[openbeos] Re: app_server: MMX/SSE help wanted
- From: "Alexander G. M. Smith" <agmsmith@xxxxxxxxxx>
- To: openbeos@xxxxxxxxxxxxx
- Date: Tue, 10 Aug 2004 08:52:32 -0400 EDT
Christian Packmann wrote on Mon, 09 Aug 2004 23:03:49 +0200:
> Even for non-cacheable data and simple operations, SIMD processing (and use
> of data prefetch instructions) can give more than decisive advantages.
Looks like somewhere between 2 and 3 times speedup for large data.
Sure are lots of shift instructions in the C code - that's what MMX does do all
in one operation. I wonder if it would be faster or slower with byte pointers
and math rather than shift operations to extract the bytes. I'd also check the
generated code to make sure *src was not being reloaded for every operation
(copy it to a local variable first in that case) and compile with optimization.
Anyway, it's nice to see those actual numbers!
- Alex
Other related posts:
