Martin Kroeker
d96daa220d
Merge pull request #5290 from Srangrang/develop
...
Add support for FP16 to openBLAS and shgemm on RISCV
2025-06-24 23:10:15 +02:00
Srangrang
ec14e1648c
fix: resolve non-RISCV host build failed issue
...
- adjust interface to disable "small matrix" pathway
- separate HFLOAT16 from BFLOAT16
- remove SHGEMM_UNROLL_M and SHGEMM_UNROLL_N equal conditions
Related to PR#5290
Co-authored-by Martin
2025-06-15 20:25:15 +08:00
Martin Kroeker
73af02b89f
use dummy2 as Inf/NAN handling flag
2025-06-12 13:33:56 -07:00
Martin Kroeker
f18b7a46bf
add dummy2 flag handling for inf/nan agnostic zeroing
2025-06-11 01:47:43 -07:00
guoyuanplct
2ae019161a
fixed the performance problem in RISCV64_ZVL256 when OPENBLAS_K is small
2025-06-05 21:53:03 +08:00
Srangrang
fb89820f20
Merge branch 'develop' of https://github.com/Srangrang/OpenBLAS into develop
2025-06-04 20:27:05 +08:00
Srangrang
4e1a381e5b
fix: resolve the compilation failure without zfh instruction
...
- modify the macro conditions in Makefile.system
- Delete development test code
Related to issue#5279
2025-06-04 20:00:12 +08:00
gkdddd
670ec6f757
Added shgemm_kernel_8x8 for RISCV64_ZVL128B and shgemm_kernel_16x8 for RISCV64_ZVL256B
...
Added HFLOAT16 support for RISCV64
Added shgemm_kernel_8x8 for RISCV64_ZVL128B and shgemm_kernel_16x8 for RISCV64_ZVL256B based on HFLOAT16
The instruction sets used are ZVFH and ZFH, which need to be supported by RVV1.0
Related to issue #5279
Co-authored-by Linjin Li <linjin_li@163.com >
2025-06-03 20:14:30 +08:00
guoyuanplct
d2003dc886
del lines
2025-05-29 18:38:22 +08:00
guoyuanplct
45fd2d9b07
Optimized the axpby function.
2025-05-29 17:50:44 +08:00
Srangrang
2996c25c94
add shgemm for RISCV_ZVL128B
2025-05-24 23:55:49 +08:00
guoyuanplct
be9f7550b5
Format Code
2025-05-15 18:55:47 +08:00
guoyuanplct
4d213653d8
kernel/riscv64:Added support for omatcopy on riscv64.
2025-05-15 13:29:14 +08:00
guoyuanplct
9a7e3f102b
kernel/riscv64:Fixed the bug of openblas_utest_ext failing in c/zgemv and some c/zgbmv tests:
2025-05-14 00:09:26 +08:00
guoyuanplct
11ffc8680e
Format the code
2025-04-25 00:27:27 +08:00
guoyuanplct
7616c42095
Optimized RVV_ZVL256B Implementation of zgemv_n
...
The implementation of zgemv_n using RVV_ZVL256B has been optimized.
Compared to the previous implementation, it has achieved a 1.5x
performance improvement.
2025-04-25 00:05:15 +08:00
lglglglgy
1ff303f36e
Optimizing the Implementation of GEMV on the RISC-V V Extension
...
Specialized some scenarios, performed loop unrolling, and reduced the
number of multiplications.
2025-04-08 21:18:00 +08:00
Martin Kroeker
180ba5e7d0
Merge pull request #5069 from tingboliao/dev_rotm_20250107
...
Further rearranged the rotm kernel for the different architectures.
2025-01-23 10:16:43 +01:00
tingbo.liao
3c8df6358f
Further rearranged the rotm kernel for the different architectures.
...
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com >
2025-01-22 11:41:12 +08:00
tingbo.liao
ef7f54b357
Optimized the gemm_tcopy_8_rvv to be compatible with the vlens 128 and 256.
...
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com >
2025-01-15 11:31:28 +08:00
tingbo.liao
0a5dbf13d3
Optimize the omatcopy_cn and zomatcopy_cn kernels with RVV 1.0 intrinsic.
...
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com >
2025-01-08 11:00:35 +08:00
tingbo.liao
c37509c213
Optimize the nrm2_rvv function to further improve performance.
...
