[PATCH qemu v4 12/14] target/riscv: rvv: Add tail agnostic for vector reduction instructions

[~eopxd]

From: eopXD <eop.chen@sifive.com>

Signed-off-by: eop Chen <eop.chen@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
---
 target/riscv/vector_helper.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d654377fc8..3d19b9d141 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4550,6 +4550,9 @@ 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 = env_archcpu(env)->cfg.vlen >> 3;     \
+    uint32_t vta = vext_vta(desc);                        \
     uint32_t i;                                           \
     TD s1 =  *((TD *)vs1 + HD(0));                        \
                                                           \
@@ -4562,6 +4565,9 @@ 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_fns[ctzl(esz)](vd, vta, 1, esz,     \
+                                     vlenb);              \
 }
 
 /* vd[0] = sum(vs1[0], vs2[*]) */
@@ -4667,6 +4673,9 @@ 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 = env_archcpu(env)->cfg.vlen >> 3;
+    uint32_t vta = vext_vta(desc);
     uint32_t i;
     uint32_t s1 =  *((uint32_t *)vs1 + H4(0));
 
@@ -4680,6 +4689,8 @@ 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_fns[ctzl(esz)](vd, vta, 1, esz, vlenb);
 }
 
 void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
@@ -4687,6 +4698,9 @@ 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 = env_archcpu(env)->cfg.vlen >> 3;
+    uint32_t vta = vext_vta(desc);
     uint32_t i;
     uint64_t s1 =  *((uint64_t *)vs1);
 
@@ -4700,6 +4714,8 @@ 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_fns[ctzl(esz)](vd, vta, 1, esz, vlenb);
 }
 
 /*
-- 
2.34.1