Take care of reading/indicating the 32-bit elements.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/helper.h           |  2 ++
 target/s390x/insn-data.def      |  2 ++
 target/s390x/translate_vx.inc.c | 19 +++++++++++++++++
 target/s390x/vec_fpu_helper.c   | 36 +++++++++++++++++++++++++++++++++
 4 files changed, 59 insertions(+)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 10a9cb39b6..cb25141ffe 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -278,6 +278,8 @@ DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_5(gvec_vfd64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
 DEF_HELPER_FLAGS_4(gvec_vfi64s, 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_vfll32s, TCG_CALL_NO_WG, void, ptr, 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 f77aa41253..5afdb36aec 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1230,6 +1230,8 @@
     F(0xe7e5, VFD,     VRR_c, V,   0, 0, 0, 0, vfa, 0, IF_VEC)
 /* VECTOR LOAD FP INTEGER */
     F(0xe7c7, VFI,     VRR_a, V,   0, 0, 0, 0, vcdg, 0, IF_VEC)
+/* VECTOR LOAD LENGTHENED */
+    F(0xe7c4, VFLL,    VRR_a, V,   0, 0, 0, 0, vfll, 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 59d8b971c0..a25985e5c9 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -2679,3 +2679,22 @@ static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o)
                    deposit32(m4, 4, 4, erm), fn);
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vfll(DisasContext *s, DisasOps *o)
+{
+    const uint8_t fpf = get_field(s->fields, m3);
+    const uint8_t m4 = get_field(s->fields, m4);
+    gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vfll32;
+
+    if (fpf != FPF_SHORT || extract32(m4, 0, 3)) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    if (extract32(m4, 3, 1)) {
+        fn = gen_helper_gvec_vfll32s;
+    }
+    gen_gvec_2_ptr(get_field(s->fields, v1), get_field(s->fields, v2), cpu_env,
+                   0, fn);
+    return DISAS_NEXT;
+}
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index 63ba4cf548..f8919beed5 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -412,3 +412,39 @@ void HELPER(gvec_vfi64s)(void *v1, const void *v2, CPUS390XState *env,
 
     vop64_2(v1, v2, env, true, XxC, erm, vfi64, GETPC());
 }
+
+static void vfll32(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
+                   bool s, uintptr_t retaddr)
+{
+    uint8_t vxc, vec_exc = 0;
+    S390Vector tmp = {};
+    int i;
+
+    for (i = 0; i < 2; i++) {
+        /* load from even element */
+        const float32 a = make_float32(s390_vec_read_element32(v2, i * 2));
+        const uint64_t ret = float64_val(float32_to_float64(a,
+                                                            &env->fpu_status));
+
+        s390_vec_write_element64(&tmp, i, ret);
+        /* indicate the source element */
+        vxc = check_ieee_exc(env, i * 2, false, &vec_exc);
+        if (s || vxc) {
+            break;
+        }
+    }
+    handle_ieee_exc(env, vxc, vec_exc, retaddr);
+    *v1 = tmp;
+}
+
+void HELPER(gvec_vfll32)(void *v1, const void *v2, CPUS390XState *env,
+                         uint32_t desc)
+{
+    vfll32(v1, v2, env, false, GETPC());
+}
+
+void HELPER(gvec_vfll32s)(void *v1, const void *v2, CPUS390XState *env,
+                          uint32_t desc)
+{
+    vfll32(v1, v2, env, true, GETPC());
+}
-- 
2.20.1

On 5/31/19 5:44 AM, David Hildenbrand wrote:
> +    for (i = 0; i < 2; i++) {
> +        /* load from even element */
> +        const float32 a = make_float32(s390_vec_read_element32(v2, i * 2));

I suppose.

You could also reuse vop64_2 with

static uint64_t vfll(uint64_t a, float_status *s)
{
    /* Even float32 are stored in the high half of each doubleword.  */
    return float32_to_float64(a >> 32, s);
}


r~

On 31.05.19 19:33, Richard Henderson wrote:
> On 5/31/19 5:44 AM, David Hildenbrand wrote:
>> +    for (i = 0; i < 2; i++) {
>> +        /* load from even element */
>> +        const float32 a = make_float32(s390_vec_read_element32(v2, i * 2));
> 
> I suppose.
> 
> You could also reuse vop64_2 with
> 
> static uint64_t vfll(uint64_t a, float_status *s)
> {
>     /* Even float32 are stored in the high half of each doubleword.  */
>     return float32_to_float64(a >> 32, s);
> }
> 

Then, I wouldn't be able to indicate the correct element index on
exceptions via the vex (has to be the 32-bit index).

Thanks!

> 
> r~
> 


-- 

Thanks,

David / dhildenb

On 5/31/19 12:35 PM, David Hildenbrand wrote:
> On 31.05.19 19:33, Richard Henderson wrote:
>> On 5/31/19 5:44 AM, David Hildenbrand wrote:
>>> +    for (i = 0; i < 2; i++) {
>>> +        /* load from even element */
>>> +        const float32 a = make_float32(s390_vec_read_element32(v2, i * 2));
>>
>> I suppose.
>>
>> You could also reuse vop64_2 with
>>
>> static uint64_t vfll(uint64_t a, float_status *s)
>> {
>>     /* Even float32 are stored in the high half of each doubleword.  */
>>     return float32_to_float64(a >> 32, s);
>> }
>>
> 
> Then, I wouldn't be able to indicate the correct element index on
> exceptions via the vex (has to be the 32-bit index).

Ah, tricky.  Missed that detail.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>


r~

On 31.05.19 19:36, Richard Henderson wrote:
> On 5/31/19 12:35 PM, David Hildenbrand wrote:
>> On 31.05.19 19:33, Richard Henderson wrote:
>>> On 5/31/19 5:44 AM, David Hildenbrand wrote:
>>>> +    for (i = 0; i < 2; i++) {
>>>> +        /* load from even element */
>>>> +        const float32 a = make_float32(s390_vec_read_element32(v2, i * 2));
>>>
>>> I suppose.
>>>
>>> You could also reuse vop64_2 with
>>>
>>> static uint64_t vfll(uint64_t a, float_status *s)
>>> {
>>>     /* Even float32 are stored in the high half of each doubleword.  */
>>>     return float32_to_float64(a >> 32, s);
>>> }
>>>
>>
>> Then, I wouldn't be able to indicate the correct element index on
>> exceptions via the vex (has to be the 32-bit index).

I guess we can later handle all type conversions (lower -> bigger) via
this single function (passing the source size). Then we only need a
second function for the other direction.

Thanks!

> 
> Ah, tricky.  Missed that detail.
> 
> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
> 
> 
> r~
> 


-- 

Thanks,

David / dhildenb