Re: [PATCH v2 03/10] i386: Use generic fmod

[Adhemerval Zanella Netto <adhemerval.zanella@linaro.org>]

On 27/03/24 16:55, H.J. Lu wrote:
> On Wed, Mar 27, 2024 at 12:40 PM Adhemerval Zanella
> <adhemerval.zanella@linaro.org> wrote:
>>
>> The benchtest results shows a slight improvement (Ryzen 5900, gcc
>> 13.2.1):
>>
>> * sysdeps/i386/fpu/e_fmod.S:
>>   "fmod": {
>>    "subnormals": {
>>     "duration": 3.68855e+09,
>>     "iterations": 2.12608e+08,
>>     "max": 62.012,
>>     "min": 16.798,
>>     "mean": 17.349
>>    },
>>    "normal": {
>>     "duration": 3.88459e+09,
>>     "iterations": 7.168e+06,
>>     "max": 2879.12,
>>     "min": 16.909,
>>     "mean": 541.934
>>    },
>>    "close-exponents": {
>>     "duration": 3.692e+09,
>>     "iterations": 1.96608e+08,
>>     "max": 66.452,
>>     "min": 16.835,
>>     "mean": 18.7785
>>    }
>>   }
>>
>> * generic
>>   "fmod": {
>>    "subnormals": {
>>     "duration": 3.68645e+09,
>>     "iterations": 2.2848e+08,
>>     "max": 66.896,
>>     "min": 15.91,
>>     "mean": 16.1347
>>    },
>>    "normal": {
>>     "duration": 4.1455e+09,
>>     "iterations": 8.192e+06,
>>     "max": 3376.18,
>>     "min": 15.873,
>>     "mean": 506.043
>>    },
>>    "close-exponents": {
>>     "duration": 3.70197e+09,
>>     "iterations": 2.08896e+08,
>>     "max": 69.597,
>>     "min": 15.947,
>>     "mean": 17.7216
>>    }
>>   }
>> ---
>>  sysdeps/i386/fpu/Versions                 |  4 ++++
>>  sysdeps/i386/fpu/e_fmod.S                 | 18 ------------------
>>  sysdeps/i386/fpu/e_fmod.c                 |  2 ++
>>  sysdeps/i386/fpu/math_err.c               |  1 -
>>  sysdeps/i386/fpu/w_fmod_compat.c          | 15 ---------------
>>  sysdeps/ieee754/dbl-64/e_fmod.c           |  5 ++++-
>>  sysdeps/mach/hurd/i386/libm.abilist       |  1 +
>>  sysdeps/unix/sysv/linux/i386/libm.abilist |  1 +
>>  8 files changed, 12 insertions(+), 35 deletions(-)
>>  delete mode 100644 sysdeps/i386/fpu/e_fmod.S
>>  create mode 100644 sysdeps/i386/fpu/e_fmod.c
>>  delete mode 100644 sysdeps/i386/fpu/math_err.c
>>  delete mode 100644 sysdeps/i386/fpu/w_fmod_compat.c
>>
>> diff --git a/sysdeps/i386/fpu/Versions b/sysdeps/i386/fpu/Versions
>> index a2eec371f1..d37bc1eae6 100644
>> --- a/sysdeps/i386/fpu/Versions
>> +++ b/sysdeps/i386/fpu/Versions
>> @@ -3,4 +3,8 @@ libm {
>>      # functions used in inline functions or macros
>>      __expl; __expm1l;
>>    }
>> +  GLIBC_2.40 {
>> +    # No SVID compatible error handling.
>> +    fmod;
>> +  }
> 
> This changes the ABI.  I assume that it fixes a real bug.   Is there a bug
> report open for this?
> 

The new version is the way to provide the system without the SVID compat
support, which we for all ABIs but i386 on 2.38. For instance:

find . -iname libm.abilist | xargs grep -w fmod
./sysdeps/unix/sysv/linux/sparc/sparc32/libm.abilist:GLIBC_2.0 fmod F
./sysdeps/unix/sysv/linux/sparc/sparc32/libm.abilist:GLIBC_2.38 fmod F
[...]

For i386 specifically, the old SVID symbol will be kept as fmod@GLIBC_2.0.

