[ Thread Index |
Date Index
| More lists.liballeg.org/allegro-developers Archives
]
Eric Botcazou wrote:
[snip]
Do you mean that calling sincos() takes as much time as calling sin() then
cos() ? Even at the CPU level ? Ouch! Then we have just been fooled by the
Intel engineers ;-)
Well, the Pentium Optimization Guide gives me:
Function: Issue (p0): Delay:
FSIN, FCOS 17-97 27-103
FSINCOS 18-110 29-130
And since they are not pipelined, then FSINCOS is ~2x faster than FSIN +
FCOS. Of course, taking a 50+ cycle hit for a function call and memory
writes pretty much nullifies any advantage...
--
- Robert J Ohannessian
"Microsoft code is probably O(n^20)" (my CS prof)
http://pages.infinit.net/voidstar/