[Qemu-devel] [PATCH v1 20/41] s390x/tcg: Implement VECTOR MULTIPLY *

[David Hildenbrand <david@redhat.com>]

Yet another set of variants. Implement it similar to VECTOR MULTIPLY AND
ADD *. At least for one variant we have a gvec helper we can reuse.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/helper.h           |  16 +++++
 target/s390x/insn-data.def      |  14 +++++
 target/s390x/translate_vx.inc.c | 100 ++++++++++++++++++++++++++++++++
 target/s390x/vec_int_helper.c   | 100 ++++++++++++++++++++++++++++++++
 4 files changed, 230 insertions(+)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index b73a35107e..a44cc462ae 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -184,6 +184,22 @@ DEF_HELPER_FLAGS_5(gvec_vmao32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, cptr, i3
 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)
+DEF_HELPER_FLAGS_4(gvec_vmh8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmh16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmlh8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmlh16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vme8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vme16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vme32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmle8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmle16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmle32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmo8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmo16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmo32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmlo8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmlo16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vmlo32, TCG_CALL_NO_RWG, void, ptr, 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 7ccec0544f..2c794a2744 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1120,6 +1120,20 @@
     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)
+/* VECTOR MULTIPLY HIGH */
+    F(0xe7a3, VMH,     VRR_c, V,   0, 0, 0, 0, vm, 0, IF_VEC)
+/* VECTOR MULTIPLY LOGICAL HIGH */
+    F(0xe7a1, VMLH,    VRR_c, V,   0, 0, 0, 0, vm, 0, IF_VEC)
+/* VECTOR MULTIPLY LOW */
+    F(0xe7a2, VML,     VRR_c, V,   0, 0, 0, 0, vm, 0, IF_VEC)
+/* VECTOR MULTIPLY EVEN */
+    F(0xe7a6, VME,     VRR_c, V,   0, 0, 0, 0, vm, 0, IF_VEC)
+/* VECTOR MULTIPLY LOGICAL EVEN */
+    F(0xe7a4, VMLE,    VRR_c, V,   0, 0, 0, 0, vm, 0, IF_VEC)
+/* VECTOR MULTIPLY ODD */
+    F(0xe7a7, VMO,     VRR_c, V,   0, 0, 0, 0, vm, 0, IF_VEC)
+/* VECTOR MULTIPLY LOGICAL ODD */
+    F(0xe7a5, VMLO,    VRR_c, V,   0, 0, 0, 0, vm, 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 4967af6a07..53bbb4a2ce 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -1689,3 +1689,103 @@ static DisasJumpType op_vma(DisasContext *s, DisasOps *o)
                get_field(s->fields, v3), get_field(s->fields, v4), fn);
     return DISAS_NEXT;
 }
+
+static void gen_mh_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i64 t0 = tcg_temp_new_i64();
+    TCGv_i64 t1 = tcg_temp_new_i64();
+
+    tcg_gen_ext_i32_i64(t0, a);
+    tcg_gen_ext_i32_i64(t1, b);
+    tcg_gen_mul_i64(t0, t0, t1);
+    tcg_gen_extrh_i64_i32(d, t0);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+}
+
+static void gen_mlh_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i64 t0 = tcg_temp_new_i64();
+    TCGv_i64 t1 = tcg_temp_new_i64();
+
+    tcg_gen_extu_i32_i64(t0, a);
+    tcg_gen_extu_i32_i64(t1, b);
+    tcg_gen_mul_i64(t0, t0, t1);
+    tcg_gen_extrh_i64_i32(d, t0);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+}
+
+static DisasJumpType op_vm(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    static const GVecGen3 g_vmh[3] = {
+        { .fno = gen_helper_gvec_vmh8, },
+        { .fno = gen_helper_gvec_vmh16, },
+        { .fni4 = gen_mh_i32, },
+    };
+    static const GVecGen3 g_vmlh[3] = {
+        { .fno = gen_helper_gvec_vmlh8, },
+        { .fno = gen_helper_gvec_vmlh16, },
+        { .fni4 = gen_mlh_i32, },
+    };
+    static const GVecGen3 g_vme[3] = {
+        { .fno = gen_helper_gvec_vme8, },
+        { .fno = gen_helper_gvec_vme16, },
+        { .fno = gen_helper_gvec_vme32, },
+    };
+    static const GVecGen3 g_vmle[3] = {
+        { .fno = gen_helper_gvec_vmle8, },
+        { .fno = gen_helper_gvec_vmle16, },
+        { .fno = gen_helper_gvec_vmle32, },
+    };
+    static const GVecGen3 g_vmo[3] = {
+        { .fno = gen_helper_gvec_vmo8, },
+        { .fno = gen_helper_gvec_vmo16, },
+        { .fno = gen_helper_gvec_vmo32, },
+    };
+    static const GVecGen3 g_vmlo[3] = {
+        { .fno = gen_helper_gvec_vmlo8, },
+        { .fno = gen_helper_gvec_vmlo16, },
+        { .fno = gen_helper_gvec_vmlo32, },
+    };
+    const GVecGen3 *fn;
+
+    if (es > ES_32) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    switch (s->fields->op2) {
+    case 0xa2:
+        gen_gvec_fn_3(mul, es, get_field(s->fields, v1),
+                      get_field(s->fields, v2), get_field(s->fields, v3));
+        return DISAS_NEXT;
+    case 0xa3:
+        fn = &g_vmh[es];
