glibc/sysdeps/i386/fpu/e_exp2l.S

61 lines
1.2 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>
Refactor i386 libm code forcing underflow exceptions. This patch refactors code in sysdeps/i386/fpu that forces underflow exceptions to use common macros for that purpose as far as possible. (Although some of the macros end up used in only one place, I think it's cleanest to define all these macros together so that all the code forcing underflow uses such macros. Some more uses of such macros will also be introduced when fixing remaining bugs about missing underflow exceptions, and it would be possible to do further refactoring of the macros in i386-math-asm.h to share more code by using other macros internally. Places that test for underflow by examining the representation of the argument with integer operations, rather that using floating-point comparisons on the argument or result, are unchanged by this patch.) Most of this code uses a macro MO to abstract away the differences between PIC and non-PIC memory references to constants. log1p functions, however, hardcoded PIC conditionals for this. Because the common macros rely on the use of MO, I changed the log1p functions to use the normal style here, and, for consistency, also made that change to log1pl which is otherwise unaffected by this patch. Tested for x86. * sysdeps/i386/fpu/i386-math-asm.h (DEFINE_LDBL_MIN): New macro. (FLT_CHECK_FORCE_UFLOW): Likewise. (DBL_CHECK_FORCE_UFLOW): Likewise. (FLT_CHECK_FORCE_UFLOW_NARROW): Likewise. (DBL_CHECK_FORCE_UFLOW_NARROW): Likewise. (LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN): Likewise. (FLT_CHECK_FORCE_UFLOW_NONNAN): Likewise. (DBL_CHECK_FORCE_UFLOW_NONNAN): Likewise. (FLT_CHECK_FORCE_UFLOW_NONNEG): Likewise. (DBL_CHECK_FORCE_UFLOW_NONNEG): Likewise. (LDBL_CHECK_FORCE_UFLOW_NONNEG): Likewise. * sysdeps/i386/fpu/e_asin.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__ieee754_asin): Use DBL_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/e_asinf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__ieee754_asinf): Use FLT_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/e_atan2.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__ieee754_atan2): Use DBL_CHECK_FORCE_UFLOW_NARROW. * sysdeps/i386/fpu/e_atan2f.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__ieee754_atan2f): Use FLT_CHECK_FORCE_UFLOW_NARROW. * sysdeps/i386/fpu/e_atanh.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__ieee754_atanh): Use DBL_CHECK_FORCE_UFLOW_NONNEG. * sysdeps/i386/fpu/e_atanhf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__ieee754_atanhf): Use FLT_CHECK_FORCE_UFLOW_NONNEG. * sysdeps/i386/fpu/e_exp2l.S: Include <i386-math-asm.h>. (ldbl_min): Replace with use of DEFINE_LDBL_MIN. (__ieee754_exp2l): Use LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN. * sysdeps/i386/fpu/e_expl.S: Include <i386-math-asm.h>. [!USE_AS_EXPM1L] (cmin): Replace with use of DEFINE_LDBL_MIN. (IEEE754_EXPL): Use LDBL_CHECK_FORCE_UFLOW_NONNEG. * sysdeps/i386/fpu/s_atan.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__atan): Use DBL_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/s_atanf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__atanf): Use FLT_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/s_expm1.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__expm1): Use DBL_CHECK_FORCE_UFLOW. Move underflow check after main computation. * sysdeps/i386/fpu/s_expm1f.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__expm1f): Use FLT_CHECK_FORCE_UFLOW. Move underflow check after main computation. * sysdeps/i386/fpu/s_log1p.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (MO): New macro. (__log1p): Use MO. Use DBL_CHECK_FORCE_UFLOW_NONNAN. * sysdeps/i386/fpu/s_log1pf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (MO): New macro. (__log1pf): Use MO. Use FLT_CHECK_FORCE_UFLOW_NONNAN. * sysdeps/i386/fpu/s_log1pl.S (MO): New macro. (__log1pl): Use MO.
