From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 22 Dec 2020 17:13:24 +0000 (+0100)
Subject: i386: Fix __builtin_floor with FE_DOWNWARD rounding direction [PR96793]
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=337ed0eb490b14899f4049bc4c8922eb1d8a2e67;p=gcc.git

i386: Fix __builtin_floor with FE_DOWNWARD rounding direction [PR96793]

x86_expand_floorceil expander uses x86_sse_copysign_to_positive, which
is unable to change the sign from - to +.  When FE_DOWNWARD rounding
direction is in effect, the expanded sequence that involves subtraction
can trigger x - x = -0.0 special rule.  x86_sse_copysign_to_positive
fails to change the sign of the intermediate value, assumed to always
be positive, back to positive.

The patch adds one extra fabs that strips the sign from the intermediate
value when flag_rounding_math is in effect.

2020-12-22  Uroš Bizjak  <ubizjak@gmail.com>

gcc/
	PR target/96793
	* config/i386/i386-expand.c (ix86_expand_floorceil):
	Remove the sign of the intermediate value for flag_rounding_math.
	(ix86_expand_floorceildf_32): Ditto.

gcc/testsuite/
	PR target/96793
	* gcc.target/i386/pr96793.c: New test.
---

diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 7c31cc7daac..f838112783c 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -16352,12 +16352,14 @@ ix86_expand_floorceil (rtx operand0, rtx operand1, bool do_floor)
         if (!isless (xa, TWO52))
           return x;
 	x2 = (double)(long)x;
+
      Compensate.  Floor:
 	if (x2 > x)
 	  x2 -= 1;
      Compensate.  Ceil:
 	if (x2 < x)
 	  x2 += 1;
+
 	if (HONOR_SIGNED_ZEROS (mode))
 	  return copysign (x2, x);
 	return x2;
@@ -16392,10 +16394,15 @@ ix86_expand_floorceil (rtx operand0, rtx operand1, bool do_floor)
   emit_insn (gen_rtx_SET (tmp, gen_rtx_AND (mode, one, tmp)));
   tmp = expand_simple_binop (mode, do_floor ? MINUS : PLUS,
 			     xa, tmp, NULL_RTX, 0, OPTAB_DIRECT);
-  emit_move_insn (res, tmp);
-
   if (HONOR_SIGNED_ZEROS (mode))
-    ix86_sse_copysign_to_positive (res, res, force_reg (mode, operand1), mask);
+    {
+      /* Remove the sign with FE_DOWNWARD, where x - x = -0.0.  */
+      if (do_floor && flag_rounding_math)
+	tmp = ix86_expand_sse_fabs (tmp, NULL);
+
+      ix86_sse_copysign_to_positive (tmp, tmp, res, mask);
+    }
+  emit_move_insn (res, tmp);
 
   emit_label (label);
   LABEL_NUSES (label) = 1;
@@ -16415,12 +16422,14 @@ ix86_expand_floorceildf_32 (rtx operand0, rtx operand1, bool do_floor)
           return x;
         xa = xa + TWO52 - TWO52;
         x2 = copysign (xa, x);
+
      Compensate.  Floor:
         if (x2 > x)
           x2 -= 1;
      Compensate.  Ceil:
         if (x2 < x)
           x2 += 1;
+
 	if (HONOR_SIGNED_ZEROS (mode))
 	  x2 = copysign (x2, x);
 	return x2;
@@ -16457,8 +16466,14 @@ ix86_expand_floorceildf_32 (rtx operand0, rtx operand1, bool do_floor)
   emit_insn (gen_rtx_SET (tmp, gen_rtx_AND (mode, one, tmp)));
   tmp = expand_simple_binop (mode, do_floor ? MINUS : PLUS,
 			     xa, tmp, NULL_RTX, 0, OPTAB_DIRECT);
-  if (!do_floor && HONOR_SIGNED_ZEROS (mode))
-    ix86_sse_copysign_to_positive (tmp, tmp, res, mask);
+  if (HONOR_SIGNED_ZEROS (mode))
+    {
+      /* Remove the sign with FE_DOWNWARD, where x - x = -0.0.  */
+      if (do_floor && flag_rounding_math)
+	tmp = ix86_expand_sse_fabs (tmp, NULL);
+
+      ix86_sse_copysign_to_positive (tmp, tmp, res, mask);
+    }
   emit_move_insn (res, tmp);
 
   emit_label (label);
diff --git a/gcc/testsuite/gcc.target/i386/pr96793.c b/gcc/testsuite/gcc.target/i386/pr96793.c
new file mode 100644
index 00000000000..4a96478e31e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr96793.c
@@ -0,0 +1,28 @@
+/* PR target/96793 */
+/* { dg-do run { target sse2_runtime } } */
+/* { dg-require-effective-target fenv } */
+/* { dg-options "-O2 -frounding-math -msse2 -mno-sse4 -mfpmath=sse" } */
+
+#include <fenv.h>
+
+double
+__attribute__((noinline))
+test (double value)
+{
+  return __builtin_floor (value);
+}
+
+int
+main ()
+{
+  double result;
+
+  fesetround (FE_DOWNWARD);
+
+  result = test (0.25);
+
+  if (__builtin_signbit (result) != 0)
+    __builtin_abort ();
+
+  return 0;
+}