[Qemu-devel] [PATCH v1 16/23] s390x/tcg: Implement VECTOR FP MULTIPLY AND (ADD|SUBTRACT)

[David Hildenbrand <david@redhat.com>]

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/helper.h           |  4 +++
 target/s390x/insn-data.def      |  4 +++
 target/s390x/translate_vx.inc.c | 23 +++++++++++++
 target/s390x/vec_fpu_helper.c   | 61 +++++++++++++++++++++++++++++++++
 4 files changed, 92 insertions(+)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 22e02a0178..bcaabb91a5 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -284,6 +284,10 @@ DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfma64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, 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 e56059ac34..e86ade9e44 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1236,6 +1236,10 @@
     F(0xe7c5, VFLR,    VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
 /* VECTOR FP MULTIPLY */
     F(0xe7e7, VFM,     VRR_c, V,   0, 0, 0, 0, vfa, 0, IF_VEC)
+/* VECTOR FP MULTIPLY AND ADD */
+    F(0xe78f, VFMA,    VRR_e, V,   0, 0, 0, 0, vfma, 0, IF_VEC)
+/* VECTOR FP MULTIPLY AND SUBTRACT */
+    F(0xe78e, VFMS,    VRR_e, V,   0, 0, 0, 0, vfma, 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 ae31a327cf..b624c7a8aa 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -2704,3 +2704,26 @@ static DisasJumpType op_vfll(DisasContext *s, DisasOps *o)
                    0, fn);
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
+{
+    const uint8_t m5 = get_field(s->fields, m5);
+    const uint8_t fpf = get_field(s->fields, m6);
+    const bool se = extract32(m5, 3, 1);
+    gen_helper_gvec_4_ptr *fn;
+
+    if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (s->fields->op2 == 0x8f) {
+        fn = se ? gen_helper_gvec_vfma64s : gen_helper_gvec_vfma64;
+    } else {
+        fn = se ? gen_helper_gvec_vfms64s : gen_helper_gvec_vfms64;
+    }
+    gen_gvec_4_ptr(get_field(s->fields, v1), get_field(s->fields, v2),
+                   get_field(s->fields, v3), get_field(s->fields, v4), cpu_env,
+                   0, fn);
+    return DISAS_NEXT;
+}
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index fd147cc055..a27b354214 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -125,6 +125,31 @@ static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
     *v1 = tmp;
 }
 
+typedef uint64_t (*vop64_4_fn)(uint64_t a, uint64_t b, uint64_t c,
+                               float_status *s);
+static void vop64_4(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
+                    const S390Vector *v4, CPUS390XState *env, bool s,
+                    vop64_4_fn fn, uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int i;
+
+    for (i = 0; i < 2; i++) {
+        const uint64_t a = s390_vec_read_element64(v2, i);
+        const uint64_t b = s390_vec_read_element64(v3, i);
+        const uint64_t c = s390_vec_read_element64(v4, i);
+
+        s390_vec_write_element64(&tmp, i, fn(a, b, c, &env->fpu_status));
+        vxc = check_ieee_exc(env, i, false, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
 static uint64_t vfa64(uint64_t a, uint64_t b, float_status *s)
 {
     return float64_val(float64_add(make_float64(a), make_float64(b), s));
@@ -508,3 +533,39 @@ void HELPER(gvec_vfm64s)(void *v1, const void *v2, const void *v3,
 {
     vop64_3(v1, v2, v3, env, true, vfm64, GETPC());
 }
+
+static uint64_t vfma64(uint64_t a, uint64_t b, uint64_t c, float_status *s)
+{
+    return float64_val(float64_muladd(make_float64(a), make_float64(b),
+                       make_float64(c), 0, s));
+}
+
+void HELPER(gvec_vfma64)(void *v1, const void *v2, const void *v3,
+                         const void *v4, CPUS390XState *env, uint32_t desc)
+{
+    vop64_4(v1, v2, v3, v4, env, false, vfma64, GETPC());
+}
+
+void HELPER(gvec_vfma64s)(void *v1, const void *v2, const void *v3,
+                         const void *v4, CPUS390XState *env, uint32_t desc)
+{
+    vop64_4(v1, v2, v3, v4, env, true, vfma64, GETPC());
+}
+
+static uint64_t vfms64(uint64_t a, uint64_t b, uint64_t c, float_status *s)
+{
+    return float64_val(float64_muladd(make_float64(a), make_float64(b),
+                       make_float64(c), float_muladd_negate_c, s));
+}
+
+void HELPER(gvec_vfms64)(void *v1, const void *v2, const void *v3,
+                         const void *v4, CPUS390XState *env, uint32_t desc)
+{
+    vop64_4(v1, v2, v3, v4, env, false, vfms64, GETPC());
+}
+
+void HELPER(gvec_vfms64s)(void *v1, const void *v2, const void *v3,
+                         const void *v4, CPUS390XState *env, uint32_t desc)
+{
+    vop64_4(v1, v2, v3, v4, env, true, vfms64, GETPC());
+}
-- 
2.20.1