[19/38] target/riscv: Signed 16-bit Multiply 64-bit Add/Subtract Instructions

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index b1f831bb02..2511134610 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1313,3 +1313,5 @@  DEF_HELPER_4(kmadrs, tl, env, tl, tl, tl)
 DEF_HELPER_4(kmaxds, tl, env, tl, tl, tl)
 DEF_HELPER_4(kmsda, tl, env, tl, tl, tl)
 DEF_HELPER_4(kmsxda, tl, env, tl, tl, tl)
+
+DEF_HELPER_3(smal, i64, env, i64, tl)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 4e5cdbb928..a022f660b7 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -781,3 +781,5 @@  kmadrs     0110110  ..... ..... 001 ..... 1111111 @r
 kmaxds     0111110  ..... ..... 001 ..... 1111111 @r
 kmsda      0100110  ..... ..... 001 ..... 1111111 @r
 kmsxda     0100111  ..... ..... 001 ..... 1111111 @r
+
+smal       0101111  ..... ..... 001 ..... 1111111 @r
diff --git a/target/riscv/insn_trans/trans_rvp.c.inc b/target/riscv/insn_trans/trans_rvp.c.inc
index 261aab402a..73a26bbfbd 100644
--- a/target/riscv/insn_trans/trans_rvp.c.inc
+++ b/target/riscv/insn_trans/trans_rvp.c.inc
@@ -602,3 +602,57 @@  GEN_RVP_R_ACC_OOL(kmadrs);
 GEN_RVP_R_ACC_OOL(kmaxds);
 GEN_RVP_R_ACC_OOL(kmsda);
 GEN_RVP_R_ACC_OOL(kmsxda);
+
+/* Signed 16-bit Multiply with 64-bit Add/Subtract Instructions */
+static bool
+r_d64_s64_ool(DisasContext *ctx, arg_r *a,
+              void (* fn)(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv))
+{
+#ifdef TARGET_RISCV64
+    return r_ool(ctx, a, fn);
+#else
+    TCGv_i32 src2, a0, a1, d0, d1;
+    TCGv_i64 src1, dst;
+
+    if (!has_ext(ctx, RVP) || !ctx->ext_p64) {
+        return false;
+    }
+
+    src1 = tcg_temp_new_i64();
+    src2 = tcg_temp_new_i32();
+    dst = tcg_temp_new_i64();
+    a0 = tcg_temp_new_i32();
+    a1 = tcg_temp_new_i32();
+
+    gen_get_gpr(a0, a->rs1);
+    gen_get_gpr(a1, a->rs1 + 1);
+    tcg_gen_concat_i32_i64(src1, a0, a1);
+    gen_get_gpr(src2, a->rs2);
+
+    fn(dst, cpu_env, src1, src2);
+
+    d0 = tcg_temp_new_i32();
+    d1 = tcg_temp_new_i32();
+    tcg_gen_extrl_i64_i32(d0, dst);
+    tcg_gen_extrh_i64_i32(d1, dst);
+    gen_set_gpr(a->rd, d0);
+    gen_set_gpr(a->rd + 1, d1);
+    tcg_temp_free_i32(d0);
+    tcg_temp_free_i32(d1);
+
+    tcg_temp_free_i64(src1);
+    tcg_temp_free_i32(src2);
+    tcg_temp_free_i64(dst);
+    tcg_temp_free_i32(a0);
+    tcg_temp_free_i32(a1);
+    return true;
+#endif
+}
+
+#define GEN_RVP_R_D64_S64_OOL(NAME)                    \
+static bool trans_##NAME(DisasContext *s, arg_r *a)    \
+{                                                      \
+    return r_d64_s64_ool(s, a, gen_helper_##NAME);     \
+}
+
+GEN_RVP_R_D64_S64_OOL(smal);
diff --git a/target/riscv/packed_helper.c b/target/riscv/packed_helper.c
index b3673a33ee..8ad7ea8354 100644
--- a/target/riscv/packed_helper.c
+++ b/target/riscv/packed_helper.c
@@ -1953,3 +1953,28 @@  static inline void do_kmsxda(CPURISCVState *env, void *vd, void *va,
 }
 
 RVPR_ACC(kmsxda, 1, 4);
+
+/* Signed 16-bit Multiply with 64-bit Add/Subtract Instructions */
+static inline void do_smal(CPURISCVState *env, void *vd, void *va,
+                           void *vb, uint8_t i)
+{
+    int64_t *d = vd, *a = va;
+    int16_t *b = vb;
+
+    if (i == 0) {
+        *d = *a;
+    }
+
+    *d += b[H2(i)] * b[H2(i + 1)];
+}
+
+uint64_t helper_smal(CPURISCVState *env, uint64_t a, target_ulong b)
+{
+    int i;
+    int64_t result = 0;
+
+    for (i = 0; i < sizeof(target_ulong); i += 2) {
+        do_smal(env, &result, &a, &b, i);
+    }
+    return result;
+}