glibc/sysdeps/i386/fpu/e_exp2f.S

71 lines
1.3 KiB
ArmAsm
Raw Normal View History

/*
* Written by J.T. Conklin <jtc@netbsd.org>.
* Adapted for exp2 by Ulrich Drepper <drepper@cygnus.com>.
* Public domain.
*/
#include <machine/asm.h>
Fix exp2 missing underflows (bug 16521). Various exp2 implementations in glibc can miss underflow exceptions when the scaling down part of the calculation is exact (or, in the x86 case, when the conversion from extended precision to the target precision is exact). This patch forces the exception in a similar way to previous fixes. The x86 exp2f changes may in fact not be needed for this purpose - it's likely to be the case that no argument of type float has an exp2 result so close to an exact subnormal float value that it equals that value when rounded to 64 bits (even taking account of variation between different x86 implementations). However, they are included for consistency with the changes to exp2 and so as to fix the exp2f part of bug 18875 by ensuring that excess range and precision is removed from underflowing return values. Tested for x86_64, x86 and mips64. [BZ #16521] [BZ #18875] * math/e_exp2l.c (__ieee754_exp2l): Force underflow exception for small results. * sysdeps/i386/fpu/e_exp2.S (dbl_min): New object. (MO): New macro. (__ieee754_exp2): For small results, force underflow exception and remove excess range and precision from return value. * sysdeps/i386/fpu/e_exp2f.S (flt_min): New object. (MO): New macro. (__ieee754_exp2f): For small results, force underflow exception and remove excess range and precision from return value. * sysdeps/i386/fpu/e_exp2l.S (ldbl_min): New object. (MO): New macro. (__ieee754_exp2l): Force underflow exception for small results. * sysdeps/ieee754/dbl-64/e_exp2.c (__ieee754_exp2): Likewise. * sysdeps/ieee754/flt-32/e_exp2f.c (__ieee754_exp2f): Likewise. * sysdeps/x86_64/fpu/e_exp2l.S (ldbl_min): New object. (MO): New macro. (__ieee754_exp2l): Force underflow exception for small results. * math/auto-libm-test-in: Add more tests or exp2. * math/auto-libm-test-out: Regenerated.
2015-09-14 22:00:12 +00:00
.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
ENTRY(__ieee754_exp2f)
Fix exp2 missing underflows (bug 16521). Various exp2 implementations in glibc can miss underflow exceptions when the scaling down part of the calculation is exact (or, in the x86 case, when the conversion from extended precision to the target precision is exact). This patch forces the exception in a similar way to previous fixes. The x86 exp2f changes may in fact not be needed for this purpose - it's likely to be the case that no argument of type float has an exp2 result so close to an exact subnormal float value that it equals that value when rounded to 64 bits (even taking account of variation between different x86 implementations). However, they are included for consistency with the changes to exp2 and so as to fix the exp2f part of bug 18875 by ensuring that excess range and precision is removed from underflowing return values. Tested for x86_64, x86 and mips64. [BZ #16521] [BZ #18875] * math/e_exp2l.c (__ieee754_exp2l): Force underflow exception for small results. * sysdeps/i386/fpu/e_exp2.S (dbl_min): New object. (MO): New macro. (__ieee754_exp2): For small results, force underflow exception and remove excess range and precision from return value. * sysdeps/i386/fpu/e_exp2f.S (flt_min): New object. (MO): New macro. (__ieee754_exp2f): For small results, force underflow exception and remove excess range and precision from return value. * sysdeps/i386/fpu/e_exp2l.S (ldbl_min): New object. (MO): New macro. (__ieee754_exp2l): Force underflow exception for small results. * sysdeps/ieee754/dbl-64/e_exp2.c (__ieee754_exp2): Likewise. * sysdeps/ieee754/flt-32/e_exp2f.c (__ieee754_exp2f): Likewise. * sysdeps/x86_64/fpu/e_exp2l.S (ldbl_min): New object. (MO): New macro. (__ieee754_exp2l): Force underflow exception for small results. * math/auto-libm-test-in: Add more tests or exp2. * math/auto-libm-test-out: Regenerated.
2015-09-14 22:00:12 +00:00
#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. */
fld %st
frndint /* int(x) */
fsubr %st,%st(1) /* fract(x) */
fxch
f2xm1 /* 2^(fract(x)) - 1 */
fld1
faddp /* 2^(fract(x)) */
fscale /* e^x */
fstp %st(1)
Fix exp2 missing underflows (bug 16521). Various exp2 implementations in glibc can miss underflow exceptions when the scaling down part of the calculation is exact (or, in the x86 case, when the conversion from extended precision to the target precision is exact). This patch forces the exception in a similar way to previous fixes. The x86 exp2f changes may in fact not be needed for this purpose - it's likely to be the case that no argument of type float has an exp2 result so close to an exact subnormal float value that it equals that value when rounded to 64 bits (even taking account of variation between different x86 implementations). However, they are included for consistency with the changes to exp2 and so as to fix the exp2f part of bug 18875 by ensuring that excess range and precision is removed from underflowing return values. Tested for x86_64, x86 and mips64. [BZ #16521] [BZ #18875] * math/e_exp2l.c (__ieee754_exp2l): Force underflow exception for small results. * sysdeps/i386/fpu/e_exp2.S (dbl_min): New object. (MO): New macro. (__ieee754_exp2): For small results, force underflow exception and remove excess range and precision from return value. * sysdeps/i386/fpu/e_exp2f.S (flt_min): New object. (MO): New macro. (__ieee754_exp2f): For small results, force underflow exception and remove excess range and precision from return value. * sysdeps/i386/fpu/e_exp2l.S (ldbl_min): New object. (MO): New macro. (__ieee754_exp2l): Force underflow exception for small results. * sysdeps/ieee754/dbl-64/e_exp2.c (__ieee754_exp2): Likewise. * sysdeps/ieee754/flt-32/e_exp2f.c (__ieee754_exp2f): Likewise. * sysdeps/x86_64/fpu/e_exp2l.S (ldbl_min): New object. (MO): New macro. (__ieee754_exp2l): Force underflow exception for small results. * math/auto-libm-test-in: Add more tests or exp2. * math/auto-libm-test-out: Regenerated.
2015-09-14 22:00:12 +00:00
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_exp2f)
strong_alias (__ieee754_exp2f, __exp2f_finite)