s390x/tcg: Implement VECTOR MULTIPLY AND ADD *

Quite some variants to handle. At least handle some 32-bit element
variants via gvec expansion (we could also handle 16/32-bit variants
for ODD and EVEN easily via gvec expansion, but let's keep it simple
for now).

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>

4 files changed, 277 insertions, 0 deletions

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 6e6ba9bf32..18f8756d43 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -162,6 +162,24 @@ DEF_HELPER_FLAGS_5(gvec_vgfma8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i3
 DEF_HELPER_FLAGS_5(gvec_vgfma16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_5(gvec_vgfma32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_5(gvec_vgfma64, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmal8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmal16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmah8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmah16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmalh8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmalh16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmae8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmae16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmae32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmale8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmale16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmale32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmao8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmao16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmao32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmalo8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmalo16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_5(gvec_vmalo32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i32)
 
 #ifndef CONFIG_USER_ONLY
 DEF_HELPER_3(servc, i32, env, i64, i64)
diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index b22d9f0f6a..7ccec0544f 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1106,6 +1106,20 @@
     F(0xe7fe, VMN,     VRR_c, V,   0, 0, 0, 0, vmx, 0, IF_VEC)
 /* VECTOR MINIMUM LOGICAL */
     F(0xe7fc, VMNL,    VRR_c, V,   0, 0, 0, 0, vmx, 0, IF_VEC)
+/* VECTOR MULTIPLY AND ADD LOW */
+    F(0xe7aa, VMAL,    VRR_d, V,   0, 0, 0, 0, vma, 0, IF_VEC)
+/* VECTOR MULTIPLY AND ADD HIGH */
+    F(0xe7ab, VMAH,    VRR_d, V,   0, 0, 0, 0, vma, 0, IF_VEC)
+/* VECTOR MULTIPLY AND ADD LOGICAL HIGH */
+    F(0xe7a9, VMALH,   VRR_d, V,   0, 0, 0, 0, vma, 0, IF_VEC)
+/* VECTOR MULTIPLY AND ADD EVEN */
+    F(0xe7ae, VMAE,    VRR_d, V,   0, 0, 0, 0, vma, 0, IF_VEC)
+/* VECTOR MULTIPLY AND ADD LOGICAL EVEN */
+    F(0xe7ac, VMALE,   VRR_d, V,   0, 0, 0, 0, vma, 0, IF_VEC)
+/* VECTOR MULTIPLY AND ADD ODD */
+    F(0xe7af, VMAO,    VRR_d, V,   0, 0, 0, 0, vma, 0, IF_VEC)
+/* VECTOR MULTIPLY AND ADD LOGICAL ODD */
+    F(0xe7ad, VMALO,   VRR_d, V,   0, 0, 0, 0, vma, 0, IF_VEC)
 