2015-09-24 21:41:00 +00:00
#include <i386-math-asm.h>
Refactor i386 libm code forcing underflow exceptions. This patch refactors code in sysdeps/i386/fpu that forces underflow exceptions to use common macros for that purpose as far as possible. (Although some of the macros end up used in only one place, I think it's cleanest to define all these macros together so that all the code forcing underflow uses such macros. Some more uses of such macros will also be introduced when fixing remaining bugs about missing underflow exceptions, and it would be possible to do further refactoring of the macros in i386-math-asm.h to share more code by using other macros internally. Places that test for underflow by examining the representation of the argument with integer operations, rather that using floating-point comparisons on the argument or result, are unchanged by this patch.) Most of this code uses a macro MO to abstract away the differences between PIC and non-PIC memory references to constants. log1p functions, however, hardcoded PIC conditionals for this. Because the common macros rely on the use of MO, I changed the log1p functions to use the normal style here, and, for consistency, also made that change to log1pl which is otherwise unaffected by this patch. Tested for x86. * sysdeps/i386/fpu/i386-math-asm.h (DEFINE_LDBL_MIN): New macro. (FLT_CHECK_FORCE_UFLOW): Likewise. (DBL_CHECK_FORCE_UFLOW): Likewise. (FLT_CHECK_FORCE_UFLOW_NARROW): Likewise. (DBL_CHECK_FORCE_UFLOW_NARROW): Likewise. (LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN): Likewise. (FLT_CHECK_FORCE_UFLOW_NONNAN): Likewise. (DBL_CHECK_FORCE_UFLOW_NONNAN): Likewise. (FLT_CHECK_FORCE_UFLOW_NONNEG): Likewise. (DBL_CHECK_FORCE_UFLOW_NONNEG): Likewise. (LDBL_CHECK_FORCE_UFLOW_NONNEG): Likewise. * sysdeps/i386/fpu/e_asin.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__ieee754_asin): Use DBL_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/e_asinf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__ieee754_asinf): Use FLT_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/e_atan2.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__ieee754_atan2): Use DBL_CHECK_FORCE_UFLOW_NARROW. * sysdeps/i386/fpu/e_atan2f.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__ieee754_atan2f): Use FLT_CHECK_FORCE_UFLOW_NARROW. * sysdeps/i386/fpu/e_atanh.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__ieee754_atanh): Use DBL_CHECK_FORCE_UFLOW_NONNEG. * sysdeps/i386/fpu/e_atanhf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__ieee754_atanhf): Use FLT_CHECK_FORCE_UFLOW_NONNEG. * sysdeps/i386/fpu/e_exp2l.S: Include <i386-math-asm.h>. (ldbl_min): Replace with use of DEFINE_LDBL_MIN. (__ieee754_exp2l): Use LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN. * sysdeps/i386/fpu/e_expl.S: Include <i386-math-asm.h>. [!USE_AS_EXPM1L] (cmin): Replace with use of DEFINE_LDBL_MIN. (IEEE754_EXPL): Use LDBL_CHECK_FORCE_UFLOW_NONNEG. * sysdeps/i386/fpu/s_atan.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__atan): Use DBL_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/s_atanf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__atanf): Use FLT_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/s_expm1.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__expm1): Use DBL_CHECK_FORCE_UFLOW. Move underflow check after main computation. * sysdeps/i386/fpu/s_expm1f.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__expm1f): Use FLT_CHECK_FORCE_UFLOW. Move underflow check after main computation. * sysdeps/i386/fpu/s_log1p.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (MO): New macro. (__log1p): Use MO. Use DBL_CHECK_FORCE_UFLOW_NONNAN. * sysdeps/i386/fpu/s_log1pf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (MO): New macro. (__log1pf): Use MO. Use FLT_CHECK_FORCE_UFLOW_NONNAN. * sysdeps/i386/fpu/s_log1pl.S (MO): New macro. (__log1pl): Use MO.
