[qemu-s390x] [PATCH v3 20/32] s390x/tcg: Implement VECTOR PERMUTE

[David Hildenbrand]

Take care of overlying inputs and outputs by using a temporary vector.

Reviewed-by: Richard Henderson <address@hidden>
Signed-off-by: David Hildenbrand <address@hidden>
---
 target/s390x/helper.h           |  1 +
 target/s390x/insn-data.def      |  1 +
 target/s390x/translate_vx.inc.c | 12 ++++++++++++
 target/s390x/vec_helper.c       | 20 ++++++++++++++++++++
 4 files changed, 34 insertions(+)

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 315495f49f..577edb384f 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -141,6 +141,7 @@ DEF_HELPER_FLAGS_4(gvec_vpkls64, TCG_CALL_NO_RWG, void, 
ptr, cptr, cptr, i32)
 DEF_HELPER_5(gvec_vpkls_cc16, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vpkls_cc32, void, ptr, cptr, cptr, env, i32)
 DEF_HELPER_5(gvec_vpkls_cc64, void, ptr, cptr, cptr, env, i32)
+DEF_HELPER_FLAGS_5(gvec_vperm, TCG_CALL_NO_RWG, void, ptr, cptr, 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 39cd6f27c1..5f77462bb1 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1020,6 +1020,7 @@
     F(0xe797, VPKS,    VRR_b, V,   0, 0, 0, 0, vpk, 0, IF_VEC)
 /* VECTOR PACK LOGICAL SATURATE */
     F(0xe795, VPKLS,   VRR_b, V,   0, 0, 0, 0, vpk, 0, IF_VEC)
+    F(0xe78c, VPERM,   VRR_e, V,   0, 0, 0, 0, vperm, 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 7ae38f71f7..d8cf4360cf 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -141,6 +141,10 @@ static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t 
reg, TCGv_i64 enr,
 #define gen_gvec_3_ptr(v1, v2, v3, ptr, data, fn) \
     tcg_gen_gvec_3_ptr(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                        vec_full_reg_offset(v3), ptr, 16, 16, data, fn)
+#define gen_gvec_4_ool(v1, v2, v3, v4, data, fn) \
+    tcg_gen_gvec_4_ool(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
+                       vec_full_reg_offset(v3), vec_full_reg_offset(v4), \
+                       16, 16, data, fn)
 #define gen_gvec_dup_i64(es, v1, c) \
     tcg_gen_gvec_dup_i64(es, vec_full_reg_offset(v1), 16, 16, c)
 #define gen_gvec_mov(v1, v2) \
@@ -663,3 +667,11 @@ static DisasJumpType op_vpk(DisasContext *s, DisasOps *o)
     }
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vperm(DisasContext *s, DisasOps *o)
+{
+    gen_gvec_4_ool(get_field(s->fields, v1), get_field(s->fields, v2),
+                   get_field(s->fields, v3), get_field(s->fields, v4),
+                   0, gen_helper_gvec_vperm);
+    return DISAS_NEXT;
+}
diff --git a/target/s390x/vec_helper.c b/target/s390x/vec_helper.c
index 7f680201b5..021695b38c 100644
--- a/target/s390x/vec_helper.c
+++ b/target/s390x/vec_helper.c
@@ -147,3 +147,23 @@ void HELPER(gvec_vpkls_cc##BITS)(void *v1, const void *v2, 
const void *v3,     \
 DEF_VPKLS(64, 32)
 DEF_VPKLS(32, 16)
 DEF_VPKLS(16, 8)
+
+void HELPER(gvec_vperm)(void *v1, const void *v2, const void *v3,
+                        const void *v4, uint32_t desc)
+{
+    S390Vector tmp;
+    int i;
+
+    for (i = 0; i < 16; i++) {
+        const uint8_t selector = s390_vec_read_element8(v4, i) & 0x1f;
+        uint8_t byte;
+
+        if (selector < 16) {
+            byte = s390_vec_read_element8(v2, selector);
+        } else {
+            byte = s390_vec_read_element8(v3, selector - 16);
+        }
+        s390_vec_write_element8(&tmp, i, byte);
+    }
+    *(S390Vector *)v1 = tmp;
+}
-- 
2.17.2