc (in particular, __riscv_ prefixes for rvv intrinsics)
2023-02-24 10:45:03 +00:00
dot_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
dot_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
dot.c
factoring riscv64/dot.c fix into separate PR as requested
2023-03-01 17:40:42 +00:00
dsdot_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
dtrmm_kernel_8x8_zvl256b.c
* update intrinsics to match latest spec at https://github.com/riscv-non-isa/rvv-intrinsic-doc (in particular, __riscv_ prefixes for rvv intrinsics)
2023-02-24 10:45:03 +00:00
gemm_beta_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
gemm_ncopy_8_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
gemm_ncopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
gemm_tcopy_8_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
gemm_tcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
gemmkernel_rvv_v1x8.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
gemv_n_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
gemv_n_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
gemv_n.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
gemv_t_rvv.c
Adds tail undisturbed for RVV Level 2 operations
2023-07-25 11:36:23 +01:00
gemv_t_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
gemv_t.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
generate_kernel.py
[RISC-V] Improve RVV kernel generator LMUL usage
2023-12-04 11:13:35 +00:00
iamax_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
iamax_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
iamax.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
iamin_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
iamin_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
iamin.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
imax_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
imax_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
imax.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
imin_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
imin_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
imin.c
riscv64/imin: Fix wrong comparison
2021-06-07 22:49:39 +00:00
izamax_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
izamax_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
izamax.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
izamin_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
izamin_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
izamin.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
KERNEL
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
KERNEL.C910V
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
KERNEL.RISCV64_GENERIC
RISCV64_GENERIC: Use generic kernel for DSDOT for better precision
2021-06-07 22:50:23 +00:00
KERNEL.RISCV64_ZVL256B
* update intrinsics to match latest spec at https://github.com/riscv-non-isa/rvv-intrinsic-doc (in particular, __riscv_ prefixes for rvv intrinsics)
2023-02-24 10:45:03 +00:00
KERNEL.x280
Add rvv support for zsymv and active rvv support for zhemv
2023-05-20 01:19:44 +08:00
Makefile
riscv64: Add Makefile
2021-06-07 22:55:56 +00:00
max_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
max_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
max.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
min_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
min_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
min.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
nrm2_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
nrm2_vector_dot.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
nrm2_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
nrm2.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
omatcopy_cn.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
omatcopy_ct.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
omatcopy_rn.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
omatcopy_rt.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
rot_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
rot_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
rot.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
scal_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
scal_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
scal.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
sgemm_kernel_16x4_c910v.c
Update RISC-V Intrinsic API.
2022-06-06 13:52:21 +08:00
sgemm_kernel_16x8_zvl256b.c
* update intrinsics to match latest spec at https://github.com/riscv-non-isa/rvv-intrinsic-doc (in particular, __riscv_ prefixes for rvv intrinsics)
2023-02-24 10:45:03 +00:00
strmm_kernel_16x8_zvl256b.c
* update intrinsics to match latest spec at https://github.com/riscv-non-isa/rvv-intrinsic-doc (in particular, __riscv_ prefixes for rvv intrinsics)
2023-02-24 10:45:03 +00:00
sum_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
sum_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
swap_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
swap_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
swap.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
symm_lcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
symm_ucopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
symv_L_rvv.c
Adds tail undisturbed for RVV Level 2 operations
2023-07-25 11:36:23 +01:00
symv_L_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
symv_L.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
symv_U_rvv.c
Adds tail undisturbed for RVV Level 2 operations
2023-07-25 11:36:23 +01:00
symv_U_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
symv_U.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
trmm_lncopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trmm_ltcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trmm_uncopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trmm_utcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trmmkernel_rvv_v1x8.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trsm_kernel_LN_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trsm_kernel_LT_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trsm_kernel_RN_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trsm_kernel_RT_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trsm_lncopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trsm_ltcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trsm_uncopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
trsm_utcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zamax_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
zamax_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
zamax.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zamin_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
zamin_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
zamin.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zasum_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
zasum_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zasum.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zaxpby_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zaxpby_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zaxpby.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zaxpy_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zaxpy_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zaxpy.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zcopy_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zcopy_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zcopy.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zdot_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
zdot_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zdot.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zgemm_beta_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zgemm_kernel_8x4_zvl256b.c
* update intrinsics to match latest spec at https://github.com/riscv-non-isa/rvv-intrinsic-doc (in particular, __riscv_ prefixes for rvv intrinsics)
2023-02-24 10:45:03 +00:00
zgemm_kernel_generic.c
* update intrinsics to match latest spec at https://github.com/riscv-non-isa/rvv-intrinsic-doc (in particular, __riscv_ prefixes for rvv intrinsics)
2023-02-24 10:45:03 +00:00
zgemm_ncopy_4_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zgemm_ncopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zgemm_tcopy_4_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zgemm_tcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zgemmkernel_rvv_v1x4.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zgemv_n_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zgemv_n_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zgemv_n.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zgemv_t_rvv.c
Adds tail undisturbed for RVV Level 2 operations
2023-07-25 11:36:23 +01:00
zgemv_t_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zgemv_t.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zhemm_ltcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zhemm_utcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zhemv_LM_rvv.c
Combine two reduction operations of zhe/symv into one, with tail undisturbed setted.
2023-05-22 22:39:45 +08:00
zhemv_LM_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zhemv_UV_rvv.c
Combine two reduction operations of zhe/symv into one, with tail undisturbed setted.
2023-05-22 22:39:45 +08:00
zhemv_UV_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
znrm2_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
znrm2_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
znrm2.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zomatcopy_cn.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zomatcopy_cnc.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zomatcopy_ct.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zomatcopy_ctc.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zomatcopy_rn.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zomatcopy_rnc.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zomatcopy_rt.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zomatcopy_rtc.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zrot_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zrot_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zrot.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zscal_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zscal_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zscal.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zsum_rvv.c
Adds tail undisturbed for RVV Level 1 operations
2023-07-20 15:28:35 +01:00
zsum_vector.c
fix builds with t-head toolchains that use old versions of the intrinsics spec
2024-01-16 14:33:08 +00:00
zswap_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zswap_vector.c
Fix BLAS and LAPACK tests for C910V and RISCV64_ZVL256B targets
2024-01-23 19:01:31 +03:00
zswap.c
Add the support for RISC-V Vector.
2020-10-15 16:09:02 +08:00
zsymm_lcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zsymm_ucopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
zsymv_L_rvv.c
Combine two reduction operations of zhe/symv into one, with tail undisturbed setted.
2023-05-22 22:39:45 +08:00
zsymv_U_rvv.c
Combine two reduction operations of zhe/symv into one, with tail undisturbed setted.
2023-05-22 22:39:45 +08:00
ztrmm_kernel_8x4_zvl256b.c
* update intrinsics to match latest spec at https://github.com/riscv-non-isa/rvv-intrinsic-doc (in particular, __riscv_ prefixes for rvv intrinsics)
2023-02-24 10:45:03 +00:00
ztrmm_lncopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
ztrmm_ltcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
ztrmm_uncopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
ztrmm_utcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
ztrmmkernel_2x2_rvv.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
ztrmmkernel_rvv_v1x4.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
ztrsm_lncopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
ztrsm_ltcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
ztrsm_uncopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00
ztrsm_utcopy_rvv_v1.c
This PR adapts latest spec changes
2023-03-19 23:59:03 -07:00