diff options
author | senorblanco@chromium.org <senorblanco@chromium.org@2bbb7eff-a529-9590-31e7-b0007b416f81> | 2010-12-16 19:07:45 +0000 |
---|---|---|
committer | senorblanco@chromium.org <senorblanco@chromium.org@2bbb7eff-a529-9590-31e7-b0007b416f81> | 2010-12-16 19:07:45 +0000 |
commit | 29e5054dd07c97c2195c5f64bf67aaa6b5afa204 (patch) | |
tree | bdd024a5cce23ce7f26151fe09b6e4a0d5f8ede4 /Makefile | |
parent | 31e623003472d98d8623b72b8535220c400c4058 (diff) |
Fix perf regression in Color32.
The regression was due to the fact that we were calling PlatformColorProc() for
every span (which in turns makes CPUID, a fairly expensive call). Since we draw
a lot of rects, and rects have 1-pixel wide spans for the vertical segments,
that's a lot of CPUID.
Fixed by cacheing the result of PlatformColorProc(), as is done for the other
platform-specific blitters.
Review URL: http://codereview.appspot.com/3669042/
git-svn-id: http://skia.googlecode.com/svn/trunk@636 2bbb7eff-a529-9590-31e7-b0007b416f81
Diffstat (limited to 'Makefile')
-rw-r--r-- | Makefile | 1 |
1 files changed, 1 insertions, 0 deletions
@@ -94,6 +94,7 @@ endif # For these files, and these files only, compile with -msse2. SSE2_OBJS := out/src/opts/SkBlitRow_opts_SSE2.o \ + out/src/opts/SkBitmapProcState_opts_SSE2.o \ out/src/opts/SkUtils_opts_SSE2.o $(SSE2_OBJS) : CFLAGS := $(CFLAGS_SSE2) |