diff options
| author | eopXD <yueh.ting.chen@gmail.com> | 2022-06-06 06:16:16 +0000 |
|---|---|---|
| committer | Alistair Francis <alistair.francis@wdc.com> | 2022-06-10 09:31:42 +1000 |
| commit | df4f52a7582c5cd8d2d2f73684996ebc18ac72e3 (patch) | |
| tree | 0c9ef5fad731e1261bf1410a8db20e4659cbb0a8 | |
| parent | 5eacf7d8a0fb19ea4d87eb678462fdb9a29b9190 (diff) | |
target/riscv: rvv: Add tail agnostic for vector reduction instructions
Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Reviewed-by: Weiwei Li <liweiwei@iscas.ac.cn>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <165449614532.19704.7000832880482980398-13@git.sr.ht>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>
| -rw-r--r-- | target/riscv/vector_helper.c | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 17390d8d06..174a548ac2 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -4535,6 +4535,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ { \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ + uint32_t esz = sizeof(TD); \ + uint32_t vlenb = simd_maxsz(desc); \ + uint32_t vta = vext_vta(desc); \ uint32_t i; \ TD s1 = *((TD *)vs1 + HD(0)); \ \ @@ -4547,6 +4550,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ } \ *((TD *)vd + HD(0)) = s1; \ env->vstart = 0; \ + /* set tail elements to 1s */ \ + vext_set_elems_1s(vd, vta, esz, vlenb); \ } /* vd[0] = sum(vs1[0], vs2[*]) */ @@ -4616,6 +4621,9 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ { \ uint32_t vm = vext_vm(desc); \ uint32_t vl = env->vl; \ + uint32_t esz = sizeof(TD); \ + uint32_t vlenb = simd_maxsz(desc); \ + uint32_t vta = vext_vta(desc); \ uint32_t i; \ TD s1 = *((TD *)vs1 + HD(0)); \ \ @@ -4628,6 +4636,8 @@ void HELPER(NAME)(void *vd, void *v0, void *vs1, \ } \ *((TD *)vd + HD(0)) = s1; \ env->vstart = 0; \ + /* set tail elements to 1s */ \ + vext_set_elems_1s(vd, vta, esz, vlenb); \ } /* Unordered sum */ @@ -4652,6 +4662,9 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1, { uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; + uint32_t esz = sizeof(uint32_t); + uint32_t vlenb = simd_maxsz(desc); + uint32_t vta = vext_vta(desc); uint32_t i; uint32_t s1 = *((uint32_t *)vs1 + H4(0)); @@ -4665,6 +4678,8 @@ void HELPER(vfwredsum_vs_h)(void *vd, void *v0, void *vs1, } *((uint32_t *)vd + H4(0)) = s1; env->vstart = 0; + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vta, esz, vlenb); } void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1, @@ -4672,6 +4687,9 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1, { uint32_t vm = vext_vm(desc); uint32_t vl = env->vl; + uint32_t esz = sizeof(uint64_t); + uint32_t vlenb = simd_maxsz(desc); + uint32_t vta = vext_vta(desc); uint32_t i; uint64_t s1 = *((uint64_t *)vs1); @@ -4685,6 +4703,8 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1, } *((uint64_t *)vd) = s1; env->vstart = 0; + /* set tail elements to 1s */ + vext_set_elems_1s(vd, vta, esz, vlenb); } /* |