From 3e336a8754678d7a4ef7348c129e6f6e37523798 Mon Sep 17 00:00:00 2001
From: Ulrich Drepper <drepper@redhat.com>
Date: Mon, 16 Apr 2007 20:41:42 +0000
Subject: [BZ #3306]

2007-03-27  Jakub Jelinek  <jakub@redhat.com>
	[BZ #3306]
	* math/math_private.h (math_opt_barrier, math_force_eval): Define.
	* sysdeps/i386/fpu/math_private.h: New file.
	* sysdeps/x86_64/fpu/math_private.h: New file.
	* math/s_nexttowardf.c (__nexttowardf): Use math_opt_barrier and
	math_force_eval macros.  Use "+m" constraint on asm rather than
	"=m" and "m".
	* math/s_nextafter.c (__nextafter): Likewise.
	* sysdeps/ieee754/ldbl-128ibm/s_nexttoward.c (__nexttoward):
	Likewise.
	* sysdeps/ieee754/flt-32/s_nextafterf.c (__nextafterf): Likewise.
	* sysdeps/ieee754/ldbl-128/s_nexttoward.c (__nexttoward): Likewise.
	* sysdeps/ieee754/ldbl-96/s_nexttoward.c (__nexttoward): Likewise.
	* sysdeps/i386/fpu/s_nextafterl.c (__nextafterl): Use
	math_opt_barrier and math_force_eval macros.
	* sysdeps/ieee754/ldbl-128/s_nextafterl.c (__nextafterl): Likewise.
	* sysdeps/ieee754/ldbl-96/s_nextafterl.c (__nextafterl): Likewise.
	* sysdeps/i386/fpu/s_nexttoward.c: Include float.h.
	(__nexttoward): Use math_opt_barrier and
	math_force_eval macros.  Use "+m" constraint on asm rather than
	"=m" and "m".  Only use asm to force double result if
	FLT_EVAL_METHOD is 2.
	* sysdeps/i386/fpu/s_nexttowardf.c: Include float.h.
	(__nexttowardf): Use math_opt_barrier and
	math_force_eval macros.  Use "+m" constraint on asm rather than
	"=m" and "m".  Only use asm to force double result if
	FLT_EVAL_METHOD is not 0.
	* sysdeps/ieee754/ldbl-128ibm/s_nexttowardf.c: Include float.h.
	(__nexttowardf): Use math_opt_barrier and
	math_force_eval macros.  If FLT_EVAL_METHOD is not 0, force
	x to float using asm.
	* sysdeps/ieee754/ldbl-opt/s_nexttowardfd.c: Include float.h.
	(__nldbl_nexttowardf): Use math_opt_barrier and
	math_force_eval macros.  If FLT_EVAL_METHOD is not 0, force
	x to float using asm.
	* sysdeps/ieee754/ldbl-96/s_nexttowardf.c: Include float.h.
	(__nexttowardf): Use math_opt_barrier and math_force_eval
	macros.  If FLT_EVAL_METHOD is not 0, force x to float using asm.
	* math/bug-nextafter.c (zero, inf): New variables.
	(main): Add new tests.
	* math/bug-nexttoward.c (zero, inf): New variables.
	(main): Add new tests.
---
 sysdeps/ieee754/ldbl-opt/s_nexttowardfd.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

(limited to 'sysdeps/ieee754/ldbl-opt/s_nexttowardfd.c')

diff --git a/sysdeps/ieee754/ldbl-opt/s_nexttowardfd.c b/sysdeps/ieee754/ldbl-opt/s_nexttowardfd.c
index d52526f719..68027f26fa 100644
--- a/sysdeps/ieee754/ldbl-opt/s_nexttowardfd.c
+++ b/sysdeps/ieee754/ldbl-opt/s_nexttowardfd.c
@@ -20,7 +20,10 @@
  *   Special cases:
  */
 
+#include <math.h>
+#include <math_private.h>
 #include <math_ldbl_opt.h>
+#include <float.h>
 
 float __nldbl_nexttowardf(float x, double y);
 
@@ -39,10 +42,12 @@ float __nldbl_nexttowardf(float x, double y)
 	   return x+y;
 	if((double) x==y) return y;		/* x=y, return y */
 	if(ix==0) {				/* x == 0 */
-	    float x2;
+	    float u;
 	    SET_FLOAT_WORD(x,(u_int32_t)(hy&0x80000000)|1);/* return +-minsub*/
-	    x2 = x*x;
-	    if(x2==x) return x2; else return x; /* raise underflow flag */
+	    u = math_opt_barrier (x);
+	    u = u * u;
+	    math_force_eval (u);		/* raise underflow flag */
+	    return x;
 	}
 	if(hx>=0) {				/* x > 0 */
 	    if(hy<0||(ix>>23)>(iy>>20)-0x380
@@ -60,13 +65,16 @@ float __nldbl_nexttowardf(float x, double y)
 		hx += 1;
 	}
 	hy = hx&0x7f800000;
-	if(hy>=0x7f800000) return x+x;	/* overflow  */
-	if(hy<0x00800000) {		/* underflow */
-	    float x2 = x*x;
-	    if(x2!=x) {		/* raise underflow flag */
-		SET_FLOAT_WORD(x2,hx);
-		return x2;
-	    }
+	if(hy>=0x7f800000) {
+	  x = x+x;	/* overflow  */
+	  if (FLT_EVAL_METHOD != 0)
+	    /* Force conversion to float.  */
+	    asm ("" : "+m"(x));
+	  return x;
+	}
+	if(hy<0x00800000) {
+	    float u = x*x;			/* underflow */
+	    math_force_eval (u);		/* raise underflow flag */
 	}
 	SET_FLOAT_WORD(x,hx);
 	return x;
-- 
cgit 1.4.1