re PR rtl-optimization/54300 (regcprop incorrectly looks through parallel register...

PR rtl-optimization/54300

gcc/

	PR rtl-optimization/54300
	* regcprop.c (copyprop_hardreg_forward_1): Ensure any unused
	outputs in a single-set are killed from the value chains.

gcc/testsuite:

	PR rtl-optimization/54300
	* gcc.target/arm/pr54300.C: New test.

From-SVN: r205117

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 15476a4f611d57e72fa40a427b47e23c31bd3171..1064cfe0601b270f652cd27aa4ba250c5af87b0d 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2013-11-20  Richard Earnshaw  <rearnsha@arm.com>
+
+       PR rtl-optimization/54300
+       * regcprop.c (copyprop_hardreg_forward_1): Ensure any unused
+       outputs in a single-set are killed from the value chains.
+
 2013-11-20  Ilya Enkovich  <ilya.enkovich@intel.com>
 
        * cgraph.h (varpool_node): Add need_bounds_init field.

diff --git a/gcc/regcprop.c b/gcc/regcprop.c
index 0fa0afbc82488d26685183c26d7e0acba8d0b9e3..9b52a6301f7caeb9ce526ec4dc885c8402c39787 100644 (file)
--- a/gcc/regcprop.c
+++ b/gcc/regcprop.c
@@ -747,6 +747,7 @@ copyprop_hardreg_forward_1 (basic_block bb, struct value_data *vd)
       int n_ops, i, alt, predicated;
       bool is_asm, any_replacements;
       rtx set;
+      rtx link;
       bool replaced[MAX_RECOG_OPERANDS];
       bool changed = false;
       struct kill_set_value_data ksvd;
@@ -815,6 +816,23 @@ copyprop_hardreg_forward_1 (basic_block bb, struct value_data *vd)
        if (recog_op_alt[i][alt].earlyclobber)
          kill_value (recog_data.operand[i], vd);
 
+      /* If we have dead sets in the insn, then we need to note these as we
+        would clobbers.  */
+      for (link = REG_NOTES (insn); link; link = XEXP (link, 1))
+       {
+         if (REG_NOTE_KIND (link) == REG_UNUSED)
+           {
+             kill_value (XEXP (link, 0), vd);
+             /* Furthermore, if the insn looked like a single-set,
+                but the dead store kills the source value of that
+                set, then we can no-longer use the plain move
+                special case below.  */
+             if (set
+                 && reg_overlap_mentioned_p (XEXP (link, 0), SET_SRC (set)))
+               set = NULL;
+           }
+       }
+
       /* Special-case plain move instructions, since we may well
         be able to do the move from a different register class.  */
       if (set && REG_P (SET_SRC (set)))

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index e937d50277ab8249f6911c284ff17eef2b0a47c4..37e83eae5b2762b1bc23e4d62e26229ff2da100d 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2013-11-20  Richard Earnshaw  <rearnsha@arm.com>
+
+       PR rtl-optimization/54300
+       * gcc.target/arm/pr54300.C: New test.
+
 2013-11-20  Diego Novillo  <dnovillo@google.com>
 
        PR 59212

diff --git a/gcc/testsuite/gcc.target/arm/pr54300.C b/gcc/testsuite/gcc.target/arm/pr54300.C
new file mode 100644 (file)
index 0000000..eb1a74e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/pr54300.C
@@ -0,0 +1,61 @@
+/* { dg-do run } */
+/* { dg-require-effective-target arm_neon } */
+/* { dg-options "-O2" } */
+/* { dg-add-options arm_neon } */
+
+#include <arm_neon.h>
+#include <stdlib.h>
+
+struct __attribute__ ((aligned(8))) _v16u8_ {
+  uint8x16_t val;
+  _v16u8_( const int16x8_t &src) { val = vreinterpretq_u8_s16(src); }
+  operator int16x8_t () const { return vreinterpretq_s16_u8(val); }
+};
+typedef struct _v16u8_ v16u8;
+
+struct __attribute__ ((aligned(4))) _v8u8_ {
+  uint8x8_t val;
+  _v8u8_( const uint8x8_t &src) { val = src; }
+  operator int16x4_t () const { return vreinterpret_s16_u8(val); }
+};
+typedef struct _v8u8_ v8u8;
+
+typedef v16u8                v8i16;
+typedef int32x4_t            v4i32;
+typedef const short         cv1i16;
+typedef const unsigned char cv1u8;
+typedef const v8i16         cv8i16;
+
+static inline __attribute__((always_inline)) v8u8 zero_64(){ return vdup_n_u8( 0 ); }
+
+static inline __attribute__((always_inline)) v8i16 loadlo_8i16( cv8i16* p ){
+  return vcombine_s16( vld1_s16( (cv1i16 *)p ), zero_64() );
+}
+static inline __attribute__((always_inline)) v8i16 _loadlo_8i16( cv8i16* p, int offset ){
+  return loadlo_8i16( (cv8i16*)(&((cv1u8*)p)[offset]) );
+}
+
+void __attribute__((noinline))
+test(unsigned short *_Inp, int32_t *_Out,
+     unsigned int s1v, unsigned int dv0,
+     unsigned int smask_v)
+{
+  int32x4_t c = vdupq_n_s32(0);
+
+  for(unsigned int sv=0 ; sv!=dv0 ; sv=(sv+s1v)&smask_v )
+    {
+      int32x4_t s;
+      s = vmovl_s16( vget_low_s16( _loadlo_8i16( (cv8i16*) _Inp, sv ) ) );
+      c = vaddq_s32( c, s );
+    }
+  vst1q_s32( _Out, c );
+}
+
+main()
+{
+  unsigned short a[4] = {1, 2, 3, 4};
+  int32_t b[4] = {0, 0, 0, 0};
+  test(a, b, 1, 1, ~0);
+  if (b[0] != 1 || b[1] != 2 || b[2] != 3 || b[3] != 4)
+    abort();
+}