s390x/tcg: Implement 32/128 bit for VECTOR (LOAD FP INTEGER|FP SQUARE ROOT)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210608092337.12221-15-david@redhat.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>

3 files changed, 109 insertions, 15 deletions

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 2d5e382e61..28797a6ccc 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -265,7 +265,9 @@ DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfi32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
+DEF_HELPER_FLAGS_4(gvec_vfi128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vflr64, 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)
@@ -273,7 +275,9 @@ 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_vfma64, 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_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)
 DEF_HELPER_FLAGS_5(gvec_vfs32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfs128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
diff --git a/target/s390x/translate_vx.c.inc b/target/s390x/translate_vx.c.inc
index 0fbd914b40..6241279e68 100644
--- a/target/s390x/translate_vx.c.inc
+++ b/target/s390x/translate_vx.c.inc
@@ -2654,35 +2654,63 @@ static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o)
     const uint8_t fpf = get_field(s, m3);
     const uint8_t m4 = get_field(s, m4);
     const uint8_t erm = get_field(s, m5);
-    gen_helper_gvec_2_ptr *fn;
+    gen_helper_gvec_2_ptr *fn = NULL;
 
-    if (fpf != FPF_LONG || extract32(m4, 0, 2) || erm > 7 || erm == 2) {
-        gen_program_exception(s, PGM_SPECIFICATION);
-        return DISAS_NORETURN;
-    }
 
     switch (s->fields.op2) {
     case 0xc3:
-        fn = gen_helper_gvec_vcdg64;
+        if (fpf == FPF_LONG) {
+            fn = gen_helper_gvec_vcdg64;
+        }
         break;
     case 0xc1:
-        fn = gen_helper_gvec_vcdlg64;
+        if (fpf == FPF_LONG) {
+            fn = gen_helper_gvec_vcdlg64;
+        }
         break;
     case 0xc2:
-        fn = gen_helper_gvec_vcgd64;
+        if (fpf == FPF_LONG) {
+            fn = gen_helper_gvec_vcgd64;
+        }
         break;
     case 0xc0:
-        fn = gen_helper_gvec_vclgd64;
+        if (fpf == FPF_LONG) {
+            fn = gen_helper_gvec_vclgd64;
+        }
         break;
     case 0xc7:
-        fn = gen_helper_gvec_vfi64;
+        switch (fpf) {
+        case FPF_SHORT:
+            if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+                fn = gen_helper_gvec_vfi32;
+            }
+            break;
+        case FPF_LONG:
+            fn = gen_helper_gvec_vfi64;
+            break;
+        case FPF_EXT:
+            if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+                fn = gen_helper_gvec_vfi128;
+            }
+            break;
+        default:
+            break;
+        }
         break;
     case 0xc5:
-        fn = gen_helper_gvec_vflr64;
+        if (fpf == FPF_LONG) {
+            fn = gen_helper_gvec_vflr64;
+        }
         break;
     default:
         g_assert_not_reached();
     }
+
+    if (!fn || extract32(m4, 0, 2) || erm > 7 || erm == 2) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
     gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env,
                    deposit32(m4, 4, 4, erm), fn);
     return DISAS_NEXT;
@@ -2780,14 +2808,32 @@ static DisasJumpType op_vfsq(DisasContext *s, DisasOps *o)
 {
     const uint8_t fpf = get_field(s, m3);
     const uint8_t m4 = get_field(s, m4);
+    gen_helper_gvec_2_ptr *fn = NULL;
+
+    switch (fpf) {
+    case FPF_SHORT:
+        if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+            fn = gen_helper_gvec_vfsq32;
+        }
+        break;
+    case FPF_LONG:
+        fn = gen_helper_gvec_vfsq64;
+        break;
+    case FPF_EXT:
+        if (s390_has_feat(S390_FEAT_VECTOR_ENH)) {
+            fn = gen_helper_gvec_vfsq128;
+        }
+        break;
+    default:
+        break;
+    }
 
-    if (fpf != FPF_LONG || extract32(m4, 0, 3)) {
+    if (!fn || extract32(m4, 0, 3)) {
         gen_program_exception(s, PGM_SPECIFICATION);
         return DISAS_NORETURN;
     }
 
-    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, m4,
-                   gen_helper_gvec_vfsq64);
+    gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, m4, fn);
     return DISAS_NEXT;
 }
 
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index 3484c161ba..1df8f3d5a3 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -110,6 +110,30 @@ static void s390_vec_write_float128(S390Vector *v, float128 data)
     s390_vec_write_element64(v, 1, data.low);
 }
 
+typedef float32 (*vop32_2_fn)(float32 a, float_status *s);
+static void vop32_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
+                    bool s, bool XxC, uint8_t erm, vop32_2_fn fn,
+                    uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int i, old_mode;
+
+    old_mode = s390_swap_bfp_rounding_mode(env, erm);
+    for (i = 0; i < 4; i++) {
+        const float32 a = s390_vec_read_float32(v2, i);
+
+        s390_vec_write_float32(&tmp, i, fn(a, &env->fpu_status));
+        vxc = check_ieee_exc(env, i, XxC, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+    s390_restore_bfp_rounding_mode(env, old_mode);
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
 typedef float64 (*vop64_2_fn)(float64 a, float_status *s);
 static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
                     bool s, bool XxC, uint8_t erm, vop64_2_fn fn,
@@ -134,6 +158,24 @@ static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
     *v1 = tmp;
 }
 
+typedef float128 (*vop128_2_fn)(float128 a, float_status *s);
+static void vop128_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
+                    bool s, bool XxC, uint8_t erm, vop128_2_fn fn,
+                    uintptr_t retaddr)
+{
+    const float128 a = s390_vec_read_float128(v2);
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int old_mode;
+
+    old_mode = s390_swap_bfp_rounding_mode(env, erm);
+    s390_vec_write_float128(&tmp, fn(a, &env->fpu_status));
+    vxc = check_ieee_exc(env, 0, XxC, &vec_exc);
+    s390_restore_bfp_rounding_mode(env, old_mode);
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
 static float64 vcdg64(float64 a, float_status *s)
 {
     return int64_to_float64(a, s);
@@ -173,7 +215,9 @@ void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, CPUS390XState *env,   \
 DEF_GVEC_VOP2_FN(NAME, NAME##64, 64)
 
 #define DEF_GVEC_VOP2(NAME, OP)                                                \
-DEF_GVEC_VOP2_FN(NAME, float64_##OP, 64)
+DEF_GVEC_VOP2_FN(NAME, float32_##OP, 32)                                       \
+DEF_GVEC_VOP2_FN(NAME, float64_##OP, 64)                                       \
+DEF_GVEC_VOP2_FN(NAME, float128_##OP, 128)
 
 DEF_GVEC_VOP2_64(vcdg)
 DEF_GVEC_VOP2_64(vcdlg)