[PATCH v2 21/26] s390x/tcg: Implement 32/128 bit for 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/translate_vx.c.inc | 47 ++++++++++++++++++++++++++++-----
 target/s390x/vec_fpu_helper.c   | 44 +++++++++++++++++++++++++++++-
 3 files changed, 87 insertions(+), 8 deletions(-)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index bae73b9a56..2366756063 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -291,8 +291,12 @@ DEF_HELPER_FLAGS_4(gvec_vflr128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfm128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfma32, TCG_CALL_NO_WG, void, ptr, cptr, 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_vfma128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_6(gvec_vfms32, 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_vfms128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfsq128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
diff --git a/target/s390x/translate_vx.c.inc b/target/s390x/translate_vx.c.inc
index 765f75df9c..17d41b178f 100644
--- a/target/s390x/translate_vx.c.inc
+++ b/target/s390x/translate_vx.c.inc
@@ -2818,18 +2818,51 @@ static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
 {
     const uint8_t m5 = get_field(s, m5);
     const uint8_t fpf = get_field(s, m6);
-    gen_helper_gvec_4_ptr *fn;
+    gen_helper_gvec_4_ptr *fn = NULL;
 
-    if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
+    if (s->fields.op2 == 0x8f) {
+        switch (fpf) {
+        case FPF_SHORT:
+            if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+                fn = gen_helper_gvec_vfma32;
+            }
+            break;
+        case FPF_LONG:
+            fn = gen_helper_gvec_vfma64;
+            break;
+        case FPF_EXT:
+            if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+                fn = gen_helper_gvec_vfma128;
+            }
+            break;
+        default:
+            break;
+        }
+    } else {
+        switch (fpf) {
+        case FPF_SHORT:
+            if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+                fn = gen_helper_gvec_vfms32;
+            }
+            break;
+        case FPF_LONG:
+            fn = gen_helper_gvec_vfms64;
+            break;
+        case FPF_EXT:
+            if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+                fn = gen_helper_gvec_vfms128;
+            }
+            break;
+        default:
+            break;
+        }
+    }
+
+    if (!fn || extract32(m5, 0, 3)) {
         gen_program_exception(s, PGM_SPECIFICATION);
         return DISAS_NORETURN;
     }
 
-    if (s->fields.op2 == 0x8f) {
-        fn = gen_helper_gvec_vfma64;
-    } else {
-        fn = gen_helper_gvec_vfms64;
-    }
     gen_gvec_4_ptr(get_field(s, v1), get_field(s, v2),
                    get_field(s, v3), get_field(s, v4), cpu_env, m5, fn);
     return DISAS_NEXT;
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index 4c10734c4e..966b1dbf50 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -584,6 +584,30 @@ void HELPER(gvec_vflr128)(void *v1, const void *v2, CPUS390XState *env,
     s390_vec_write_float64(v1, 0, ret);
 }
 
+static void vfma32(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
+                   const S390Vector *v4, CPUS390XState *env, bool s, int flags,
+                   uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int i;
+
+    for (i = 0; i < 4; i++) {
+        const float32 a = s390_vec_read_float32(v2, i);
+        const float32 b = s390_vec_read_float32(v3, i);
+        const float32 c = s390_vec_read_float32(v4, i);
+        float32 ret = float32_muladd(a, b, c, flags, &env->fpu_status);
+
+        s390_vec_write_float32(&tmp, i, ret);
+        vxc = check_ieee_exc(env, i, false, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
 static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
                    const S390Vector *v4, CPUS390XState *env, bool s, int flags,
                    uintptr_t retaddr)
@@ -608,6 +632,22 @@ static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
     *v1 = tmp;
 }
 
+static void vfma128(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
+                    const S390Vector *v4, CPUS390XState *env, bool s, int flags,
+                    uintptr_t retaddr)
+{
+    const float128 a = s390_vec_read_float128(v2);
+    const float128 b = s390_vec_read_float128(v3);
+    const float128 c = s390_vec_read_float128(v4);
+    uint8_t vxc, vec_exc = 0;
+    float128 ret;
+
+    ret = float128_muladd(a, b, c, flags, &env->fpu_status);
+    vxc = check_ieee_exc(env, 0, false, &vec_exc);
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    s390_vec_write_float128(v1, ret);
+}
+
 #define DEF_GVEC_VFMA_B(NAME, FLAGS, BITS)                                     \
 void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, const void *v3,       \
                                const void *v4, CPUS390XState *env,             \
@@ -619,7 +659,9 @@ void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, const void *v3,       \
 }
 
 #define DEF_GVEC_VFMA(NAME, FLAGS)                                             \
-    DEF_GVEC_VFMA_B(NAME, FLAGS, 64)
+    DEF_GVEC_VFMA_B(NAME, FLAGS, 32)                                           \
+    DEF_GVEC_VFMA_B(NAME, FLAGS, 64)                                           \
+    DEF_GVEC_VFMA_B(NAME, FLAGS, 128)
 
 DEF_GVEC_VFMA(vfma, 0)
 DEF_GVEC_VFMA(vfms, float_muladd_negate_c)
-- 
2.31.1