glibc/sysdeps/powerpc/powerpc64/fpu/s_nearbyint.S
Joseph Myers 71d1b0166b Fix powerpc nearbyint wrongly clearing "inexact" and leaving traps disabled (bug 19228).
Similar to bug 15491 recently fixed for x86_64 / x86, the powerpc
(both powerpc32 and powerpc64) hard-float implementations of
nearbyintf and nearbyint wrongly clear an "inexact" exception that was
raised before the function was called; this shows up as failure of the
test math/test-nearbyint-except added when that bug was fixed.  They
also wrongly leave traps on "inexact" disabled if they were enabled
before the function was called.

This patch fixes the bugs similar to how the x86 bug was fixed: saving
and restoring the whole floating-point state, both to restore the
original "inexact" flag state and to restore the original state of
whether traps on "inexact" were enabled.  Because there's a convenient
point in the powerpc implementations to save state after any sNaN
arguments will have raised "invalid" but before "inexact" traps need
to be disabled, no special handling for "invalid" is needed as in the
x86 version.

Tested for powerpc64 and powerpc32, where it fixes the
math/test-nearbyint-except failure as well as fixing the new test
math/test-nearbyint-except-2 added by this patch.  Also tested for
x86_64 and x86 that the new test passes.

If powerpc experts see a more efficient way of doing this
(e.g. instruction positioning that's better for pipelines on typical
processors) then of course followups optimizing the fix are welcome.

	[BZ #19228]
	* sysdeps/powerpc/powerpc32/fpu/s_nearbyint.S (__nearbyint): Save
	and restore full floating-point state.
	* sysdeps/powerpc/powerpc32/fpu/s_nearbyintf.S (__nearbyintf):
	Likewise.
	* sysdeps/powerpc/powerpc64/fpu/s_nearbyint.S (__nearbyint):
	Likewise.
	* sysdeps/powerpc/powerpc64/fpu/s_nearbyintf.S (__nearbyintf):
	Likewise.
	* math/test-nearbyint-except-2.c: New file.
	* math/Makefile (tests): Add test-nearbyint-except-2.
2015-11-11 00:06:09 +00:00

70 lines
2.2 KiB
ArmAsm

/* Round to int floating-point values. PowerPC64 version.
Copyright (C) 2011-2015 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Adhemerval Zanella <azanella@br.ibm.com>, 2011
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
<http://www.gnu.org/licenses/>. */
/* This has been coded in assembler because GCC makes such a mess of it
when it's coded in C. */
#include <sysdep.h>
#include <math_ldbl_opt.h>
/* double [fp1] nearbyint(double [fp1] x) */
.section ".toc","aw"
.LC0: /* 2**52 */
.tc FD_43300000_0[TC],0x4330000000000000
.section ".text"
EALIGN (__nearbyint, 4, 0)
CALL_MCOUNT 0
fabs fp0,fp1
lfd fp13,.LC0@toc(2)
fcmpu cr7,fp0,fp13 /* if (fabs(x) > TWO52) */
bgelr cr7
fsub fp12,fp13,fp13 /* generate 0.0 */
fcmpu cr7,fp1,fp12 /* if (x > 0.0) */
ble cr7, L(lessthanzero)
mffs fp11
mtfsb0 4*cr7+lt /* Disable FE_INEXACT exception */
fadd fp1,fp1,fp13 /* x+= TWO52 */
fsub fp1,fp1,fp13 /* x-= TWO52 */
fabs fp1,fp1 /* if (x == 0.0) */
mtfsf 0xff,fp11 /* Restore FE_INEXACT state. */
blr /* x = 0.0; */
L(lessthanzero):
bgelr cr7 /* if (x < 0.0) */
mffs fp11
mtfsb0 4*cr7+lt
fsub fp1,fp1,fp13 /* x -= TWO52 */
fadd fp1,fp1,fp13 /* x += TWO52 */
fnabs fp1,fp1 /* if (x == 0.0) */
mtfsf 0xff,fp11 /* Restore FE_INEXACT state. */
blr /* x = -0.0; */
END (__nearbyint)
weak_alias (__nearbyint, nearbyint)
#ifdef NO_LONG_DOUBLE
weak_alias (__nearbyint, nearbyint)
strong_alias (__nearbyint, __nearbyintl)
#endif
#if LONG_DOUBLE_COMPAT(libm, GLIBC_2_1)
compat_symbol (libm, __nearbyint, nearbyintl, GLIBC_2_1)
#endif