PR target/50310

	* config/i386/i386.c (ix86_prepare_sse_fp_compare_args): Return
	code early if TARGET_AVX.
	(ix86_expand_fp_vcond): Handle LTGT and UNEQ.

	* gcc.c-torture/execute/ieee/pr50310.c: New test.
	* gcc.dg/pr50310-2.c: New test.

git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@178673 138bc75d-0d04-0410-961f-82ee72b054a4

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 3f79363..6a96c33 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,10 @@
+2011-09-08  Jakub Jelinek  <jakub@redhat.com>
+
+       PR target/50310
+       * config/i386/i386.c (ix86_prepare_sse_fp_compare_args): Return
+       code early if TARGET_AVX.
+       (ix86_expand_fp_vcond): Handle LTGT and UNEQ.
+
 2011-09-07  Jakub Jelinek  <jakub@redhat.com>
 
        * config/i386/sse.md (sseinsnmode): Remove 32-byte integer vector

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index ff8c49f..7bdab73 100644 (file)
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -18318,6 +18318,11 @@ ix86_prepare_sse_fp_compare_args (rtx dest, enum rtx_code code,
 {
   rtx tmp;
 
+  /* AVX supports all the needed comparisons, no need to swap arguments
+     nor help reload.  */
+  if (TARGET_AVX)
+    return code;
+
   switch (code)
     {
     case LTGT:
@@ -18573,7 +18578,32 @@ ix86_expand_fp_vcond (rtx operands[])
   code = ix86_prepare_sse_fp_compare_args (operands[0], code,
                                           &operands[4], &operands[5]);
   if (code == UNKNOWN)
-    return false;
+    {
+      rtx temp;
+      switch (GET_CODE (operands[3]))
+       {
+       case LTGT:
+         temp = ix86_expand_sse_cmp (operands[0], ORDERED, operands[4],
+                                     operands[5], operands[0], operands[0]);
+         cmp = ix86_expand_sse_cmp (operands[0], NE, operands[4],
+                                    operands[5], operands[1], operands[2]);
+         code = AND;
+         break;
+       case UNEQ:
+         temp = ix86_expand_sse_cmp (operands[0], UNORDERED, operands[4],
+                                     operands[5], operands[0], operands[0]);
+         cmp = ix86_expand_sse_cmp (operands[0], EQ, operands[4],
+                                    operands[5], operands[1], operands[2]);
+         code = IOR;
+         break;
+       default:
+         gcc_unreachable ();
+       }
+      cmp = expand_simple_binop (GET_MODE (cmp), code, temp, cmp, cmp, 1,
+                                OPTAB_DIRECT);
+      ix86_expand_sse_movcc (operands[0], cmp, operands[1], operands[2]);
+      return true;
+    }
 
   if (ix86_expand_sse_fp_minmax (operands[0], code, operands[4],
                                 operands[5], operands[1], operands[2]))

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 5189d62..364d0dc 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2011-09-08  Jakub Jelinek  <jakub@redhat.com>
+
+       PR target/50310
+       * gcc.c-torture/execute/ieee/pr50310.c: New test.
+       * gcc.dg/pr50310-2.c: New test.
+
 2011-09-07  Janus Weil  <janus@gcc.gnu.org>
 
        PR fortran/48095

diff --git a/gcc/testsuite/gcc.c-torture/execute/ieee/pr50310.c b/gcc/testsuite/gcc.c-torture/execute/ieee/pr50310.c
new file mode 100644 (file)
index 0000000..8d323ca
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/ieee/pr50310.c
@@ -0,0 +1,73 @@
+/* PR target/50310 */
+
+extern void abort (void);
+double s1[4], s2[4], s3[64];
+
+void
+foo (void)
+{
+  int i;
+  for (i = 0; i < 4; i++)
+    s3[0 * 4 + i] = __builtin_isgreater (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[1 * 4 + i] = (!__builtin_isgreater (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[2 * 4 + i] = __builtin_isgreaterequal (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[3 * 4 + i] = (!__builtin_isgreaterequal (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[4 * 4 + i] = __builtin_isless (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[5 * 4 + i] = (!__builtin_isless (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[6 * 4 + i] = __builtin_islessequal (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[7 * 4 + i] = (!__builtin_islessequal (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[8 * 4 + i] = __builtin_islessgreater (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[9 * 4 + i] = (!__builtin_islessgreater (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[10 * 4 + i] = __builtin_isunordered (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[11 * 4 + i] = (!__builtin_isunordered (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[12 * 4 + i] = s1[i] > s2[i] ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[13 * 4 + i] = s1[i] <= s2[i] ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[14 * 4 + i] = s1[i] < s2[i] ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[15 * 4 + i] = s1[i] >= s2[i] ? -1.0 : 0.0;
+}
+
+int
+main ()
+{
+  int i;
+  s1[0] = 5.0;
+  s1[1] = 6.0;
+  s1[2] = 5.0;
+  s1[3] = __builtin_nan ("");
+  s2[0] = 6.0;
+  s2[1] = 5.0;
+  s2[2] = 5.0;
+  s2[3] = 5.0;
+  asm volatile ("" : : : "memory");
+  foo ();
+  asm volatile ("" : : : "memory");
+  for (i = 0; i < 16 * 4; i++)
+    if (i >= 12 * 4 && (i & 3) == 3)
+      {
+       if (s3[i] != 0.0) abort ();
+      }
+    else
+      {
+        static int masks[] = { 2, 2|4, 1, 1|4, 1|2, 8, 2, 1 };
+        if (s3[i]
+           != (((1 << (i & 3)) & ((i & 4) ? ~masks[i / 8] : masks[i / 8]))
+               ? -1.0 : 0.0))
+         abort ();
+      }
+  return 0;
+}

diff --git a/gcc/testsuite/gcc.dg/pr50310-2.c b/gcc/testsuite/gcc.dg/pr50310-2.c
new file mode 100644 (file)
index 0000000..2962172
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/pr50310-2.c
@@ -0,0 +1,47 @@
+/* PR target/50310 */
+/* { dg-do run } */
+/* { dg-options "-O3" } */
+/* { dg-options "-O3 -mavx" { target avx_runtime } } */
+
+double s1[4], s2[4], s3[64];
+
+int
+main (void)
+{
+  int i;
+  asm volatile ("" : : : "memory");
+  for (i = 0; i < 4; i++)
+    s3[0 * 4 + i] = __builtin_isgreater (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[1 * 4 + i] = (!__builtin_isgreater (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[2 * 4 + i] = __builtin_isgreaterequal (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[3 * 4 + i] = (!__builtin_isgreaterequal (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[4 * 4 + i] = __builtin_isless (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[5 * 4 + i] = (!__builtin_isless (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[6 * 4 + i] = __builtin_islessequal (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[7 * 4 + i] = (!__builtin_islessequal (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[8 * 4 + i] = __builtin_islessgreater (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[9 * 4 + i] = (!__builtin_islessgreater (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[10 * 4 + i] = __builtin_isunordered (s1[i], s2[i]) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[11 * 4 + i] = (!__builtin_isunordered (s1[i], s2[i])) ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[12 * 4 + i] = s1[i] > s2[i] ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[13 * 4 + i] = s1[i] >= s2[i] ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[14 * 4 + i] = s1[i] < s2[i] ? -1.0 : 0.0;
+  for (i = 0; i < 4; i++)
+    s3[15 * 4 + i] = s1[i] <= s2[i] ? -1.0 : 0.0;
+  asm volatile ("" : : : "memory");
+  return 0;
+}