 #ifndef CONFIG_USER_ONLY
 /* COMPARE AND SWAP AND PURGE */
diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
index bb27cad4d8..7de411f4f6 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -1581,3 +1581,125 @@ static DisasJumpType op_vmx(DisasContext *s, DisasOps *o)
     }
     return DISAS_NEXT;
 }
+
+static void gen_mal_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b, TCGv_i32 c)
+{
+    TCGv_i32 t0 = tcg_temp_new_i32();
+
+    tcg_gen_mul_i32(t0, a, b);
+    tcg_gen_add_i32(d, t0, c);
+
+    tcg_temp_free_i32(t0);
+}
+
+static void gen_mah_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b, TCGv_i32 c)
+{
+    TCGv_i64 t0 = tcg_temp_new_i64();
+    TCGv_i64 t1 = tcg_temp_new_i64();
+    TCGv_i64 t2 = tcg_temp_new_i64();
+
+    tcg_gen_ext_i32_i64(t0, a);
+    tcg_gen_ext_i32_i64(t1, b);
+    tcg_gen_ext_i32_i64(t2, c);
+    tcg_gen_mul_i64(t0, t0, t1);
+    tcg_gen_add_i64(t0, t0, t2);
+    tcg_gen_extrh_i64_i32(d, t0);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+    tcg_temp_free(t2);
+}
+
+static void gen_malh_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b, TCGv_i32 c)
+{
+    TCGv_i64 t0 = tcg_temp_new_i64();
+    TCGv_i64 t1 = tcg_temp_new_i64();
+    TCGv_i64 t2 = tcg_temp_new_i64();
+
+    tcg_gen_extu_i32_i64(t0, a);
+    tcg_gen_extu_i32_i64(t1, b);
+    tcg_gen_extu_i32_i64(t2, c);
+    tcg_gen_mul_i64(t0, t0, t1);
+    tcg_gen_add_i64(t0, t0, t2);
+    tcg_gen_extrh_i64_i32(d, t0);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+    tcg_temp_free(t2);
+}
+
+static DisasJumpType op_vma(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m5);
+    static const GVecGen4 g_vmal[3] = {
+        { .fno = gen_helper_gvec_vmal8, },
+        { .fno = gen_helper_gvec_vmal16, },
+        { .fni4 = gen_mal_i32, },
+    };
+    static const GVecGen4 g_vmah[3] = {
+        { .fno = gen_helper_gvec_vmah8, },
+        { .fno = gen_helper_gvec_vmah16, },
+        { .fni4 = gen_mah_i32, },
+    };
+    static const GVecGen4 g_vmalh[3] = {
+        { .fno = gen_helper_gvec_vmalh8, },
+        { .fno = gen_helper_gvec_vmalh16, },
+        { .fni4 = gen_malh_i32, },
+    };
+    static const GVecGen4 g_vmae[3] = {
+        { .fno = gen_helper_gvec_vmae8, },
+        { .fno = gen_helper_gvec_vmae16, },
+        { .fno = gen_helper_gvec_vmae32, },
+    };
+    static const GVecGen4 g_vmale[3] = {
+        { .fno = gen_helper_gvec_vmale8, },
+        { .fno = gen_helper_gvec_vmale16, },
+        { .fno = gen_helper_gvec_vmale32, },
+    };
+    static const GVecGen4 g_vmao[3] = {
+        { .fno = gen_helper_gvec_vmao8, },
+        { .fno = gen_helper_gvec_vmao16, },
+        { .fno = gen_helper_gvec_vmao32, },
+    };
+    static const GVecGen4 g_vmalo[3] = {
+        { .fno = gen_helper_gvec_vmalo8, },
+        { .fno = gen_helper_gvec_vmalo16, },
+        { .fno = gen_helper_gvec_vmalo32, },
+    };
+    const GVecGen4 *fn;
+
+    if (es > ES_32) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    switch (s->fields->op2) {
+    case 0xaa:
+        fn = &g_vmal[es];
+        break;
+    case 0xab:
+        fn = &g_vmah[es];
+        break;
+    case 0xa9:
+        fn = &g_vmalh[es];
+        break;
+    case 0xae:
+        fn = &g_vmae[es];
+        break;
+    case 0xac:
+        fn = &g_vmale[es];
+        break;
+    case 0xaf:
+        fn = &g_vmao[es];
+        break;
+    case 0xad:
+        fn = &g_vmalo[es];
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    gen_gvec_4(get_field(s->fields, v1), get_field(s->fields, v2),
+               get_field(s->fields, v3), get_field(s->fields, v4), fn);
+    return DISAS_NEXT;
+}
diff --git a/target/s390x/vec_int_helper.c b/target/s390x/vec_int_helper.c
index 20a1034dd8..171c20fc54 100644
--- a/target/s390x/vec_int_helper.c
+++ b/target/s390x/vec_int_helper.c
@@ -241,3 +241,126 @@ void HELPER(gvec_vgfma64)(void *v1, const void *v2, const void *v3,
     s390_vec_xor(&tmp1, &tmp1, &tmp2);
     s390_vec_xor(v1, &tmp1, v4);
 }
+
+#define DEF_VMAL(BITS)                                                         \
+void HELPER(gvec_vmal##BITS)(void *v1, const void *v2, const void *v3,         \
+                             const void *v4, uint32_t desc)                    \
+{                                                                              \
+    int i;                                                                     \
+                                                                               \
+    for (i = 0; i < (128 / BITS); i++) {                                       \
+        const uint##BITS##_t a = s390_vec_read_element##BITS(v2, i);           \
+        const uint##BITS##_t b = s390_vec_read_element##BITS(v3, i);           \
+        const uint##BITS##_t c = s390_vec_read_element##BITS(v4, i);           \
+                                                                               \
+        s390_vec_write_element##BITS(v1, i, a * b + c);                        \
+    }                                                                          \
+}
+DEF_VMAL(8)
+DEF_VMAL(16)
+
+#define DEF_VMAH(BITS)                                                         \
+void HELPER(gvec_vmah##BITS)(void *v1, const void *v2, const void *v3,         \
+                             const void *v4, uint32_t desc)                    \
+{                                                                              \
+    int i;                                                                     \
+                                                                               \
+    for (i = 0; i < (128 / BITS); i++) {                                       \
+        const int32_t a = (int##BITS##_t)s390_vec_read_element##BITS(v2, i);   \
+        const int32_t b = (int##BITS##_t)s390_vec_read_element##BITS(v3, i);   \
+        const int32_t c = (int##BITS##_t)s390_vec_read_element##BITS(v4, i);   \
