diff mbox series

[v2,04/10] i386: Use generic fmodf

Message ID 20240327194024.1409677-5-adhemerval.zanella@linaro.org
State New
Headers show
Series Fix some libm static issues | expand

Commit Message

Adhemerval Zanella Netto March 27, 2024, 7:40 p.m. UTC 
The resulting performance is similiar (Ryzen 5900, gcc 13.2.1):

* sysdeps/i386/fpu/e_fmodf.S
  "fmodf": {
   "subnormals": {
    "duration": 3.68732e+09,
    "iterations": 2.2912e+08,
    "max": 71.447,
    "min": 15.836,
    "mean": 16.0934
   },
   "normal": {
    "duration": 3.75848e+09,
    "iterations": 5.5296e+07,
    "max": 273.208,
    "min": 15.725,
    "mean": 67.9702
   },
   "close-exponents": {
    "duration": 3.69035e+09,
    "iterations": 2.07872e+08,
    "max": 64.454,
    "min": 15.762,
    "mean": 17.753
   }
  }

* master
  "fmodf": {
   "subnormals": {
    "duration": 3.6863e+09,
    "iterations": 2.23616e+08,
    "max": 65.453,
    "min": 16.243,
    "mean": 16.485
   },
   "normal": {
    "duration": 3.71129e+09,
    "iterations": 5.3248e+07,
    "max": 281.57,
    "min": 16.169,
    "mean": 69.6983
   },
   "close-exponents": {
    "duration": 3.70274e+09,
    "iterations": 2.03776e+08,
    "max": 81.474,
    "min": 16.206,
    "mean": 18.1706
   }
  }
---
 sysdeps/i386/fpu/Versions                 |  2 +-
 sysdeps/i386/fpu/e_fmodf.S                | 18 ------------------
 sysdeps/i386/fpu/e_fmodf.c                |  2 ++
 sysdeps/i386/fpu/w_fmodf_compat.c         | 15 ---------------
 sysdeps/ieee754/flt-32/e_fmodf.c          |  5 ++++-
 sysdeps/mach/hurd/i386/libm.abilist       |  1 +
 sysdeps/unix/sysv/linux/i386/libm.abilist |  1 +
 7 files changed, 9 insertions(+), 35 deletions(-)
 delete mode 100644 sysdeps/i386/fpu/e_fmodf.S
 create mode 100644 sysdeps/i386/fpu/e_fmodf.c
 delete mode 100644 sysdeps/i386/fpu/w_fmodf_compat.c