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com >
2024-12-31 08:46:55 +08:00
tingbo.liao
0bea1cfd9d
Optimize the zgemm_tcopy_4_rvv function to be compatible with the situations where the vector lengths(vlens) are 128 and 256.
...
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com >
2024-12-24 10:33:27 +08:00
tingbo.liao
d00cc400b1
Replaced the __riscv_vid_v_i32m2 and __riscv_vid_v_i64m2 with __riscv_vid_v_u32m2 and __riscv_vid_v_u64m2 for riscv64-unknown-linux-gnu-gcc compiling.
...
Signed-off-by: tingbo.liao <tingbo.liao@starfivetech.com >
2024-12-18 08:38:30 +08:00
Martin Kroeker
a875304eb0
fix inverted conditional for NAN handling
2024-07-26 09:50:20 +02:00
Martin Kroeker
f5d04318e3
Merge branch 'OpenMathLib:develop' into scalfixes
2024-07-21 13:43:43 +02:00
Martin Kroeker
a815594fd1
Merge pull request #4801 from markdryan/markdryan/riscv-dynamic-arch
...
Add autodetection for riscv64
2024-07-19 17:12:07 +02:00
Martin Kroeker
2020569705
fix NAN handling and make it depend on dummy2 parameter
2024-07-17 23:55:54 +02:00
Martin Kroeker
3870995f01
make NAN handling depend on dummy2 parameter
2024-07-17 23:54:24 +02:00
Martin Kroeker
7284c533b5
make NAN handling depend on dummy2 parameter
2024-07-17 23:50:40 +02:00
Mark Ryan
67bf4b6998
Fix axpby_rvv kernels for cases where inc_y = 0
...
The following openblas_utest tests fail when the RISCV64_ZVL128B is
enabled.
TEST 89/103 axpby:zaxpby_inc_0 [FAIL]
TEST 92/103 axpby:caxpby_inc_0 [FAIL]
TEST 95/103 axpby:daxpby_inc_0 [FAIL]
TEST 98/103 axpby:saxpby_inc_0 [FAIL]
The issue is that the vectorized kernels do not work when inc_y == 0.
This patch updates the kernels to fall back to the scalar algorithms
when inc_y == 0, fixing the failing tests.
Signed-off-by: Mark Ryan <markdryan@rivosinc.com >
2024-07-15 14:24:47 +00:00
Mark Ryan
3b715e6162
Add autodetection for riscv64
...
Implement DYNAMIC_ARCH support for riscv64. Three cpu types are
supported, riscv64_generic, riscv64_zvl256b, riscv64_zvl128b.
The two non-generic kernels require CPU support for RVV 1.0 to
function correctly. Detecting that a riscv64 device supports
RVV 1.0 is a little complicated as there are some boards on the
market that advertise support for V via hwcap but only support
RVV 0.7.1, which is not binary compatible with RVV 1.0. The
approach taken is to first try hwprobe. If hwprobe is not
available, we fall back to hwcap + an additional check to distinguish
between RVV 1.0 and RVV 0.7.1.
Tested on a VM with VLEN=256, a CanMV K230 with VLEN=128 (with only
the big core enabled), a Lichee Pi with RVV 0.7.1 and a VF2 with no
vector.
A compiler with RVV 1.0 support must be used to build OpenBLAS for
riscv64 when DYNAMIC_ARCH=1.
Signed-off-by: Mark Ryan <markdryan@rivosinc.com >
2024-07-15 14:24:22 +00:00
Martin Kroeker
c1019d5832
Handle INF and NAN in inputs
2024-06-27 10:58:59 +02:00
Martin Kroeker
516743f7dc
fix other instances of mishandling INF
2024-05-31 16:02:12 +02:00
Martin Kroeker
cf80bd8500
Update nrm2_rvv.c
2024-03-13 13:07:26 +01:00
Martin Kroeker
9baa757905
Update nrm2_vector.c
2024-03-13 11:40:14 +01:00
Martin Kroeker
18a6db6862
Update nrm2_vector.c
2024-03-13 11:10:26 +01:00
Martin Kroeker
3752e73919
handle incx < 0
2024-03-12 20:44:01 +01:00
Martin Kroeker
db70c7f7fb
handle incx < 0
2024-03-12 20:42:11 +01:00
Martin Kroeker
dee8557d58
handle incx < 0
2024-03-12 20:40:29 +01:00
Martin Kroeker
d9dff17aec
handle incx < 0
2024-03-12 20:38:23 +01:00
Martin Kroeker
6b89e1f1d7
fix loop condition for incx < 0
2024-03-12 15:49:41 +01:00
Martin Kroeker
20016a0096
fix loop condition for incx < 0
2024-03-12 15:48:55 +01:00
Sergei Lewis
ba17758c02
fix axpy implementations where y has a stride of 0
2024-02-16 16:00:38 +00:00
Sergei Lewis
ff1523163f
Fix axpy test hangs when n==0. Reenable zaxpy_vector kernel for C910V.