+                                                                               \
+        s390_vec_write_element##BITS(v1, i, (a * b + c) >> BITS);              \
+    }                                                                          \
+}
+DEF_VMAH(8)
+DEF_VMAH(16)
+
+#define DEF_VMALH(BITS)                                                        \
+void HELPER(gvec_vmalh##BITS)(void *v1, const void *v2, const void *v3,        \
+                              const void *v4, uint32_t desc)                   \
+{                                                                              \
+    int i;                                                                     \
+                                                                               \
+    for (i = 0; i < (128 / BITS); i++) {                                       \
+        const uint##BITS##_t a = s390_vec_read_element##BITS(v2, i);           \
+        const uint##BITS##_t b = s390_vec_read_element##BITS(v3, i);           \
+        const uint##BITS##_t c = s390_vec_read_element##BITS(v4, i);           \
+                                                                               \
+        s390_vec_write_element##BITS(v1, i, (a * b + c) >> BITS);              \
+    }                                                                          \
+}
+DEF_VMALH(8)
+DEF_VMALH(16)
+
+#define DEF_VMAE(BITS, TBITS)                                                  \
+void HELPER(gvec_vmae##BITS)(void *v1, const void *v2, const void *v3,         \
+                             const void *v4, uint32_t desc)                    \
+{                                                                              \
+    int i, j;                                                                  \
+                                                                               \
+    for (i = 0, j = 0; i < (128 / TBITS); i++, j += 2) {                       \
+        int##TBITS##_t a = (int##BITS##_t)s390_vec_read_element##BITS(v2, j);  \
+        int##TBITS##_t b = (int##BITS##_t)s390_vec_read_element##BITS(v3, j);  \
+        int##TBITS##_t c = (int##BITS##_t)s390_vec_read_element##BITS(v4, j);  \
+                                                                               \
+        s390_vec_write_element##TBITS(v1, i, a * b + c);                       \
+    }                                                                          \
+}
+DEF_VMAE(8, 16)
+DEF_VMAE(16, 32)
+DEF_VMAE(32, 64)
+
+#define DEF_VMALE(BITS, TBITS)                                                 \
+void HELPER(gvec_vmale##BITS)(void *v1, const void *v2, const void *v3,        \
+                              const void *v4, uint32_t desc)                   \
+{                                                                              \
+    int i, j;                                                                  \
+                                                                               \
+    for (i = 0, j = 0; i < (128 / TBITS); i++, j += 2) {                       \
+        uint##TBITS##_t a = s390_vec_read_element##BITS(v2, j);                \
+        uint##TBITS##_t b = s390_vec_read_element##BITS(v3, j);                \
+        uint##TBITS##_t c = s390_vec_read_element##BITS(v4, j);                \
+                                                                               \
+        s390_vec_write_element##TBITS(v1, i, a * b + c);                       \
+    }                                                                          \
+}
+DEF_VMALE(8, 16)
+DEF_VMALE(16, 32)
+DEF_VMALE(32, 64)
+
+#define DEF_VMAO(BITS, TBITS)                                                  \
+void HELPER(gvec_vmao##BITS)(void *v1, const void *v2, const void *v3,         \
+                             const void *v4, uint32_t desc)                    \
+{                                                                              \
+    int i, j;                                                                  \
+                                                                               \
+    for (i = 0, j = 1; i < (128 / TBITS); i++, j += 2) {                       \
+        int##TBITS##_t a = (int##BITS##_t)s390_vec_read_element##BITS(v2, j);  \
+        int##TBITS##_t b = (int##BITS##_t)s390_vec_read_element##BITS(v3, j);  \
+        int##TBITS##_t c = (int##BITS##_t)s390_vec_read_element##BITS(v4, j);  \
+                                                                               \
+        s390_vec_write_element##TBITS(v1, i, a * b + c);                       \
+    }                                                                          \
+}
+DEF_VMAO(8, 16)
+DEF_VMAO(16, 32)
+DEF_VMAO(32, 64)
+
+#define DEF_VMALO(BITS, TBITS)                                                 \
+void HELPER(gvec_vmalo##BITS)(void *v1, const void *v2, const void *v3,        \
+                              const void *v4, uint32_t desc)                   \
+{                                                                              \
+    int i, j;                                                                  \
+                                                                               \
+    for (i = 0, j = 1; i < (128 / TBITS); i++, j += 2) {                       \
+        uint##TBITS##_t a = s390_vec_read_element##BITS(v2, j);                \
+        uint##TBITS##_t b = s390_vec_read_element##BITS(v3, j);                \
+        uint##TBITS##_t c = s390_vec_read_element##BITS(v4, j);                \
+                                                                               \
+        s390_vec_write_element##TBITS(v1, i, a * b + c);                       \
+    }                                                                          \
+}
+DEF_VMALO(8, 16)
+DEF_VMALO(16, 32)
+DEF_VMALO(32, 64)