Simple workaround to use fast computation is to use functions from spec.
header similar to following:
#ifndef FAST_MATH_H
#define FAST_MATH_H
#include
inline double fast_sin(long double x) {
return sinl(x);
}
inline double fast_cos(long double x) {
return cosl(x);
}
inline double fast
Public bug reported:
Memmove and memcpy operations in lic6 and libc6-dev packages are very slow on
new CPUs (Intel i5, ...).
It's possible to meassure it in the STRING SORT test of nbench benchmark.
http://www.tux.org/~mayer/linux/bmark.html
When linked with manually compiled eglibc 2.13 sources,
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/853969
Title:
slow memmove/memcpy on new CPUs
To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/eglibc/+bug/853969
lt; "end: " << diftime / 100ll << '.' << setw(6) << setfill('0') <<
diftime % 100ll << " s" << endl;
return (EXIT_SUCCESS);
}
Petr Cervenka
** Affects: glibc (Ubuntu)
Importance: Undecided
