Bruce Evans 828f7b4a82 Rearrange the polynomial evaluation for better parallelism. This is ... faster on all machines tested (old Celeron (P2), A64 (amd64 and i386) and ia64) except on ia64 when compiled with -O1. It takes 2 more multiplications, so it will be slower on old machines. The speedup is about 8 cycles = 17% on A64 (amd64 and i386) with best CFLAGS and some parallelism in the caller. Move the evaluation of 2**k up a bit so that it doesn't compete too much with the new polynomial evaluation. Unlike the previous optimization, this rearrangement cannot change the result, so compilers and CPU schedulers can do it, but they don't do it quite right yet. This saves a whole 1 or 2 cycles on A64.		2008-02-13 08:36:13 +00:00
..
amd64	Use hardware remainder on amd64 since it is 5 to 10 times faster than	2008-02-13 06:01:48 +00:00
arm
bsdsrc
i387	Implement rintl(), nearbyintl(), lrintl(), and llrintl().	2008-01-14 02:12:07 +00:00
ia64
ld80	Use a better method of scaling by 2**k. Instead of adding to the	2008-02-07 03:17:05 +00:00
ld128	Use a better method of scaling by 2**k. Instead of adding to the	2008-02-07 03:17:05 +00:00
man	Introduce a new log(3) manpage and move the relevant functions there.	2008-01-18 21:43:00 +00:00
powerpc
sparc64
src	Rearrange the polynomial evaluation for better parallelism. This is	2008-02-13 08:36:13 +00:00
Makefile	Hook up exp2l() and related docs to the build.	2008-01-18 21:43:10 +00:00
Symbol.map	Hook up exp2l() and related docs to the build.	2008-01-18 21:43:10 +00:00