Improve TI mode address offsets - these may either use LDP of 64-bit or LDR of 128-bit...

Improve TI mode address offsets - these may either use LDP of 64-bit or
LDR of 128-bit, so we need to use the correct intersection of offsets.
When splitting a large offset into base and offset, use a signed 9-bit 
unscaled offset.

Remove the Ump constraint on movti and movtf instructions as this blocks
the reload optimizer from merging address CSEs (is this supposed to work
only on 'm' constraints?).  The result is improved codesize, especially
wrf and gamess in SPEC2006.

    gcc/
	* config/aarch64/aarch64.md (movti_aarch64): Change Ump to m.
	(movtf_aarch64): Likewise.
	* config/aarch64/aarch64.c (aarch64_classify_address):
	Use correct intersection of offsets.
	(aarch64_legitimize_address_displacement): Use 9-bit signed offsets.
	(aarch64_legitimize_address): Use 9-bit signed offsets for TI/TF mode.
	Use 7-bit signed scaled mode for modes > 16 bytes.

From-SVN: r243346

gcc/ChangeLog

+2016-12-07  Wilco Dijkstra  <wdijkstr@arm.com>
+
+	* config/aarch64/aarch64.md (movti_aarch64): Change Ump to m.
+	(movtf_aarch64): Likewise.
+	* config/aarch64/aarch64.c (aarch64_classify_address):
+	Use correct intersection of offsets.
+	(aarch64_legitimize_address_displacement): Use 9-bit signed offsets.
+	(aarch64_legitimize_address): Use 9-bit signed offsets for TI/TF mode.
+	Use 7-bit signed scaled mode for modes > 16 bytes.
+
 2016-12-07  James Greenhalgh  <james.greenhalgh@arm.com>
 
 	PR rtl-optimization/78561

gcc/config/aarch64/aarch64.c

@@ -4330,7 +4330,8 @@ aarch64_classify_address (struct aarch64_address_info *info,
 	     instruction memory accesses.  */
 	  if (mode == TImode || mode == TFmode)
 	    return (aarch64_offset_7bit_signed_scaled_p (DImode, offset)
-		    && offset_9bit_signed_unscaled_p (mode, offset));
+		    && (offset_9bit_signed_unscaled_p (mode, offset)
+			|| offset_12bit_unsigned_scaled_p (mode, offset)));
 
 	  /* A 7bit offset check because OImode will emit a ldp/stp
 	     instruction (only big endian will get here).
@@ -4534,18 +4535,19 @@ aarch64_legitimate_address_p (machine_mode mode, rtx x,
 /* Split an out-of-range address displacement into a base and offset.
    Use 4KB range for 1- and 2-byte accesses and a 16KB range otherwise
    to increase opportunities for sharing the base address of different sizes.
-   For TI/TFmode and unaligned accesses use a 256-byte range.  */
+   For unaligned accesses and TI/TF mode use the signed 9-bit range.  */
 static bool
 aarch64_legitimize_address_displacement (rtx *disp, rtx *off, machine_mode mode)
 {
-  HOST_WIDE_INT mask = GET_MODE_SIZE (mode) < 4 ? 0xfff : 0x3fff;
+  HOST_WIDE_INT offset = INTVAL (*disp);
+  HOST_WIDE_INT base = offset & ~(GET_MODE_SIZE (mode) < 4 ? 0xfff : 0x3ffc);
 
-  if (mode == TImode || mode == TFmode ||
-      (INTVAL (*disp) & (GET_MODE_SIZE (mode) - 1)) != 0)
-    mask = 0xff;
+  if (mode == TImode || mode == TFmode
+      || (offset & (GET_MODE_SIZE (mode) - 1)) != 0)
+    base = (offset + 0x100) & ~0x1ff;
 
-  *off = GEN_INT (INTVAL (*disp) & ~mask);
-  *disp = GEN_INT (INTVAL (*disp) & mask);
+  *off = GEN_INT (base);
+  *disp = GEN_INT (offset - base);
   return true;
 }
 
@@ -5412,12 +5414,10 @@ aarch64_legitimize_address (rtx x, rtx /* orig_x  */, machine_mode mode)
 	  x = gen_rtx_PLUS (Pmode, base, offset_rtx);
 	}
 
-      /* Does it look like we'll need a load/store-pair operation?  */
+      /* Does it look like we'll need a 16-byte load/store-pair operation?  */
       HOST_WIDE_INT base_offset;
-      if (GET_MODE_SIZE (mode) > 16
-	  || mode == TImode)
-	base_offset = ((offset + 64 * GET_MODE_SIZE (mode))
-		       & ~((128 * GET_MODE_SIZE (mode)) - 1));
+      if (GET_MODE_SIZE (mode) > 16)
+	base_offset = (offset + 0x400) & ~0x7f0;
       /* For offsets aren't a multiple of the access size, the limit is
 	 -256...255.  */
       else if (offset & (GET_MODE_SIZE (mode) - 1))
@@ -5431,6 +5431,8 @@ aarch64_legitimize_address (rtx x, rtx /* orig_x  */, machine_mode mode)
       /* Small negative offsets are supported.  */
       else if (IN_RANGE (offset, -256, 0))
 	base_offset = 0;
+      else if (mode == TImode || mode == TFmode)
+	base_offset = (offset + 0x100) & ~0x1ff;
       /* Use 12-bit offset by access size.  */
       else
 	base_offset = offset & (~0xfff * GET_MODE_SIZE (mode));

gcc/config/aarch64/aarch64.md

@@ -1120,9 +1120,9 @@
 
 (define_insn "*movti_aarch64"
   [(set (match_operand:TI 0
-	 "nonimmediate_operand"  "=r, *w,r ,*w,r  ,Ump,Ump,*w,m")
+	 "nonimmediate_operand"  "=r, *w,r ,*w,r,m,m,*w,m")
 	(match_operand:TI 1
-	 "aarch64_movti_operand" " rn,r ,*w,*w,Ump,r  ,Z  , m,*w"))]
+	 "aarch64_movti_operand" " rn,r ,*w,*w,m,r,Z, m,*w"))]
   "(register_operand (operands[0], TImode)
     || aarch64_reg_or_zero (operands[1], TImode))"
   "@
@@ -1237,9 +1237,9 @@
 
 (define_insn "*movtf_aarch64"
   [(set (match_operand:TF 0
-	 "nonimmediate_operand" "=w,?&r,w ,?r,w,?w,w,m,?r ,Ump,Ump")
+	 "nonimmediate_operand" "=w,?&r,w ,?r,w,?w,w,m,?r,m ,m")
 	(match_operand:TF 1
-	 "general_operand"      " w,?r, ?r,w ,Y,Y ,m,w,Ump,?r ,Y"))]
+	 "general_operand"      " w,?r, ?r,w ,Y,Y ,m,w,m ,?r,Y"))]
   "TARGET_FLOAT && (register_operand (operands[0], TFmode)
     || aarch64_reg_or_fp_zero (operands[1], TFmode))"
   "@