mirror of
https://sourceware.org/git/glibc.git
synced 2025-08-07 06:43:00 +03:00
56c81132cc
The instructions xsxexpdp and xsxexpqp introduced on POWER9 extract the exponent from a double-precision and quad-precision floating-point respectively, thus they can be used to improve ilogb, ilogbf and ilogbf128.
5 lines
169 B
C
5 lines
169 B
C
/* Skip the optimization for long double as ibm128 does not provide an
|
|
optimized builtin. */
|
|
#include <math-type-macros-ldouble.h>
|
|
#include <math/w_ilogb_template.c>
|