glibc/sysdeps/i386/fpu/e_exp10f.S
Joseph Myers 828bf6828b Fix i386 exp10 missing underflows (bug 18966).
On i386, the double version of exp10 can miss underflow exceptions if
the result is in the subnormal range for double but the last 11 bits
of the 64-bit extended-precision mantissa happen to be zero.  This
patch forces the exception in a similar way to previous fixes.

As with the exp2 and exp fixes, the exp10f changes may in fact not be
needed to ensure underflow exceptions, but are included for
consistency and to fix the exp10 part of bug 18875 by ensuring that
excess range and precision is removed from underflowing return values.

Tested for x86_64 and x86.

	[BZ #18875]
	[BZ #18966]
	* sysdeps/i386/fpu/e_exp10.S (dbl_min): New object.
	(MO): New macro.
	(__ieee754_exp10): For small results, force underflow exception
	and remove excess range and precision from return value.
	* sysdeps/i386/fpu/e_exp10f.S (flt_min): New object.
	(MO): New macro.
	(__ieee754_exp10f): For small results, force underflow exception
	and remove excess range and precision from return value.
	* math/auto-libm-test-in: Add more tests of exp10.
	* math/auto-libm-test-out: Regenerated.
2015-09-15 16:50:02 +00:00

72 lines
1.4 KiB
ArmAsm

/*
* Written by Ulrich Drepper.
*/
#include <machine/asm.h>
.section .rodata.cst4,"aM",@progbits,4
.p2align 2
.type flt_min,@object
flt_min: .byte 0, 0, 0x80, 0
ASM_SIZE_DIRECTIVE(flt_min)
#ifdef PIC
# define MO(op) op##@GOTOFF(%ecx)
#else
# define MO(op) op
#endif
.text
/* 10^x = 2^(x * log2(10)) */
ENTRY(__ieee754_exp10f)
#ifdef PIC
LOAD_PIC_REG (cx)
#endif
flds 4(%esp)
/* I added the following ugly construct because exp(+-Inf) resulted
in NaN. The ugliness results from the bright minds at Intel.
For the i686 the code can be written better.
-- drepper@cygnus.com. */
fxam /* Is NaN or +-Inf? */
fstsw %ax
movb $0x45, %dh
andb %ah, %dh
cmpb $0x05, %dh
je 1f /* Is +-Inf, jump. */
fldl2t
fmulp /* x * log2(10) */
fld %st
frndint /* int(x * log2(10)) */
fsubr %st,%st(1) /* fract(x * log2(10)) */
fxch
f2xm1 /* 2^(fract(x * log2(10))) - 1 */
fld1
faddp /* 2^(fract(x * log2(10))) */
fscale /* e^x */
fstp %st(1)
flds MO(flt_min)
fld %st(1)
fucompp
fnstsw
sahf
jnc 3f
subl $4, %esp
cfi_adjust_cfa_offset (4)
fld %st(0)
fmul %st(0)
fstps (%esp)
fstps (%esp)
flds (%esp)
addl $4, %esp
cfi_adjust_cfa_offset (-4)
3: ret
1: testl $0x200, %eax /* Test sign. */
jz 2f /* If positive, jump. */
fstp %st
fldz /* Set result to 0. */
2: ret
END (__ieee754_exp10f)
strong_alias (__ieee754_exp10f, __exp10f_finite)