Fix Thumb-2 NEON ICE

["Joseph S. Myers" <joseph@codesourcery.com>]

This patch fixes an ICE for Thumb-2 NEON on the included testcase.

output_move_neon has operands[0]

  (mem:V16QI (plus:SI (reg:SI 3 r3) (const_int -256)))

and operands[1]

  (reg:V16QI 95 d16)

and calls adjust_address (mem, SImode, 8 * i).  This ends up
validating the address for SImode, but the offset of -256 is not valid
for SImode for Thumb-2.  The new address is only used with vldr/vstr
instructions; there seems to be no need for it to be valid for SImode,
so this patch makes it use DImode instead, for which all valid NEON
offsets are accepted.

Tested with no regressions with cross to arm-none-eabi.  OK to commit?

2009-10-08  Joseph Myers  <joseph@codesourcery.com>

	* config/arm/arm.c (output_move_neon): Use DImode in call to
	adjust_address.

testsuite:
2009-10-08  Joseph Myers  <joseph@codesourcery.com>

	* gcc.target/arm/neon-thumb2-move.c: New test.

Index: gcc/config/arm/arm.c
===================================================================
--- gcc/config/arm/arm.c	(revision 152576)
+++ gcc/config/arm/arm.c	(working copy)
@@ -12269,7 +12269,7 @@ output_move_neon (rtx *operands)
 	  {
 	    /* We're only using DImode here because it's a convenient size.  */
 	    ops[0] = gen_rtx_REG (DImode, REGNO (reg) + 2 * i);
-	    ops[1] = adjust_address (mem, SImode, 8 * i);
+	    ops[1] = adjust_address (mem, DImode, 8 * i);
 	    if (reg_overlap_mentioned_p (ops[0], mem))
 	      {
 		gcc_assert (overlap == -1);
Index: gcc/testsuite/gcc.target/arm/neon-thumb2-move.c
===================================================================
--- gcc/testsuite/gcc.target/arm/neon-thumb2-move.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/neon-thumb2-move.c	(revision 0)
@@ -0,0 +1,98 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_neon_ok } */
+/* { dg-options "-O2 -mthumb -march=armv7-a -mfloat-abi=softfp -mfpu=neon" } */
+
+#include <arm_neon.h>
+#include <stddef.h>
+
+void *
+memset (DST, C, LENGTH)
+     void *DST;
+     int C;
+     size_t LENGTH;
+{
+  void* DST0 = DST;
+  unsigned char C_BYTE = C;
+
+
+  if (__builtin_expect(LENGTH < 4, 1)) {
+    size_t i = 0;
+    while (i < LENGTH) {
+      ((char*)DST)[i] = C_BYTE;
+      i++;
+    }
+    return DST;
+  }
+
+  const char* DST_end = (char*)DST + LENGTH;
+
+
+  while ((uintptr_t)DST % 4 != 0) {
+    *(char*) (DST++) = C_BYTE;
+  }
+
+
+  uint32_t C_SHORTWORD = (uint32_t)(unsigned char)(C_BYTE) * 0x01010101;
+
+
+  if (__builtin_expect(DST_end - (char*)DST >= 16, 0)) {
+    while ((uintptr_t)DST % 16 != 0) {
+      *((uint32_t*)((char*)(DST) + (0))) = C_SHORTWORD;
+      DST += 4;
+    }
+
+
+    uint8x16_t C_WORD = vdupq_n_u8(C_BYTE);
+
+
+
+
+
+    size_t i = 0;
+    LENGTH = DST_end - (char*)DST;
+    while (i + 16 * 16 <= LENGTH) {
+      *((uint8x16_t*)((char*)(DST) + (i))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 1))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 2))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 3))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 4))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 5))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 6))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 7))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 8))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 9))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 10))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 11))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 12))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 13))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 14))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 15))) = C_WORD;
+      i += 16 * 16;
+    }
+    while (i + 16 * 4 <= LENGTH) {
+      *((uint8x16_t*)((char*)(DST) + (i))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 1))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 2))) = C_WORD;
+      *((uint8x16_t*)((char*)(DST) + (i + 16 * 3))) = C_WORD;
+      i += 16 * 4;
+    }
+    while (i + 16 <= LENGTH) {
+      *((uint8x16_t*)((char*)(DST) + (i))) = C_WORD;
+      i += 16;
+    }
+    DST += i;
+  }
+
+  while (4 <= DST_end - (char*)DST) {
+    *((uint32_t*)((char*)(DST) + (0))) = C_SHORTWORD;
+    DST += 4;
+  }
+
+
+  while ((char*)DST < DST_end) {
+    *((char*)DST) = C_BYTE;
+    DST++;
+  }
+
+  return DST0;
+}

-- 
Joseph S. Myers
joseph@codesourcery.com