aboutsummaryrefslogtreecommitdiff
path: root/libcpp/include/cpplib.h
diff options
context:
space:
mode:
authorJuzhe-Zhong <juzhe.zhong@rivai.ai>2023-11-01 14:56:39 +0800
committerPan Li <pan2.li@intel.com>2023-11-02 08:51:15 +0800
commit1a0af6e5a99cd895a663f0221c25321ae802413f (patch)
tree0402ab6261de29021fa24ab0f7386627b1f42e86 /libcpp/include/cpplib.h
parentc73d2d49f9beec33bb843a0c04bde8bc41d7a0b9 (diff)
downloadgcc-1a0af6e5a99cd895a663f0221c25321ae802413f.zip
gcc-1a0af6e5a99cd895a663f0221c25321ae802413f.tar.gz
gcc-1a0af6e5a99cd895a663f0221c25321ae802413f.tar.bz2
RISC-V: Allow dest operand and accumulator operand overlap of widen reduction instruction[PR112327]
Consider this following intrinsic code: void rvv_dot_prod(int16_t *pSrcA, int16_t *pSrcB, uint32_t n, int64_t *result) { size_t vl; vint16m4_t vSrcA, vSrcB; vint64m1_t vSum = __riscv_vmv_s_x_i64m1(0, 1); while (n > 0) { vl = __riscv_vsetvl_e16m4(n); vSrcA = __riscv_vle16_v_i16m4(pSrcA, vl); vSrcB = __riscv_vle16_v_i16m4(pSrcB, vl); vSum = __riscv_vwredsum_vs_i32m8_i64m1(__riscv_vwmul_vv_i32m8(vSrcA, vSrcB, vl), vSum, vl); pSrcA += vl; pSrcB += vl; n -= vl; } *result = __riscv_vmv_x_s_i64m1_i64(vSum); } https://godbolt.org/z/vWd35W7G6 Before this patch: ... Loop: ... vmv1r.v v2,v1 ... vwredsum.vs v1,v8,v2 ... After this patch: ... Loop: ... vwredsum.vs v1,v8,v1 ... PR target/112327 gcc/ChangeLog: * config/riscv/vector.md: Add '0'. gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/base/pr112327-1.c: New test. * gcc.target/riscv/rvv/base/pr112327-2.c: New test.
Diffstat (limited to 'libcpp/include/cpplib.h')
0 files changed, 0 insertions, 0 deletions