tcg/i386: Implement tcg_out_dupm_vec

At the same time, improve tcg_out_dupi_vec wrt broadcast
from the constant pool.

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

1 files changed, 43 insertions, 14 deletions

diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c
index f04933bc19..f4bd00e24f 100644
--- a/tcg/i386/tcg-target.inc.c
+++ b/tcg/i386/tcg-target.inc.c
@@ -358,7 +358,6 @@ static inline int tcg_target_const_match(tcg_target_long val, TCGType type,
 #define OPC_MOVBE_MyGy  (0xf1 | P_EXT38)
 #define OPC_MOVD_VyEy   (0x6e | P_EXT | P_DATA16)
 #define OPC_MOVD_EyVy   (0x7e | P_EXT | P_DATA16)
-#define OPC_MOVDDUP     (0x12 | P_EXT | P_SIMDF2)
 #define OPC_MOVDQA_VxWx (0x6f | P_EXT | P_DATA16)
 #define OPC_MOVDQA_WxVx (0x7f | P_EXT | P_DATA16)
 #define OPC_MOVDQU_VxWx (0x6f | P_EXT | P_SIMDF3)
@@ -458,6 +457,10 @@ static inline int tcg_target_const_match(tcg_target_long val, TCGType type,
 #define OPC_UD2         (0x0b | P_EXT)
 #define OPC_VPBLENDD    (0x02 | P_EXT3A | P_DATA16)
 #define OPC_VPBLENDVB   (0x4c | P_EXT3A | P_DATA16)
+#define OPC_VPINSRB     (0x20 | P_EXT3A | P_DATA16)
+#define OPC_VPINSRW     (0xc4 | P_EXT | P_DATA16)
+#define OPC_VBROADCASTSS (0x18 | P_EXT38 | P_DATA16)
+#define OPC_VBROADCASTSD (0x19 | P_EXT38 | P_DATA16)
 #define OPC_VPBROADCASTB (0x78 | P_EXT38 | P_DATA16)
 #define OPC_VPBROADCASTW (0x79 | P_EXT38 | P_DATA16)
 #define OPC_VPBROADCASTD (0x58 | P_EXT38 | P_DATA16)
@@ -855,16 +858,17 @@ static bool tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg)
     return true;
 }
 
+static const int avx2_dup_insn[4] = {
+    OPC_VPBROADCASTB, OPC_VPBROADCASTW,
+    OPC_VPBROADCASTD, OPC_VPBROADCASTQ,
+};
+
 static bool tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
                             TCGReg r, TCGReg a)
 {
     if (have_avx2) {
-        static const int dup_insn[4] = {
-            OPC_VPBROADCASTB, OPC_VPBROADCASTW,
-            OPC_VPBROADCASTD, OPC_VPBROADCASTQ,
-        };
         int vex_l = (type == TCG_TYPE_V256 ? P_VEXL : 0);
-        tcg_out_vex_modrm(s, dup_insn[vece] + vex_l, r, 0, a);
+        tcg_out_vex_modrm(s, avx2_dup_insn[vece] + vex_l, r, 0, a);
     } else {
         switch (vece) {
         case MO_8:
@@ -894,10 +898,35 @@ static bool tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
 static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece,
                              TCGReg r, TCGReg base, intptr_t offset)
 {
-    return false;
+    if (have_avx2) {
+        int vex_l = (type == TCG_TYPE_V256 ? P_VEXL : 0);
+        tcg_out_vex_modrm_offset(s, avx2_dup_insn[vece] + vex_l,
+                                 r, 0, base, offset);
+    } else {
+        switch (vece) {
+        case MO_64:
+            tcg_out_vex_modrm_offset(s, OPC_VBROADCASTSD, r, 0, base, offset);
+            break;
+        case MO_32:
+            tcg_out_vex_modrm_offset(s, OPC_VBROADCASTSS, r, 0, base, offset);
+            break;
+        case MO_16:
+            tcg_out_vex_modrm_offset(s, OPC_VPINSRW, r, r, base, offset);
+            tcg_out8(s, 0); /* imm8 */
+            tcg_out_dup_vec(s, type, vece, r, r);
+            break;
+        case MO_8:
+            tcg_out_vex_modrm_offset(s, OPC_VPINSRB, r, r, base, offset);
+            tcg_out8(s, 0); /* imm8 */
+            tcg_out_dup_vec(s, type, vece, r, r);
+            break;
+        default:
+            g_assert_not_reached();
+        }
+    }
+    return true;
 }
 
-
 static void tcg_out_dupi_vec(TCGContext *s, TCGType type,
                              TCGReg ret, tcg_target_long arg)
 {
@@ -918,16 +947,16 @@ static void tcg_out_dupi_vec(TCGContext *s, TCGType type,
         } else if (have_avx2) {
             tcg_out_vex_modrm_pool(s, OPC_VPBROADCASTQ + vex_l, ret);
         } else {
-            tcg_out_vex_modrm_pool(s, OPC_MOVDDUP, ret);
+            tcg_out_vex_modrm_pool(s, OPC_VBROADCASTSD, ret);
         }
         new_pool_label(s, arg, R_386_PC32, s->code_ptr - 4, -4);
-    } else if (have_avx2) {
-        tcg_out_vex_modrm_pool(s, OPC_VPBROADCASTD + vex_l, ret);
-        new_pool_label(s, arg, R_386_32, s->code_ptr - 4, 0);
     } else {
-        tcg_out_vex_modrm_pool(s, OPC_MOVD_VyEy, ret);
+        if (have_avx2) {
+            tcg_out_vex_modrm_pool(s, OPC_VBROADCASTSD + vex_l, ret);
+        } else {
+            tcg_out_vex_modrm_pool(s, OPC_VBROADCASTSS, ret);
+        }
         new_pool_label(s, arg, R_386_32, s->code_ptr - 4, 0);
-        tcg_out_dup_vec(s, type, MO_32, ret, ret);
     }
 }