AArch64 - Improve MOVI handling (5/5)

From-SVN: r199658

gcc/ChangeLog

 2013-06-04  Ian Bolton  <ian.bolton@arm.com>
 
+	* config/aarch64/aarch64.md (*mov<mode>_aarch64): Call
+	into function to generate MOVI instruction.
+	* config/aarch64/aarch64.c (aarch64_simd_container_mode):
+	New function.
+	(aarch64_preferred_simd_mode): Turn into wrapper.
+	(aarch64_output_scalar_simd_mov_immediate): New function.
+	* config/aarch64/aarch64-protos.h: Add prototype for above.
+
+2013-06-04  Ian Bolton  <ian.bolton@arm.com>
+
 	* config/aarch64/aarch64.c (simd_immediate_info): Remove
 	element_char member.
 	(sizetochar): Return signed char.

gcc/config/aarch64/aarch64-protos.h

@@ -149,6 +149,7 @@ bool aarch64_legitimate_pic_operand_p (rtx);
 bool aarch64_move_imm (HOST_WIDE_INT, enum machine_mode);
 bool aarch64_mov_operand_p (rtx, enum aarch64_symbol_context,
 			    enum machine_mode);
+char *aarch64_output_scalar_simd_mov_immediate (rtx, enum machine_mode);
 char *aarch64_output_simd_mov_immediate (rtx, enum machine_mode, unsigned);
 bool aarch64_pad_arg_upward (enum machine_mode, const_tree);
 bool aarch64_pad_reg_upward (enum machine_mode, const_tree, bool);

gcc/config/aarch64/aarch64.c

@@ -5989,32 +5989,57 @@ aarch64_vector_mode_supported_p (enum machine_mode mode)
   return false;
 }
 
-/* Return quad mode as the preferred SIMD mode.  */
+/* Return appropriate SIMD container
+   for MODE within a vector of WIDTH bits.  */
 static enum machine_mode
-aarch64_preferred_simd_mode (enum machine_mode mode)
+aarch64_simd_container_mode (enum machine_mode mode, unsigned width)
 {
+  gcc_assert (width == 64 || width == 128);
   if (TARGET_SIMD)
-    switch (mode)
-      {
-      case DFmode:
-        return V2DFmode;
-      case SFmode:
-        return V4SFmode;
-      case SImode:
-        return V4SImode;
-      case HImode:
-        return V8HImode;
-      case QImode:
-        return V16QImode;
-      case DImode:
-          return V2DImode;
-        break;
-
-      default:;
-      }
+    {
+      if (width == 128)
+	switch (mode)
+	  {
+	  case DFmode:
+	    return V2DFmode;
+	  case SFmode:
+	    return V4SFmode;
+	  case SImode:
+	    return V4SImode;
+	  case HImode:
+	    return V8HImode;
+	  case QImode:
+	    return V16QImode;
+	  case DImode:
+	    return V2DImode;
+	  default:
+	    break;
+	  }
+      else
+	switch (mode)
+	  {
+	  case SFmode:
+	    return V2SFmode;
+	  case SImode:
+	    return V2SImode;
+	  case HImode:
+	    return V4HImode;
+	  case QImode:
+	    return V8QImode;
+	  default:
+	    break;
+	  }
+    }
   return word_mode;
 }
 
+/* Return 128-bit container as the preferred SIMD mode for MODE.  */
+static enum machine_mode
+aarch64_preferred_simd_mode (enum machine_mode mode)
+{
+  return aarch64_simd_container_mode (mode, 128);
+}
+
 /* Return the bitmask of possible vector sizes for the vectorizer
    to iterate over.  */
 static unsigned int
@@ -7282,6 +7307,18 @@ aarch64_output_simd_mov_immediate (rtx const_vector,
   return templ;
 }
 
+char*
+aarch64_output_scalar_simd_mov_immediate (rtx immediate,
+					  enum machine_mode mode)
+{
+  enum machine_mode vmode;
+
+  gcc_assert (!VECTOR_MODE_P (mode));
+  vmode = aarch64_simd_container_mode (mode, 64);
+  rtx v_op = aarch64_simd_gen_const_vector_dup (vmode, INTVAL (immediate));
+  return aarch64_output_simd_mov_immediate (v_op, vmode, 64);
+}
+
 /* Split operands into moves from op[1] + op[2] into op[0].  */
 
 void

gcc/config/aarch64/aarch64.md

@@ -774,17 +774,34 @@
         (match_operand:SHORT 1 "general_operand"      " r,M,D<hq>,m, m,rZ,*w,*w, r,*w"))]
   "(register_operand (operands[0], <MODE>mode)
     || aarch64_reg_or_zero (operands[1], <MODE>mode))"
-  "@
-   mov\\t%w0, %w1
-   mov\\t%w0, %1
-   movi\\t%0.<Vallxd>, %1
-   ldr<size>\\t%w0, %1
-   ldr\\t%<size>0, %1
-   str<size>\\t%w1, %0
-   str\\t%<size>1, %0
-   umov\\t%w0, %1.<v>[0]
-   dup\\t%0.<Vallxd>, %w1
-   dup\\t%0, %1.<v>[0]"
+{
+   switch (which_alternative)
+     {
+     case 0:
+       return "mov\t%w0, %w1";
+     case 1:
+       return "mov\t%w0, %1";
+     case 2:
+       return aarch64_output_scalar_simd_mov_immediate (operands[1],
+							<MODE>mode);
+     case 3:
+       return "ldr<size>\t%w0, %1";
+     case 4:
+       return "ldr\t%<size>0, %1";
+     case 5:
+       return "str<size>\t%w1, %0";
+     case 6:
+       return "str\t%<size>1, %0";
+     case 7:
+       return "umov\t%w0, %1.<v>[0]";
+     case 8:
+       return "dup\t%0.<Vallxd>, %w1";
+     case 9:
+       return "dup\t%0, %1.<v>[0]";
+     default:
+       gcc_unreachable ();
+     }
+}
   [(set_attr "v8type" "move,alu,alu,load1,load1,store1,store1,*,*,*")
    (set_attr "simd_type" "*,*,simd_move_imm,*,*,*,*,simd_movgp,simd_dupgp,simd_dup")
    (set_attr "simd" "*,*,yes,*,*,*,*,yes,yes,yes")

gcc/testsuite/ChangeLog

+2013-06-04  Ian Bolton  <ian.bolton@arm.com>
+
+	* gcc.target/aarch64/movi_1.c: New test.
+
 2013-06-04  Tobias Burnus  <burnus@net-b.de>
 
 	PR fortran/37336

gcc/testsuite/gcc.target/aarch64/movi_1.c

+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+void
+dummy (short* b)
+{
+  /* { dg-final { scan-assembler "movi\tv\[0-9\]+\.4h, 0x4, lsl 8" } } */
+  /* { dg-final { scan-assembler-not "movi\tv\[0-9\]+\.4h, 0x400" } } */
+  /* { dg-final { scan-assembler-not "movi\tv\[0-9\]+\.4h, 1024" } } */
+  register short x asm ("h8") = 1024;
+  asm volatile ("" : : "w" (x));
+  *b = x;
+}