(svn r26213) -Add: specialised non-animated SSE4 blitter (MJP)

With 32bpp base set about 40% faster than 32bpp-optimized, or about 10% for 8bpp base sets in the Draw function. Respectively about 8 and 1% of total run time
2014-01-02 23:21:07 +00:00
parent 730127b67e
commit e25733c417
7 changed files with 420 additions and 0 deletions
--- a/source.list
+++ b/source.list
@@ -910,6 +910,8 @@ blitter/32bpp_simple.hpp
 #if WITH_SSE
 blitter/32bpp_sse2.cpp
 blitter/32bpp_sse2.hpp
+blitter/32bpp_sse4.cpp
+blitter/32bpp_sse4.hpp
 blitter/32bpp_ssse3.cpp
 blitter/32bpp_ssse3.hpp
 #end