tcg-x86_64: Special-case all 32-bit AND operands.

This avoids an unnecessary REX.W prefix when dealing with AND operands that fit into a 32-bit quantity. The most common change actually seen is movz[wb]q -> movz[wb]l.

Similarly, avoid REXW in ext{8,16}u_i64 tcg opcodes.

Signed-off-by Richard Henderson <[email protected]>

---
 tcg/x86_64/tcg-target.c |   26 ++++++++------------------
 1 files changed, 8 insertions(+), 18 deletions(-)

tcg/x86_64/tcg-target.c +0 -5

index 2339091..f584c94 100644
@@ -426,24 +426,18 @@ static inline void tgen_arithi64(TCGContext *s, int c, int r0, int64_t val)
     } else if ((c == ARITH_ADD && val == -1) || (c == ARITH_SUB && val == 1)) {
         /* dec */
         tcg_out_modrm(s, 0xff | P_REXW, 1, r0);
-    } else if (val == (int8_t)val) {
-        tcg_out_modrm(s, 0x83 | P_REXW, c, r0);
-        tcg_out8(s, val);
-    } else if (c == ARITH_AND && val == 0xffu) {
-        /* movzbl */

tcg/x86_64/tcg-target.c +4 -4

+    } else if (val == (int8_t)val) {
+        tcg_out_modrm(s, 0x83 | P_REXW, c, r0);
+        tcg_out8(s, val);
     } else if (val == (int32_t)val) {
         tcg_out_modrm(s, 0x81 | P_REXW, c, r0);
         tcg_out32(s, val);
-    } else if (c == ARITH_AND && val == (uint32_t)val) {
-        tcg_out_modrm(s, 0x81, c, r0);
-        tcg_out32(s, val);
     } else {
         tcg_abort();
     }

@@ -1182,16 +1176,12 @@ static inline void tcg_out_op(TCGContext *s, int opc, const TCGArg *args,
         tcg_out_modrm(s, 0x63 | P_REXW, args[0], args[1]);
         break;
     case INDEX_op_ext8u_i32:
+    case INDEX_op_ext8u_i64:
         tcg_out_modrm(s, 0xb6 | P_EXT | P_REXB, args[0], args[1]);
         break;
     case INDEX_op_ext16u_i32:
-        tcg_out_modrm(s, 0xb7 | P_EXT, args[0], args[1]);

Quoted 30 lines · Richard Henderson

This avoids an unnecessary REX.W prefix when dealing with AND operands that fit into a 32-bit quantity. The most common change actually seen is movz[wb]q -> movz[wb]l.

Similarly, avoid REXW in ext{8,16}u_i64 tcg opcodes.

Signed-off-by Richard Henderson<[email protected]>

---
  tcg/x86_64/tcg-target.c |   26 ++++++++------------------
  1 files changed, 8 insertions(+), 18 deletions(-)

tcg/x86_64/tcg-target.c +0 -9

index 2339091..f584c94 100644
@@ -426,24 +426,18 @@ static inline void tgen_arithi64(TCGContext *s, int c, int r0, int64_t val)
      } else if ((c == ARITH_ADD&&  val == -1) || (c == ARITH_SUB&&  val == 1)) {
          /* dec */
          tcg_out_modrm(s, 0xff | P_REXW, 1, r0);
-    } else if (val == (int8_t)val) {
-        tcg_out_modrm(s, 0x83 | P_REXW, c, r0);
-        tcg_out8(s, val);
-    } else if (c == ARITH_AND&&  val == 0xffu) {
-        /* movzbl */
-        tcg_out_modrm(s, 0xb6 | P_EXT | P_REXW, r0, r0);
-    } else if (c == ARITH_AND&&  val == 0xffffu) {
-        /* movzwl */
-        tcg_out_modrm(s, 0xb7 | P_EXT | P_REXW, r0, r0);
      } else if (c == ARITH_AND&&  val == 0xffffffffu) {
          /* 32-bit mov zero extends */

tcg/x86_64/tcg-target.c static inline void tgen_arithi64(TCGContext *s, int c, int r0, int64_t val) · line 434

Quoted 4 lines

tcg/x86_64/tcg-target.c +3 -0

          tcg_out_modrm(s, 0x8b, r0, r0);
+    } else if (c == ARITH_AND&&  (uint64_t)val<= 0xffffffffu) {
+        /* AND with no high bits set can use a 32-bit operation.  */
+        tgen_arithi32(s, c, r0, val);

Do we really want to call tgen_arithi32() here, that will redo part of the above tests again? It might be better to simply remove the REX.W prefix above instead.

Quoted 31 lines · Aurelien Jarno

Quoted 30 lines · Richard Henderson

This avoids an unnecessary REX.W prefix when dealing with AND operands that fit into a 32-bit quantity. The most common change actually seen is movz[wb]q -> movz[wb]l.

Similarly, avoid REXW in ext{8,16}u_i64 tcg opcodes.

Signed-off-by Richard Henderson<[email protected]>

---
 tcg/x86_64/tcg-target.c |   26 ++++++++------------------
 1 files changed, 8 insertions(+), 18 deletions(-)

tcg/x86_64/tcg-target.c +0 -9

index 2339091..f584c94 100644
@@ -426,24 +426,18 @@ static inline void tgen_arithi64(TCGContext *s, int c, int r0, int64_t val)
     } else if ((c == ARITH_ADD&&  val == -1) || (c == ARITH_SUB&&  val == 1)) {
         /* dec */
         tcg_out_modrm(s, 0xff | P_REXW, 1, r0);
-    } else if (val == (int8_t)val) {
-        tcg_out_modrm(s, 0x83 | P_REXW, c, r0);
-        tcg_out8(s, val);
-    } else if (c == ARITH_AND&&  val == 0xffu) {
-        /* movzbl */
-        tcg_out_modrm(s, 0xb6 | P_EXT | P_REXW, r0, r0);
-    } else if (c == ARITH_AND&&  val == 0xffffu) {
-        /* movzwl */
-        tcg_out_modrm(s, 0xb7 | P_EXT | P_REXW, r0, r0);
     } else if (c == ARITH_AND&&  val == 0xffffffffu) {
         /* 32-bit mov zero extends */

Quoted 8 lines

tcg/x86_64/tcg-target.c static inline void tgen_arithi64(TCGContext *s, int c, int r0, int64_t val) · line 434

Quoted 4 lines

tcg/x86_64/tcg-target.c +3 -0

         tcg_out_modrm(s, 0x8b, r0, r0);
+    } else if (c == ARITH_AND&&  (uint64_t)val<= 0xffffffffu) {
+        /* AND with no high bits set can use a 32-bit operation.  */
+        tgen_arithi32(s, c, r0, val);

Do we really want to call tgen_arithi32() here, that will redo part of the above tests again? It might be better to simply remove the REX.W prefix above instead.

Pardon? Do you mean the inc/dec tests? Otherwise I don't see what "above tests again" you're talking about.

I am looking to handle more than 0xff, 0xffff with the new test in gen_arithi64 -- 0x1234 is an appropriate mask to shorten to 32-bit AND as well. I have no idea if that answers your question.