2024-02-09 12:59:14 +00:00
Martin Kroeker
6d8a273cca
Handle zero increment(s) in C910V ?AXPBY ( #4483 )
...
* Handle zero increment(s)
2024-02-04 22:07:51 +01:00
Martin Kroeker
4d8dee508c
temporarily disable the CAXPY/ZAXPY kernels
2024-02-04 01:05:03 +01:00
Sergei Lewis
a3b0ef6596
Restore riscv64 fixes from develop branch: dot product double precision accumulation, zscal NaN handling
2024-02-01 10:32:00 +00:00
Sergei Lewis
1093def0d1
Merge branch 'risc-v' into develop
2024-01-29 11:11:39 +00:00
Martin Kroeker
889c5d026a
Merge pull request #4456 from kseniyazaytseva/riscv-rvv10
...
continuous build / build (cmake, flang, ubuntu-latest) (push) Canceled after 0s
continuous build / build (cmake, gfortran, macos-latest) (push) Canceled after 0s
continuous build / build (cmake, gfortran, ubuntu-latest) (push) Canceled after 0s
continuous build / build (make, flang, ubuntu-latest) (push) Canceled after 0s
continuous build / build (make, gfortran, macos-latest) (push) Canceled after 0s
continuous build / build (make, gfortran, ubuntu-latest) (push) Canceled after 0s
continuous build / msys2 (None, mingw-w64-x86_64-gcc-fortran, int32, MINGW64, mingw-w64-x86_64) (push) Canceled after 0s
continuous build / msys2 (Release, -DC_LAPACK=ON, int32, CLANG64, mingw-w64-clang-x86_64) (push) Canceled after 0s
continuous build / msys2 (Release, -DC_LAPACK=ON, int64, -DBINARY=64 -DINTERFACE64=1, CLANG64, mingw-w64-clang-x86_64) (push) Canceled after 0s
continuous build / msys2 (Release, mingw-w64-i686-gcc-fortran, int32, MINGW32, mingw-w64-i686) (push) Canceled after 0s
continuous build / msys2 (Release, mingw-w64-x86_64-gcc-fortran, int32, MINGW64, mingw-w64-x86_64) (push) Canceled after 0s
continuous build / msys2 (Release, mingw-w64-x86_64-gcc-fortran, int64, -DBINARY=64 -DINTERFACE64=1, MINGW64, mingw-w64-x86_64) (push) Canceled after 0s
continuous build / cross_build (DYNAMIC_ARCH=1 TARGET=GENERIC, mips64el, mips64el-linux-gnuabi64) (push) Canceled after 0s
continuous build / cross_build (TARGET=EV4, alpha, alpha-linux-gnu) (push) Canceled after 0s
continuous build / cross_build (TARGET=MIPS1004K, mipsel, mipsel-linux-gnu) (push) Canceled after 0s
continuous build / cross_build (TARGET=RISCV64_GENERIC, riscv64, riscv64-linux-gnu) (push) Canceled after 0s
mips64 qemu test / TEST (NO_SHARED=1 TARGET=I6400, I6400, mipsisa64r6el-linux-gnuabi64) (push) Canceled after 0s
mips64 qemu test / TEST (NO_SHARED=1 TARGET=I6500, I6500, mipsisa64r6el-linux-gnuabi64) (push) Canceled after 0s
mips64 qemu test / TEST (NO_SHARED=1 TARGET=MIPS64_GENERIC, MIPS64_GENERIC, mips64el-linux-gnuabi64) (push) Canceled after 0s
mips64 qemu test / TEST (NO_SHARED=1 TARGET=P6600, P6600, mipsisa64r6el-linux-gnuabi64) (push) Canceled after 0s
mips64 qemu test / TEST (NO_SHARED=1 TARGET=SICORTEX, SICORTEX, mips64el-linux-gnuabi64) (push) Canceled after 0s
Fix BLAS and LAPACK tests for RVV 1.0 target, update to 0.12.0 intrincics
2024-01-26 13:31:09 +01:00