When sew <= 32bits, not need to extend scalar reg.
When sew > 32bits, if xlen is less that sew, we should sign extend
the scalar register, except explicitly specified by the spec.
Signed-off-by: LIU Zhiwei <zhiwei_...@c-sky.com>
---
target/riscv/insn_trans/trans_rvv.c.inc | 5 +++--
target/riscv/internals.h | 1 +
target/riscv/vector_helper.c | 11 +++++++++--
3 files changed, 13 insertions(+), 4 deletions(-)
diff --git a/target/riscv/insn_trans/trans_rvv.c.inc
b/target/riscv/insn_trans/trans_rvv.c.inc
index 41c7c88904..0a956cac5b 100644
--- a/target/riscv/insn_trans/trans_rvv.c.inc
+++ b/target/riscv/insn_trans/trans_rvv.c.inc
@@ -846,7 +846,7 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t
vs2, uint32_t vm,
dest = tcg_temp_new_ptr();
mask = tcg_temp_new_ptr();
src2 = tcg_temp_new_ptr();
- src1 = get_gpr(s, rs1, EXT_NONE);
+ src1 = get_gpr(s, rs1, EXT_SIGN);
data = FIELD_DP32(data, VDATA, MLEN, s->mlen);
data = FIELD_DP32(data, VDATA, VM, vm);
@@ -2670,6 +2670,7 @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x *a)
/* This instruction ignores LMUL and vector register groups */
int maxsz = s->vlen >> 3;
TCGv_i64 t1;
+ TCGv src1 = get_gpr(s, a->rs1, EXT_ZERO);
TCGLabel *over = gen_new_label();
tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over);
@@ -2679,7 +2680,7 @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x *a)
}
t1 = tcg_temp_new_i64();
- tcg_gen_extu_tl_i64(t1, cpu_gpr[a->rs1]);
+ tcg_gen_extu_tl_i64(t1, src1);
vec_element_storei(s, a->rd, 0, t1);
tcg_temp_free_i64(t1);
done:
diff --git a/target/riscv/internals.h b/target/riscv/internals.h
index b15ad394bb..07e882160d 100644
--- a/target/riscv/internals.h
+++ b/target/riscv/internals.h
@@ -27,6 +27,7 @@ FIELD(VDATA, VM, 8, 1)
FIELD(VDATA, LMUL, 9, 2)
FIELD(VDATA, NF, 11, 4)
FIELD(VDATA, WD, 11, 1)
+FIELD(VDATA, TRUNC, 15, 1)
/* float point classify helpers */
target_ulong fclass_h(uint64_t frs1);
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 0b297f6bc8..51bcf63d65 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -112,6 +112,11 @@ static uint32_t vext_wd(uint32_t desc)
return (simd_data(desc) >> 11) & 0x1;
}
+static inline bool vext_trunc(uint32_t desc)
+{
+ return FIELD_EX32(simd_data(desc), VDATA, TRUNC);
+}
+
/*
* Get vector group length in bytes. Its range is [64, 2048].
*
@@ -4748,6 +4753,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
uint32_t mlen = vext_mlen(desc); \
uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \
uint32_t vm = vext_vm(desc); \
+ bool trunc = vext_trunc(desc); \
uint32_t vl = env->vl; \
uint32_t i; \
\
@@ -4756,7 +4762,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
continue; \
} \
if (i == 0) { \
- *((ETYPE *)vd + H(i)) = s1; \
+ *((ETYPE *)vd + H(i)) = trunc ? (s1 & UINT32_MAX) : s1; \
} else { \
*((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - 1)); \
} \
@@ -4777,6 +4783,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
uint32_t mlen = vext_mlen(desc); \
uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen; \
uint32_t vm = vext_vm(desc); \
+ bool trunc = vext_trunc(desc); \
uint32_t vl = env->vl; \
uint32_t i; \
\
@@ -4785,7 +4792,7 @@ void HELPER(NAME)(void *vd, void *v0, target_ulong s1,
void *vs2, \
continue; \
} \
if (i == vl - 1) { \
- *((ETYPE *)vd + H(i)) = s1; \
+ *((ETYPE *)vd + H(i)) = trunc ? (s1 & UINT32_MAX) : s1; \
} else { \
*((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i + 1)); \
} \
--
2.25.1
