[v8,26/62] target/riscv: vector single-width fractional multiply with rounding and saturation

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 32d549ce36..e6cae1b59c 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -736,3 +736,12 @@  DEF_HELPER_6(vasub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vasub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vasub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vasub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vsmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index e617d7bd60..633f782fbf 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -422,6 +422,8 @@  vaadd_vx        100100 . ..... ..... 100 ..... 1010111 @r_vm
 vaadd_vi        100100 . ..... ..... 011 ..... 1010111 @r_vm
 vasub_vv        100110 . ..... ..... 000 ..... 1010111 @r_vm
 vasub_vx        100110 . ..... ..... 100 ..... 1010111 @r_vm
+vsmul_vv        100111 . ..... ..... 000 ..... 1010111 @r_vm
+vsmul_vx        100111 . ..... ..... 100 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 6d5aa011c5..c17f0a6aae 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1754,3 +1754,7 @@  GEN_OPIVV_TRANS(vasub_vv, opivv_check)
 GEN_OPIVX_TRANS(vaadd_vx,  opivx_check)
 GEN_OPIVX_TRANS(vasub_vx,  opivx_check)
 GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
+
+/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
+GEN_OPIVV_TRANS(vsmul_vv, opivv_check)
+GEN_OPIVX_TRANS(vsmul_vx,  opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 784993b5f6..23868fb1b2 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2596,3 +2596,110 @@  GEN_VEXT_VX_RM(vasub_vx_b, 1, 1, clearb)
 GEN_VEXT_VX_RM(vasub_vx_h, 2, 2, clearh)
 GEN_VEXT_VX_RM(vasub_vx_w, 4, 4, clearl)
 GEN_VEXT_VX_RM(vasub_vx_d, 8, 8, clearq)
+
+/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
+static inline int8_t vsmul8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
+{
+    uint8_t round;
+    int16_t res;
+
+    res = (int16_t)a * (int16_t)b;
+    round = get_round(vxrm, res, 7);
+    res   = (res >> 7) + round;
+
+    if (res > INT8_MAX) {
+        env->vxsat = 0x1;
+        return INT8_MAX;
+    } else if (res < INT8_MIN) {
+        env->vxsat = 0x1;
+        return INT8_MIN;
+    } else {
+        return res;
+    }
+}
+
+static int16_t vsmul16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
+{
+    uint8_t round;
+    int32_t res;
+
+    res = (int32_t)a * (int32_t)b;
+    round = get_round(vxrm, res, 15);
+    res   = (res >> 15) + round;
+
+    if (res > INT16_MAX) {
+        env->vxsat = 0x1;
+        return INT16_MAX;
+    } else if (res < INT16_MIN) {
+        env->vxsat = 0x1;
+        return INT16_MIN;
+    } else {
+        return res;
+    }
+}
+
+static int32_t vsmul32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+{
+    uint8_t round;
+    int64_t res;
+
+    res = (int64_t)a * (int64_t)b;
+    round = get_round(vxrm, res, 31);
+    res   = (res >> 31) + round;
+
+    if (res > INT32_MAX) {
+        env->vxsat = 0x1;
+        return INT32_MAX;
+    } else if (res < INT32_MIN) {
+        env->vxsat = 0x1;
+        return INT32_MIN;
+    } else {
+        return res;
+    }
+}
+
+static int64_t vsmul64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+{
+    uint8_t round;
+    uint64_t hi_64, lo_64;
+    int64_t res;
+
+    if (a == INT64_MIN && b == INT64_MIN) {
+        env->vxsat = 1;
+        return INT64_MAX;
+    }
+
+    muls64(&lo_64, &hi_64, a, b);
+    round = get_round(vxrm, lo_64, 63);
+    /*
+     * Cannot overflow, as there are always
+     * 2 sign bits after multiply.
+     */
+    res = (hi_64 << 1) | (lo_64 >> 63);
+    if (round) {
+        if (res == INT64_MAX) {
+            env->vxsat = 1;
+        } else {
+            res += 1;
+        }
+    }
+    return res;
+}
+
+RVVCALL(OPIVV2_RM, vsmul_vv_b, OP_SSS_B, H1, H1, H1, vsmul8)
+RVVCALL(OPIVV2_RM, vsmul_vv_h, OP_SSS_H, H2, H2, H2, vsmul16)
+RVVCALL(OPIVV2_RM, vsmul_vv_w, OP_SSS_W, H4, H4, H4, vsmul32)
+RVVCALL(OPIVV2_RM, vsmul_vv_d, OP_SSS_D, H8, H8, H8, vsmul64)
+GEN_VEXT_VV_RM(vsmul_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vsmul_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vsmul_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_RM(vsmul_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_RM, vsmul_vx_b, OP_SSS_B, H1, H1, vsmul8)
+RVVCALL(OPIVX2_RM, vsmul_vx_h, OP_SSS_H, H2, H2, vsmul16)
+RVVCALL(OPIVX2_RM, vsmul_vx_w, OP_SSS_W, H4, H4, vsmul32)
+RVVCALL(OPIVX2_RM, vsmul_vx_d, OP_SSS_D, H8, H8, vsmul64)
+GEN_VEXT_VX_RM(vsmul_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vsmul_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vsmul_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_RM(vsmul_vx_d, 8, 8, clearq)