mirror of
https://github.com/opencv/opencv.git
synced 2024-12-15 18:09:11 +08:00
b5ea32158a
Upgrade RISC-V Vector intrinsic and cleanup the obsolete RVV backend. #25883 This patch upgrade RISC-V Vector intrinsic from `v0.10` to `v0.12`/`v1.0`: - Update cmake check and options; - Upgrade RVV implement for Universal Intrinsic; - Upgrade RVV optimized DNN kernel. - Cleanup the obsolete RVV backend (`intrin_rvv.hpp`) and compatable header file. With this patch, RVV backend require Clang 17+ or GCC 14+ (which means `__riscv_v_intrinsic >= 12000`, see https://godbolt.org/z/es7ncETE3) This patch is test with Clang 17.0.6 (require extra `-DWITH_PNG=OFF` due to ICE), Clang 18.1.8 and GCC 14.1.0 on QEMU and k230 (with `--gtest_filter="*hal_*"`). ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake
38 lines
1.1 KiB
C++
38 lines
1.1 KiB
C++
#include <stdio.h>
|
|
|
|
#if !defined(__riscv) || !defined(__riscv_v)
|
|
#error "RISC-V or vector extension(RVV) is not supported by the compiler"
|
|
#endif
|
|
|
|
#if !defined(__THEAD_VERSION__) && defined(__riscv_v_intrinsic) && __riscv_v_intrinsic < 12000
|
|
#error "Wrong intrinsics version, v0.12 or higher is required for gcc or clang"
|
|
#endif
|
|
|
|
#include <riscv_vector.h>
|
|
|
|
#ifdef __THEAD_VERSION__
|
|
int test()
|
|
{
|
|
const float src[] = { 0.0f, 0.0f, 0.0f, 0.0f };
|
|
uint64_t ptr[2] = {0x0908060504020100, 0xFFFFFFFF0E0D0C0A};
|
|
vuint8m1_t a = vreinterpret_v_u64m1_u8m1(vle64_v_u64m1(ptr, 2));
|
|
vfloat32m1_t val = vle32_v_f32m1((const float*)(src), 4);
|
|
return (int)vfmv_f_s_f32m1_f32(val);
|
|
}
|
|
#else
|
|
int test()
|
|
{
|
|
const float src[] = { 0.0f, 0.0f, 0.0f, 0.0f };
|
|
uint64_t ptr[2] = {0x0908060504020100, 0xFFFFFFFF0E0D0C0A};
|
|
vuint8m1_t a = __riscv_vreinterpret_v_u64m1_u8m1(__riscv_vle64_v_u64m1(ptr, 2));
|
|
vfloat32m1_t val = __riscv_vle32_v_f32m1((const float*)(src), 4);
|
|
return (int)__riscv_vfmv_f_s_f32m1_f32(val);
|
|
}
|
|
#endif
|
|
|
|
int main()
|
|
{
|
|
printf("%d\n", test());
|
|
return 0;
|
|
}
|