>>  }
>> diff --git a/sysdeps/i386/fpu/e_fmod.S b/sysdeps/i386/fpu/e_fmod.S
>> deleted file mode 100644
>> index 86ac1bcfaf..0000000000
>> --- a/sysdeps/i386/fpu/e_fmod.S
>> +++ /dev/null
>> @@ -1,18 +0,0 @@
>> -/*
>> - * Public domain.
>> - */
>> -
>> -#include <machine/asm.h>
>> -#include <libm-alias-finite.h>
>> -
>> -ENTRY(__ieee754_fmod)
>> -       fldl    12(%esp)
>> -       fldl    4(%esp)
>> -1:     fprem
>> -       fstsw   %ax
>> -       sahf
>> -       jp      1b
>> -       fstp    %st(1)
>> -       ret
>> -END (__ieee754_fmod)
>> -libm_alias_finite (__ieee754_fmod, __fmod)
>> diff --git a/sysdeps/i386/fpu/e_fmod.c b/sysdeps/i386/fpu/e_fmod.c
>> new file mode 100644
>> index 0000000000..3625758f97
>> --- /dev/null
>> +++ b/sysdeps/i386/fpu/e_fmod.c
>> @@ -0,0 +1,2 @@
>> +#define FMOD_VERSION GLIBC_2_40
>> +#include <sysdeps/ieee754/dbl-64/e_fmod.c>
>> diff --git a/sysdeps/i386/fpu/math_err.c b/sysdeps/i386/fpu/math_err.c
>> deleted file mode 100644
>> index 1cc8931700..0000000000
>> --- a/sysdeps/i386/fpu/math_err.c
>> +++ /dev/null
>> @@ -1 +0,0 @@
>> -/* Not needed.  */
>> diff --git a/sysdeps/i386/fpu/w_fmod_compat.c b/sysdeps/i386/fpu/w_fmod_compat.c
>> deleted file mode 100644
>> index 528bfc2a13..0000000000
>> --- a/sysdeps/i386/fpu/w_fmod_compat.c
>> +++ /dev/null
>> @@ -1,15 +0,0 @@
>> -/* i386 provides an optimized __ieee752_fmod.  */
>> -#include <math-svid-compat.h>
>> -#ifdef SHARED
>> -# undef SHLIB_COMPAT
>> -# define SHLIB_COMPAT(a, b, c) 1
>> -# undef LIBM_SVID_COMPAT
>> -# define LIBM_SVID_COMPAT 1
>> -# undef compat_symbol
>> -# define compat_symbol(a, b, c, d)
>> -# include <math/w_fmod_compat.c>
>> -libm_alias_double (__fmod_compat, fmod)
>> -#else
>> -#include <math-type-macros-double.h>
>> -#include <w_fmod_template.c>
>> -#endif
>> diff --git a/sysdeps/ieee754/dbl-64/e_fmod.c b/sysdeps/ieee754/dbl-64/e_fmod.c
>> index b33cfb1223..7651cd212a 100644
>> --- a/sysdeps/ieee754/dbl-64/e_fmod.c
>> +++ b/sysdeps/ieee754/dbl-64/e_fmod.c
>> @@ -175,7 +175,10 @@ __fmod (double x, double y)
>>  strong_alias (__fmod, __ieee754_fmod)
>>  libm_alias_finite (__ieee754_fmod, __fmod)
>>  #if LIBM_SVID_COMPAT
>> -versioned_symbol (libm, __fmod, fmod, GLIBC_2_38);
>> +# ifndef FMOD_VERSION
>> +#  define FMOD_VERSION GLIBC_2_38
>> +# endif
>> +versioned_symbol (libm, __fmod, fmod, FMOD_VERSION);
>>  libm_alias_double_other (__fmod, fmod)
>>  #else
>>  libm_alias_double (__fmod, fmod)
>> diff --git a/sysdeps/mach/hurd/i386/libm.abilist b/sysdeps/mach/hurd/i386/libm.abilist
>> index 8f40ddb150..30665f8b1a 100644
>> --- a/sysdeps/mach/hurd/i386/libm.abilist
>> +++ b/sysdeps/mach/hurd/i386/libm.abilist
>> @@ -1181,3 +1181,4 @@ GLIBC_2.35 fsqrt F
>>  GLIBC_2.35 fsqrtl F
>>  GLIBC_2.35 hypot F
>>  GLIBC_2.35 hypotf F
>> +GLIBC_2.40 fmod F
>> diff --git a/sysdeps/unix/sysv/linux/i386/libm.abilist b/sysdeps/unix/sysv/linux/i386/libm.abilist
>> index 5d89aaa08e..44932f111d 100644
>> --- a/sysdeps/unix/sysv/linux/i386/libm.abilist
>> +++ b/sysdeps/unix/sysv/linux/i386/libm.abilist
>> @@ -1188,3 +1188,4 @@ GLIBC_2.35 fsqrt F
>>  GLIBC_2.35 fsqrtl F
>>  GLIBC_2.35 hypot F
>>  GLIBC_2.35 hypotf F
>> +GLIBC_2.40 fmod F
>> --
>> 2.34.1
>>
> 
>