2015-09-24 21:41:00 +00:00
DEFINE_LDBL_MIN
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
# define MO(op) op##@GOTOFF(%ecx)
#else
# define MO(op) op
#endif
.text
ENTRY(__ieee754_exp2l)
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
fldt 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. */
movzwl 4+8(%esp), %eax
andl $0x7fff, %eax
cmpl $0x3fbe, %eax
jge 3f
/* Argument's exponent below -65, result rounds to 1. */
fld1
faddp
ret
3: 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)
Refactor i386 libm code forcing underflow exceptions. This patch refactors code in sysdeps/i386/fpu that forces underflow exceptions to use common macros for that purpose as far as possible. (Although some of the macros end up used in only one place, I think it's cleanest to define all these macros together so that all the code forcing underflow uses such macros. Some more uses of such macros will also be introduced when fixing remaining bugs about missing underflow exceptions, and it would be possible to do further refactoring of the macros in i386-math-asm.h to share more code by using other macros internally. Places that test for underflow by examining the representation of the argument with integer operations, rather that using floating-point comparisons on the argument or result, are unchanged by this patch.) Most of this code uses a macro MO to abstract away the differences between PIC and non-PIC memory references to constants. log1p functions, however, hardcoded PIC conditionals for this. Because the common macros rely on the use of MO, I changed the log1p functions to use the normal style here, and, for consistency, also made that change to log1pl which is otherwise unaffected by this patch. Tested for x86. * sysdeps/i386/fpu/i386-math-asm.h (DEFINE_LDBL_MIN): New macro. (FLT_CHECK_FORCE_UFLOW): Likewise. (DBL_CHECK_FORCE_UFLOW): Likewise. (FLT_CHECK_FORCE_UFLOW_NARROW): Likewise. (DBL_CHECK_FORCE_UFLOW_NARROW): Likewise. (LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN): Likewise. (FLT_CHECK_FORCE_UFLOW_NONNAN): Likewise. (DBL_CHECK_FORCE_UFLOW_NONNAN): Likewise. (FLT_CHECK_FORCE_UFLOW_NONNEG): Likewise. (DBL_CHECK_FORCE_UFLOW_NONNEG): Likewise. (LDBL_CHECK_FORCE_UFLOW_NONNEG): Likewise. * sysdeps/i386/fpu/e_asin.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__ieee754_asin): Use DBL_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/e_asinf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__ieee754_asinf): Use FLT_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/e_atan2.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__ieee754_atan2): Use DBL_CHECK_FORCE_UFLOW_NARROW. * sysdeps/i386/fpu/e_atan2f.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__ieee754_atan2f): Use FLT_CHECK_FORCE_UFLOW_NARROW. * sysdeps/i386/fpu/e_atanh.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__ieee754_atanh): Use DBL_CHECK_FORCE_UFLOW_NONNEG. * sysdeps/i386/fpu/e_atanhf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__ieee754_atanhf): Use FLT_CHECK_FORCE_UFLOW_NONNEG. * sysdeps/i386/fpu/e_exp2l.S: Include <i386-math-asm.h>. (ldbl_min): Replace with use of DEFINE_LDBL_MIN. (__ieee754_exp2l): Use LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN. * sysdeps/i386/fpu/e_expl.S: Include <i386-math-asm.h>. [!USE_AS_EXPM1L] (cmin): Replace with use of DEFINE_LDBL_MIN. (IEEE754_EXPL): Use LDBL_CHECK_FORCE_UFLOW_NONNEG. * sysdeps/i386/fpu/s_atan.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__atan): Use DBL_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/s_atanf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__atanf): Use FLT_CHECK_FORCE_UFLOW. * sysdeps/i386/fpu/s_expm1.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (__expm1): Use DBL_CHECK_FORCE_UFLOW. Move underflow check after main computation. * sysdeps/i386/fpu/s_expm1f.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (__expm1f): Use FLT_CHECK_FORCE_UFLOW. Move underflow check after main computation. * sysdeps/i386/fpu/s_log1p.S: Include <i386-math-asm.h>. (dbl_min): Replace with use of DEFINE_DBL_MIN. (MO): New macro. (__log1p): Use MO. Use DBL_CHECK_FORCE_UFLOW_NONNAN. * sysdeps/i386/fpu/s_log1pf.S: Include <i386-math-asm.h>. (flt_min): Replace with use of DEFINE_FLT_MIN. (MO): New macro. (__log1pf): Use MO. Use FLT_CHECK_FORCE_UFLOW_NONNAN. * sysdeps/i386/fpu/s_log1pl.S (MO): New macro. (__log1pl): Use MO.
2015-09-24 21:41:00 +00:00
LDBL_CHECK_FORCE_UFLOW_NONNEG_NAN
ret
1: testl $0x200, %eax /* Test sign. */
jz 2f /* If positive, jump. */
fstp %st
fldz /* Set result to 0. */
2: ret
END (__ieee754_exp2l)
strong_alias (__ieee754_exp2l, __exp2l_finite)