mirror of
git://sourceware.org/git/glibc.git
synced 2024-11-21 01:12:26 +08:00
2506109403
The most common use case of math functions is with default rounding mode, i.e. rounding to nearest. Setting and restoring rounding mode is an unnecessary overhead for this, so I've added support for a context, which does the set/restore only if the FP status needs a change. The code is written such that only x86 uses these. Other architectures should be unaffected by it, but would definitely benefit if the set/restore has as much overhead relative to the rest of the code, as the x86 bits do. Here's a summary of the performance improvement due to these improvements; I've only mentioned functions that use the set/restore and have benchmark inputs for x86_64: Before: cos(): ITERS:4.69335e+08: TOTAL:28884.6Mcy, MAX:4080.28cy, MIN:57.562cy, 16248.6 calls/Mcy exp(): ITERS:4.47604e+08: TOTAL:28796.2Mcy, MAX:207.721cy, MIN:62.385cy, 15543.9 calls/Mcy pow(): ITERS:1.63485e+08: TOTAL:28879.9Mcy, MAX:362.255cy, MIN:172.469cy, 5660.86 calls/Mcy sin(): ITERS:3.89578e+08: TOTAL:28900Mcy, MAX:704.859cy, MIN:47.583cy, 13480.2 calls/Mcy tan(): ITERS:7.0971e+07: TOTAL:28902.2Mcy, MAX:1357.79cy, MIN:388.58cy, 2455.55 calls/Mcy After: cos(): ITERS:6.0014e+08: TOTAL:28875.9Mcy, MAX:364.283cy, MIN:45.716cy, 20783.4 calls/Mcy exp(): ITERS:5.48578e+08: TOTAL:28764.9Mcy, MAX:191.617cy, MIN:51.011cy, 19071.1 calls/Mcy pow(): ITERS:1.70013e+08: TOTAL:28873.6Mcy, MAX:689.522cy, MIN:163.989cy, 5888.18 calls/Mcy sin(): ITERS:4.64079e+08: TOTAL:28891.5Mcy, MAX:6959.3cy, MIN:36.189cy, 16062.8 calls/Mcy tan(): ITERS:7.2354e+07: TOTAL:28898.9Mcy, MAX:1295.57cy, MIN:380.698cy, 2503.7 calls/Mcy So the improvements are: cos: 27.9089% exp: 22.6919% pow: 4.01564% sin: 19.1585% tan: 1.96086% The downside of the change is that it will have an adverse performance impact on non-default rounding modes, but I think the tradeoff is justified.
37 lines
1012 B
C
37 lines
1012 B
C
#ifndef _FENV_H
|
|
#include <math/fenv.h>
|
|
#include <stdbool.h>
|
|
|
|
#ifndef _ISOMAC
|
|
/* Now define the internal interfaces. */
|
|
|
|
extern int __feclearexcept (int __excepts);
|
|
extern int __fegetexcept (void);
|
|
extern int __fegetexceptflag (fexcept_t *__flagp, int __excepts);
|
|
extern int __feraiseexcept (int __excepts);
|
|
extern int __fesetexceptflag (const fexcept_t *__flagp, int __excepts);
|
|
extern int __fegetenv (fenv_t *__envp);
|
|
extern int __fesetenv (const fenv_t *__envp);
|
|
extern int __feupdateenv (const fenv_t *__envp);
|
|
|
|
libm_hidden_proto (feraiseexcept)
|
|
libm_hidden_proto (fegetenv)
|
|
libm_hidden_proto (fesetenv)
|
|
libm_hidden_proto (fesetround)
|
|
libm_hidden_proto (feholdexcept)
|
|
libm_hidden_proto (feupdateenv)
|
|
libm_hidden_proto (fetestexcept)
|
|
libm_hidden_proto (feclearexcept)
|
|
#endif
|
|
|
|
/* Rounding mode context. This allows functions to set/restore rounding mode
|
|
only when the desired rounding mode is different from the current rounding
|
|
mode. */
|
|
struct rm_ctx
|
|
{
|
|
fenv_t env;
|
|
bool updated_status;
|
|
};
|
|
|
|
#endif
|