[i386] : Use pinsrd to move DImode value to xmm reg

Message ID CAFULd4b2CEJnmr8gX6D2zEWTFYURzS3nVUGiZYFKAMNXQ91dFQ@mail.gmail.com
State New
Headers show
Series
  • [i386] : Use pinsrd to move DImode value to xmm reg
Related show

Commit Message

Uros Bizjak May 11, 2019, 8:23 a.m.
We can use pinsrd when moving DImode value from integer register pair
to xmm reg for 32bit SSE4.1 targets.

2019-05-11  UroŇ° Bizjak  <ubizjak@gmail.com>

    * config/i386/i386.md (floatdi<X87MODEF:mode>2_i387_with_xmm):
    Use pinsrd for TARGET_SSE4_1.
    * config/i386/sse.md (movdi_to_sse): Ditto.

Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.

Committed to mainline SVN.

Uros.

Patch

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 46277f158bb3..1886715fe77e 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -5117,12 +5117,12 @@ 
 })
 
 (define_insn_and_split "floatdi<X87MODEF:mode>2_i387_with_xmm"
-  [(set (match_operand:X87MODEF 0 "register_operand" "=f")
+  [(set (match_operand:X87MODEF 0 "register_operand" "=f,f")
 	(float:X87MODEF
-	  (match_operand:DI 1 "register_operand" "r")))
-   (clobber (match_scratch:V4SI 3 "=x"))
-   (clobber (match_scratch:V4SI 4 "=x"))
-   (clobber (match_operand:DI 2 "memory_operand" "=m"))]
+	  (match_operand:DI 1 "register_operand" "r,r")))
+   (clobber (match_operand:DI 2 "memory_operand" "=m,m"))
+   (clobber (match_scratch:V4SI 3 "=x,x"))
+   (clobber (match_scratch:V4SI 4 "=X,x"))]
   "!TARGET_64BIT && TARGET_INTER_UNIT_MOVES_TO_VEC
    && TARGET_80387 && X87_ENABLE_FLOAT (<X87MODEF:MODE>mode, DImode)
    && TARGET_SSE2 && optimize_function_for_speed_p (cfun)"
@@ -5135,14 +5135,21 @@ 
      Assemble the 64-bit DImode value in an xmm register.  */
   emit_insn (gen_sse2_loadld (operands[3], CONST0_RTX (V4SImode),
 			      gen_lowpart (SImode, operands[1])));
-  emit_insn (gen_sse2_loadld (operands[4], CONST0_RTX (V4SImode),
-			      gen_highpart (SImode, operands[1])));
-  emit_insn (gen_vec_interleave_lowv4si (operands[3], operands[3],
-					 operands[4]));
-
+  if (TARGET_SSE4_1)
+    emit_insn (gen_sse4_1_pinsrd (operands[3], operands[3],
+				  gen_highpart (SImode, operands[1]),
+				  GEN_INT (2)));
+  else
+    {
+      emit_insn (gen_sse2_loadld (operands[4], CONST0_RTX (V4SImode),
+				  gen_highpart (SImode, operands[1])));
+      emit_insn (gen_vec_interleave_lowv4si (operands[3], operands[3],
+					     operands[4]));
+    }
   operands[3] = gen_lowpart (DImode, operands[3]);
 }
-  [(set_attr "type" "multi")
+  [(set_attr "isa" "sse4,*")
+   (set_attr "type" "multi")
    (set_attr "mode" "<X87MODEF:MODE>")
    (set_attr "unit" "i387")
    (set_attr "fp_int_src" "true")])
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 6b8298d957ed..a223a58ed540 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -1300,10 +1300,10 @@ 
 ;; from there.
 
 (define_insn_and_split "movdi_to_sse"
-  [(set (match_operand:V4SI 0 "register_operand" "=?x,x")
-	(unspec:V4SI [(match_operand:DI 1 "nonimmediate_operand" "r,m")]
+  [(set (match_operand:V4SI 0 "register_operand" "=x,x,?x")
+	(unspec:V4SI [(match_operand:DI 1 "nonimmediate_operand" "r,m,r")]
 		     UNSPEC_MOVDI_TO_SSE))
-     (clobber (match_scratch:V4SI 2 "=&x,X"))]
+     (clobber (match_scratch:V4SI 2 "=X,X,&x"))]
   "!TARGET_64BIT && TARGET_SSE2 && TARGET_INTER_UNIT_MOVES_TO_VEC"
   "#"
   "&& reload_completed"
@@ -1315,18 +1315,26 @@ 
 	 Assemble the 64-bit DImode value in an xmm register.  */
       emit_insn (gen_sse2_loadld (operands[0], CONST0_RTX (V4SImode),
 				  gen_lowpart (SImode, operands[1])));
-      emit_insn (gen_sse2_loadld (operands[2], CONST0_RTX (V4SImode),
-				  gen_highpart (SImode, operands[1])));
-      emit_insn (gen_vec_interleave_lowv4si (operands[0], operands[0],
-					     operands[2]));
-   }
+      if (TARGET_SSE4_1)
+        emit_insn (gen_sse4_1_pinsrd (operands[0], operands[0],
+				      gen_highpart (SImode, operands[1]),
+				      GEN_INT (2)));
+      else
+	{
+	  emit_insn (gen_sse2_loadld (operands[2], CONST0_RTX (V4SImode),
+				      gen_highpart (SImode, operands[1])));
+	  emit_insn (gen_vec_interleave_lowv4si (operands[0], operands[0],
+						 operands[2]));
+	}
+  }
  else if (memory_operand (operands[1], DImode))
    emit_insn (gen_vec_concatv2di (gen_lowpart (V2DImode, operands[0]),
 				  operands[1], const0_rtx));
  else
    gcc_unreachable ();
  DONE;
-})
+}
+  [(set_attr "isa" "sse4,*,*")])
 
 (define_split
   [(set (match_operand:V4SF 0 "register_operand")