From a5bcb9487dd62b853a6813387309e5f83a47ce0d Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Wed, 23 Dec 2020 18:32:28 +0100
Subject: [PATCH] i386: Fix __builtin_trunc with FE_DOWNWARD rounding direction
 [PR96793]
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

x86_expand_truncdf_32 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.

2020-12-23  Uroš Bizjak  <ubizjak@gmail.com>

gcc/
	PR target/96793
	* config/i386/i386-expand.c (ix86_expand_truncdf_32):
	Remove the sign of the intermediate value for flag_rounding_math.

gcc/testsuite/
	PR target/96793
	* gcc.target/i386/pr96793-1.c: New test.
---
 gcc/config/i386/i386-expand.c             | 27 +++++++++++-----------
 gcc/testsuite/gcc.target/i386/pr96793-1.c | 28 +++++++++++++++++++++++
 2 files changed, 42 insertions(+), 13 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr96793-1.c

diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 55474fbfa210..dd710809be25 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -16035,7 +16035,7 @@ void
 ix86_expand_truncdf_32 (rtx operand0, rtx operand1)
 {
   machine_mode mode = GET_MODE (operand0);
-  rtx xa, mask, TWO52, one, res, smask, tmp;
+  rtx xa, xa2, TWO52, tmp, one, res, mask;
   rtx_code_label *label;
 
   /* C code for SSE variant we expand below.
@@ -16058,28 +16058,29 @@ ix86_expand_truncdf_32 (rtx operand0, rtx operand1)
   emit_move_insn (res, operand1);
 
   /* xa = abs (operand1) */
-  xa = ix86_expand_sse_fabs (res, &smask);
+  xa = ix86_expand_sse_fabs (res, &mask);
 
   /* if (!isless (xa, TWO52)) goto label; */
   label = ix86_expand_sse_compare_and_jump (UNLE, TWO52, xa, false);
 
-  /* res = xa + TWO52 - TWO52; */
-  tmp = expand_simple_binop (mode, PLUS, xa, TWO52, NULL_RTX, 0, OPTAB_DIRECT);
-  tmp = expand_simple_binop (mode, MINUS, tmp, TWO52, tmp, 0, OPTAB_DIRECT);
-  emit_move_insn (res, tmp);
+  /* xa2 = xa + TWO52 - TWO52; */
+  xa2 = expand_simple_binop (mode, PLUS, xa, TWO52, NULL_RTX, 0, OPTAB_DIRECT);
+  xa2 = expand_simple_binop (mode, MINUS, xa2, TWO52, xa2, 0, OPTAB_DIRECT);
 
   /* generate 1.0 */
   one = force_reg (mode, const_double_from_real_value (dconst1, mode));
 
-  /* Compensate: res = xa2 - (res > xa ? 1 : 0)  */
-  mask = ix86_expand_sse_compare_mask (UNGT, res, xa, false);
-  emit_insn (gen_rtx_SET (mask, gen_rtx_AND (mode, mask, one)));
+  /* Compensate: xa2 = xa2 - (xa2 > xa ? 1 : 0)  */
+  tmp = ix86_expand_sse_compare_mask (UNGT, xa2, xa, false);
+  emit_insn (gen_rtx_SET (tmp, gen_rtx_AND (mode, one, tmp)));
   tmp = expand_simple_binop (mode, MINUS,
-			     res, mask, NULL_RTX, 0, OPTAB_DIRECT);
-  emit_move_insn (res, tmp);
+			     xa2, tmp, NULL_RTX, 0, OPTAB_DIRECT);
+  /* Remove the sign with FE_DOWNWARD, where x - x = -0.0.  */
+  if (flag_rounding_math)
+    tmp = ix86_expand_sse_fabs (tmp, NULL);
 
-  /* res = copysign (res, operand1) */
-  ix86_sse_copysign_to_positive (res, res, force_reg (mode, operand1), smask);
+  /* res = copysign (xa2, operand1) */
+  ix86_sse_copysign_to_positive (res, tmp, res, mask);
 
   emit_label (label);
   LABEL_NUSES (label) = 1;
diff --git a/gcc/testsuite/gcc.target/i386/pr96793-1.c b/gcc/testsuite/gcc.target/i386/pr96793-1.c
new file mode 100644
index 000000000000..b205d39f63ce
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr96793-1.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_trunc (value);
+}
+
+int
+main ()
+{
+  double result;
+
+  fesetround (FE_DOWNWARD);
+
+  result = test (0.25);
+
+  if (__builtin_signbit (result) != 0)
+    __builtin_abort ();
+
+  return 0;
+}
-- 
2.47.2