glibc/sysdeps/x86_64/fpu/x86_64-math-asm.h
Joseph Myers 6ace393821 Fix pow missing underflows (bug 18825).
Similar to various other bugs in this area, pow functions can fail to
raise the underflow exception when the result is tiny and inexact but
one or more low bits of the intermediate result that is scaled down
(or, in the i386 case, converted from a wider evaluation format) are
zero.  This patch forces the exception in a similar way to previous
fixes, thereby concluding the fixes for known bugs with missing
underflow exceptions currently filed in Bugzilla.

Tested for x86_64, x86, mips64 and powerpc.

	[BZ #18825]
	* sysdeps/i386/fpu/i386-math-asm.h (FLT_NARROW_EVAL_UFLOW_NONNAN):
	New macro.
	(DBL_NARROW_EVAL_UFLOW_NONNAN): Likewise.
	(LDBL_CHECK_FORCE_UFLOW_NONNAN): Likewise.
	* sysdeps/i386/fpu/e_pow.S: Use DEFINE_DBL_MIN.
	(__ieee754_pow): Use DBL_NARROW_EVAL_UFLOW_NONNAN instead of
	DBL_NARROW_EVAL, reloading the PIC register as needed.
	* sysdeps/i386/fpu/e_powf.S: Use DEFINE_FLT_MIN.
	(__ieee754_powf): Use FLT_NARROW_EVAL_UFLOW_NONNAN instead of
	FLT_NARROW_EVAL.  Use separate return path for case when first
	argument is NaN.
	* sysdeps/i386/fpu/e_powl.S: Include <i386-math-asm.h>.  Use
	DEFINE_LDBL_MIN.
	(__ieee754_powl): Use LDBL_CHECK_FORCE_UFLOW_NONNAN, reloading the
	PIC register.
	* sysdeps/ieee754/dbl-64/e_pow.c (__ieee754_pow): Use
	math_check_force_underflow_nonneg.
	* sysdeps/ieee754/flt-32/e_powf.c (__ieee754_powf): Force
	underflow for subnormal result.
	* sysdeps/ieee754/ldbl-128/e_powl.c (__ieee754_powl): Likewise.
	* sysdeps/ieee754/ldbl-128ibm/e_powl.c (__ieee754_powl): Use
	math_check_force_underflow_nonneg.
	* sysdeps/x86/fpu/powl_helper.c (__powl_helper): Use
	math_check_force_underflow.
	* sysdeps/x86_64/fpu/x86_64-math-asm.h
	(LDBL_CHECK_FORCE_UFLOW_NONNAN): New macro.
	* sysdeps/x86_64/fpu/e_powl.S: Include <x86_64-math-asm.h>.  Use
	DEFINE_LDBL_MIN.
	(__ieee754_powl): Use LDBL_CHECK_FORCE_UFLOW_NONNAN.
	* math/auto-libm-test-in: Add more tests of pow.
	* math/auto-libm-test-out: Regenerated.
2015-09-25 22:29:10 +00:00

75 lines
2.2 KiB
C

/* Helper macros for x86_64 libm functions.
Copyright (C) 2015 Free Software Foundation, Inc.
This file is part of the GNU C Library.
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/>. */
#ifndef _X86_64_MATH_ASM_H
#define _X86_64_MATH_ASM_H 1
/* Define constants for the minimum value of a floating-point
type. */
#define DEFINE_LDBL_MIN \
.section .rodata.cst16,"aM",@progbits,16; \
.p2align 4; \
.type ldbl_min,@object; \
ldbl_min: \
.byte 0, 0, 0, 0, 0, 0, 0, 0x80, 0x1, 0; \
.byte 0, 0, 0, 0, 0, 0; \
.size ldbl_min, .-ldbl_min;
/* Force an underflow exception if the given value (nonnegative or
NaN) is subnormal. The relevant constant for the minimum of the
type must have been defined, the MO macro must have been defined
for access to memory operands, and, if PIC, the PIC register must
have been loaded. */
#define LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN \
fldt MO(ldbl_min); \
fld %st(1); \
fucomip %st(1), %st(0); \
fstp %st(0); \
jnc 6464f; \
fld %st(0); \
fmul %st(0); \
fstp %st(0); \
6464:
/* Likewise, but the argument is not a NaN. */
#define LDBL_CHECK_FORCE_UFLOW_NONNAN \
fldt MO(ldbl_min); \
fld %st(1); \
fabs; \
fcomip %st(1), %st(0); \
fstp %st(0); \
jnc 6464f; \
fld %st(0); \
fmul %st(0); \
fstp %st(0); \
6464:
/* Likewise, but the argument is nonnegative and not a NaN. */
#define LDBL_CHECK_FORCE_UFLOW_NONNEG \
fldt MO(ldbl_min); \
fld %st(1); \
fcomip %st(1), %st(0); \
fstp %st(0); \
jnc 6464f; \
fld %st(0); \
fmul %st(0); \
fstp %st(0); \
6464:
#endif /* x86_64-math-asm.h. */