This website requires JavaScript.
Explore
Help
Sign In
mirrors
/
0ad
Watch
1
Star
0
Fork
2
You've already forked 0ad
mirror of
https://gitea.wildfiregames.com/0ad/0ad.git
synced
2026-07-19 04:56:18 +00:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
Files
dd031d53673b51bba1cceb712dd6afd264f92f86
0ad
/
source
/
lib
/
sysdep
T
History
janwas
20d038efda
profiling indicates memcpy is a bottleneck, so globally replace all of them with memcpy2 (hand-optimized). depending on transfer size, this is 10%..300% faster. also made memcpy2 into a macro instead of thunk function because vc7 was still generating a jump.
...
This was SVN commit r3057.
2005-10-30 16:19:20 +00:00
..
unix
debug_putws was causing trouble on linux when mixing char and wchar_t writes to file. accordingly, have debug_wprintf do wchar->utf8 conversion (done there instead of in debug_putws because it's needed for the filtering logic as well) and call its char* equivalent and remove debug_putws.
2005-10-24 03:20:54 +00:00
win
profiling indicates memcpy is a bottleneck, so globally replace all of them with memcpy2 (hand-optimized). depending on transfer size, this is 10%..300% faster. also made memcpy2 into a macro instead of thunk function because vc7 was still generating a jump.
2005-10-30 16:19:20 +00:00
cpu.h
Stab at fixing the VertexArray compile error on VC++.
2005-10-03 03:41:42 +00:00
dir_watch.h
…
gfx.h
sysdep: add restrict keyword (placebo if not supported)
2005-10-12 04:22:44 +00:00
ia32.asm
sdl: remove complicated mouse button check/workaround; that's now done in Interact.cpp (which makes the assumptions being tested)
2005-10-24 00:06:08 +00:00
ia32.cpp
allocators: add include guard and posix.h (needed for PROT_*)
2005-10-29 02:32:36 +00:00
ia32.h
allocators: add include guard and posix.h (needed for PROT_*)
2005-10-29 02:32:36 +00:00
os.h
…
snd.h
…
sysdep.cpp
profiling indicates memcpy is a bottleneck, so globally replace all of them with memcpy2 (hand-optimized). depending on transfer size, this is 10%..300% faster. also made memcpy2 into a macro instead of thunk function because vc7 was still generating a jump.
2005-10-30 16:19:20 +00:00
sysdep.h
profiling indicates memcpy is a bottleneck, so globally replace all of them with memcpy2 (hand-optimized). depending on transfer size, this is 10%..300% faster. also made memcpy2 into a macro instead of thunk function because vc7 was still generating a jump.
2005-10-30 16:19:20 +00:00