Comments

H.J. Lu March 27, 2024, 7:55 p.m. UTC | #1 
On Wed, Mar 27, 2024 at 12:40 PM Adhemerval Zanella
<adhemerval.zanella@linaro.org> wrote:
>
> The resulting performance is similiar (Ryzen 5900, gcc 13.2.1):
>
> * sysdeps/i386/fpu/e_fmodf.S
>   "fmodf": {
>    "subnormals": {
>     "duration": 3.68732e+09,
>     "iterations": 2.2912e+08,
>     "max": 71.447,
>     "min": 15.836,
>     "mean": 16.0934
>    },
>    "normal": {
>     "duration": 3.75848e+09,
>     "iterations": 5.5296e+07,
>     "max": 273.208,
>     "min": 15.725,
>     "mean": 67.9702
>    },
>    "close-exponents": {
>     "duration": 3.69035e+09,
>     "iterations": 2.07872e+08,
>     "max": 64.454,
>     "min": 15.762,
>     "mean": 17.753
>    }
>   }
>
> * master
>   "fmodf": {
>    "subnormals": {
>     "duration": 3.6863e+09,
>     "iterations": 2.23616e+08,
>     "max": 65.453,
>     "min": 16.243,
>     "mean": 16.485
>    },
>    "normal": {
>     "duration": 3.71129e+09,
>     "iterations": 5.3248e+07,
>     "max": 281.57,
>     "min": 16.169,
>     "mean": 69.6983
>    },
>    "close-exponents": {
>     "duration": 3.70274e+09,
>     "iterations": 2.03776e+08,
>     "max": 81.474,
>     "min": 16.206,
>     "mean": 18.1706
>    }
>   }
> ---
>  sysdeps/i386/fpu/Versions                 |  2 +-
>  sysdeps/i386/fpu/e_fmodf.S                | 18 ------------------
>  sysdeps/i386/fpu/e_fmodf.c                |  2 ++
>  sysdeps/i386/fpu/w_fmodf_compat.c         | 15 ---------------
>  sysdeps/ieee754/flt-32/e_fmodf.c          |  5 ++++-
>  sysdeps/mach/hurd/i386/libm.abilist       |  1 +
>  sysdeps/unix/sysv/linux/i386/libm.abilist |  1 +
>  7 files changed, 9 insertions(+), 35 deletions(-)
>  delete mode 100644 sysdeps/i386/fpu/e_fmodf.S
>  create mode 100644 sysdeps/i386/fpu/e_fmodf.c
>  delete mode 100644 sysdeps/i386/fpu/w_fmodf_compat.c
>
> diff --git a/sysdeps/i386/fpu/Versions b/sysdeps/i386/fpu/Versions
> index d37bc1eae6..9509f9b7c7 100644
> --- a/sysdeps/i386/fpu/Versions
> +++ b/sysdeps/i386/fpu/Versions
> @@ -5,6 +5,6 @@ libm {
>    }
>    GLIBC_2.40 {
>      # No SVID compatible error handling.
> -    fmod;
> +    fmod; fmodf;
>    }
>  }
> diff --git a/sysdeps/i386/fpu/e_fmodf.S b/sysdeps/i386/fpu/e_fmodf.S
> deleted file mode 100644
> index f73ce9da1e..0000000000
> --- a/sysdeps/i386/fpu/e_fmodf.S
> +++ /dev/null
> @@ -1,18 +0,0 @@
> -/*
> - * Public domain.
> - */
> -
> -#include <machine/asm.h>
> -#include <libm-alias-finite.h>
> -
> -ENTRY(__ieee754_fmodf)
> -       flds    8(%esp)
> -       flds    4(%esp)
> -1:     fprem
> -       fstsw   %ax
> -       sahf
> -       jp      1b
> -       fstp    %st(1)
> -       ret
> -END(__ieee754_fmodf)
> -libm_alias_finite (__ieee754_fmodf, __fmodf)
> diff --git a/sysdeps/i386/fpu/e_fmodf.c b/sysdeps/i386/fpu/e_fmodf.c
> new file mode 100644
> index 0000000000..15a0f960bf
> --- /dev/null
> +++ b/sysdeps/i386/fpu/e_fmodf.c
> @@ -0,0 +1,2 @@
> +#define FMODF_VERSION GLIBC_2_40
> +#include <sysdeps/ieee754/flt-32/e_fmodf.c>
> diff --git a/sysdeps/i386/fpu/w_fmodf_compat.c b/sysdeps/i386/fpu/w_fmodf_compat.c
> deleted file mode 100644
> index 5a61693e51..0000000000
> --- a/sysdeps/i386/fpu/w_fmodf_compat.c
> +++ /dev/null
> @@ -1,15 +0,0 @@
> -/* i386 provides an optimized __ieee752_fmodf.  */
> -#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_fmodf_compat.c>
> -libm_alias_float (__fmod_compat, fmod)
> -#else
> -#include <math-type-macros-float.h>
> -#include <w_fmod_template.c>
> -#endif
> diff --git a/sysdeps/ieee754/flt-32/e_fmodf.c b/sysdeps/ieee754/flt-32/e_fmodf.c
> index ef95c05800..78071df756 100644
> --- a/sysdeps/ieee754/flt-32/e_fmodf.c
> +++ b/sysdeps/ieee754/flt-32/e_fmodf.c
> @@ -173,7 +173,10 @@ __fmodf (float x, float y)
>  }
>  strong_alias (__fmodf, __ieee754_fmodf)
>  #if LIBM_SVID_COMPAT
> -versioned_symbol (libm, __fmodf, fmodf, GLIBC_2_38);
> +# ifndef FMODF_VERSION
> +#  define FMODF_VERSION GLIBC_2_38
> +# endif
> +versioned_symbol (libm, __fmodf, fmodf, FMODF_VERSION);
>  libm_alias_float_other (__fmod, fmod)
>  #else
>  libm_alias_float (__fmod, fmod)
> diff --git a/sysdeps/mach/hurd/i386/libm.abilist b/sysdeps/mach/hurd/i386/libm.abilist
> index 30665f8b1a..88e7538e51 100644
> --- a/sysdeps/mach/hurd/i386/libm.abilist
> +++ b/sysdeps/mach/hurd/i386/libm.abilist
> @@ -1182,3 +1182,4 @@ GLIBC_2.35 fsqrtl F
>  GLIBC_2.35 hypot F
>  GLIBC_2.35 hypotf F
>  GLIBC_2.40 fmod F
> +GLIBC_2.40 fmodf F
> diff --git a/sysdeps/unix/sysv/linux/i386/libm.abilist b/sysdeps/unix/sysv/linux/i386/libm.abilist
> index 44932f111d..c99c60161d 100644
> --- a/sysdeps/unix/sysv/linux/i386/libm.abilist
> +++ b/sysdeps/unix/sysv/linux/i386/libm.abilist
> @@ -1189,3 +1189,4 @@ GLIBC_2.35 fsqrtl F
>  GLIBC_2.35 hypot F
>  GLIBC_2.35 hypotf F
>  GLIBC_2.40 fmod F
> +GLIBC_2.40 fmodf F
> --
> 2.34.1
>