+        break;
+    case 0xa1:
+        fn = &g_vmlh[es];
+        break;
+    case 0xa6:
+        fn = &g_vme[es];
+        break;
+    case 0xa4:
+        fn = &g_vmle[es];
+        break;
+    case 0xa7:
+        fn = &g_vmo[es];
+        break;
+    case 0xa5:
+        fn = &g_vmlo[es];
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    gen_gvec_3(get_field(s->fields, v1), get_field(s->fields, v2),
+               get_field(s->fields, v3), fn);
+    return DISAS_NEXT;
+}
diff --git a/target/s390x/vec_int_helper.c b/target/s390x/vec_int_helper.c
index 424f248325..b818c513a9 100644
--- a/target/s390x/vec_int_helper.c
+++ b/target/s390x/vec_int_helper.c
@@ -426,3 +426,103 @@ void HELPER(gvec_vmalo##BITS)(void *v1, const void *v2, const void *v3,        \
 DEF_VMALO(8, 16)
 DEF_VMALO(16, 32)
 DEF_VMALO(32, 64)
+
+#define DEF_VMH(BITS)                                                          \
+void HELPER(gvec_vmh##BITS)(void *v1, const void *v2, const void *v3,          \
+                            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);   \
+                                                                               \
+        s390_vec_write_element##BITS(v1, i, (a * b) >> BITS);                  \
+    }                                                                          \
+}
+DEF_VMH(8)
+DEF_VMH(16)
+
+#define DEF_VMLH(BITS)                                                         \
+void HELPER(gvec_vmlh##BITS)(void *v1, const void *v2, const void *v3,         \
+                             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);           \
+                                                                               \
+        s390_vec_write_element##BITS(v1, i, (a * b) >> BITS);                  \
+    }                                                                          \
+}
+DEF_VMLH(8)
+DEF_VMLH(16)
+
+#define DEF_VME(BITS, TBITS)                                                   \
+void HELPER(gvec_vme##BITS)(void *v1, const void *v2, const void *v3,          \
+                            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);  \
+                                                                               \
+        s390_vec_write_element##TBITS(v1, i, a * b);                           \
+    }                                                                          \
+}
+DEF_VME(8, 16)
+DEF_VME(16, 32)
+DEF_VME(32, 64)
+
+#define DEF_VMLE(BITS, TBITS)                                                  \
+void HELPER(gvec_vmle##BITS)(void *v1, const void *v2, const void *v3,         \
+                             uint32_t desc)                                    \
+{                                                                              \
+    int i, j;                                                                  \
+                                                                               \
+    for (i = 0, j = 0; i < (128 / TBITS); i++, j += 2) {                       \
+        const uint##TBITS##_t a = s390_vec_read_element##BITS(v2, j);          \
+        const uint##TBITS##_t b = s390_vec_read_element##BITS(v3, j);          \
+                                                                               \
+        s390_vec_write_element##TBITS(v1, i, a * b);                           \
+    }                                                                          \
+}
+DEF_VMLE(8, 16)
+DEF_VMLE(16, 32)
+DEF_VMLE(32, 64)
+
+#define DEF_VMO(BITS, TBITS)                                                   \
+void HELPER(gvec_vmo##BITS)(void *v1, const void *v2, const void *v3,          \
+                            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);  \
+                                                                               \
+        s390_vec_write_element##TBITS(v1, i, a * b);                           \
+    }                                                                          \
+}
+DEF_VMO(8, 16)
+DEF_VMO(16, 32)
+DEF_VMO(32, 64)
+
+#define DEF_VMLO(BITS, TBITS)                                                  \
+void HELPER(gvec_vmlo##BITS)(void *v1, const void *v2, const void *v3,         \
+                             uint32_t desc)                                    \
+{                                                                              \
+    int i, j;                                                                  \
+                                                                               \
+    for (i = 0, j = 0; i < (128 / TBITS); i++, j += 2) {                       \
+        const uint##TBITS##_t a = s390_vec_read_element##BITS(v2, j);          \
+        const uint##TBITS##_t b = s390_vec_read_element##BITS(v3, j);          \
+                                                                               \
+        s390_vec_write_element##TBITS(v1, i, a * b);                           \
+    }                                                                          \
+}
+DEF_VMLO(8, 16)
+DEF_VMLO(16, 32)
+DEF_VMLO(32, 64)
-- 
2.20.1