Need a bug report for ABI change.
diff mbox series

Patch

diff --git a/sysdeps/i386/fpu/Versions b/sysdeps/i386/fpu/Versions
index d37bc1eae6..9509f9b7c7 100644
--- a/sysdeps/i386/fpu/Versions
+++ b/sysdeps/i386/fpu/Versions
@@ -5,6 +5,6 @@  libm {
   }
   GLIBC_2.40 {
     # No SVID compatible error handling.
-    fmod;
+    fmod; fmodf;
   }
 }
diff --git a/sysdeps/i386/fpu/e_fmodf.S b/sysdeps/i386/fpu/e_fmodf.S
deleted file mode 100644
index f73ce9da1e..0000000000
--- a/sysdeps/i386/fpu/e_fmodf.S
+++ /dev/null
@@ -1,18 +0,0 @@ 
-/*
- * Public domain.
- */
-
-#include <machine/asm.h>
-#include <libm-alias-finite.h>
-
-ENTRY(__ieee754_fmodf)
-	flds	8(%esp)
-	flds	4(%esp)
-1:	fprem
-	fstsw	%ax
-	sahf
-	jp	1b
-	fstp	%st(1)
-	ret
-END(__ieee754_fmodf)
-libm_alias_finite (__ieee754_fmodf, __fmodf)
diff --git a/sysdeps/i386/fpu/e_fmodf.c b/sysdeps/i386/fpu/e_fmodf.c
new file mode 100644
index 0000000000..15a0f960bf
--- /dev/null
+++ b/sysdeps/i386/fpu/e_fmodf.c
@@ -0,0 +1,2 @@ 
+#define FMODF_VERSION GLIBC_2_40
+#include <sysdeps/ieee754/flt-32/e_fmodf.c>
diff --git a/sysdeps/i386/fpu/w_fmodf_compat.c b/sysdeps/i386/fpu/w_fmodf_compat.c
deleted file mode 100644
index 5a61693e51..0000000000
--- a/sysdeps/i386/fpu/w_fmodf_compat.c
+++ /dev/null
@@ -1,15 +0,0 @@ 
-/* i386 provides an optimized __ieee752_fmodf.  */
-#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_fmodf_compat.c>
-libm_alias_float (__fmod_compat, fmod)
-#else
-#include <math-type-macros-float.h>
-#include <w_fmod_template.c>
-#endif
diff --git a/sysdeps/ieee754/flt-32/e_fmodf.c b/sysdeps/ieee754/flt-32/e_fmodf.c
index ef95c05800..78071df756 100644
--- a/sysdeps/ieee754/flt-32/e_fmodf.c
+++ b/sysdeps/ieee754/flt-32/e_fmodf.c
@@ -173,7 +173,10 @@  __fmodf (float x, float y)
 }
 strong_alias (__fmodf, __ieee754_fmodf)
 #if LIBM_SVID_COMPAT
-versioned_symbol (libm, __fmodf, fmodf, GLIBC_2_38);
+# ifndef FMODF_VERSION
+#  define FMODF_VERSION GLIBC_2_38
+# endif
+versioned_symbol (libm, __fmodf, fmodf, FMODF_VERSION);
 libm_alias_float_other (__fmod, fmod)
 #else
 libm_alias_float (__fmod, fmod)
diff --git a/sysdeps/mach/hurd/i386/libm.abilist b/sysdeps/mach/hurd/i386/libm.abilist
index 30665f8b1a..88e7538e51 100644
--- a/sysdeps/mach/hurd/i386/libm.abilist
+++ b/sysdeps/mach/hurd/i386/libm.abilist
@@ -1182,3 +1182,4 @@  GLIBC_2.35 fsqrtl F
 GLIBC_2.35 hypot F
 GLIBC_2.35 hypotf F
 GLIBC_2.40 fmod F
+GLIBC_2.40 fmodf F
diff --git a/sysdeps/unix/sysv/linux/i386/libm.abilist b/sysdeps/unix/sysv/linux/i386/libm.abilist
index 44932f111d..c99c60161d 100644
--- a/sysdeps/unix/sysv/linux/i386/libm.abilist
+++ b/sysdeps/unix/sysv/linux/i386/libm.abilist
@@ -1189,3 +1189,4 @@  GLIBC_2.35 fsqrtl F
 GLIBC_2.35 hypot F
 GLIBC_2.35 hypotf F
 GLIBC_2.40 fmod F
+GLIBC_2.40 fmodf F