Simplify difference and exclusion.

We can fold through some math in these two modes.

$ out/ok bench:samples=100 rp filter:search="Difference|Exclusion" serial

Before:
    [blendmode_rect_Exclusion]  4.94ms  @0  6.13ms  @99 6.25ms  @100
    [blendmode_mask_Exclusion]  10.9ms  @0  12.8ms  @99 12.9ms  @100
    [blendmode_rect_Difference] 5.56ms  @0  6.79ms  @99 6.8ms   @100
    [blendmode_mask_Difference] 11.4ms  @0  13.8ms  @99 14.1ms  @100

After:
    [blendmode_rect_Exclusion]  3.5ms   @0  4.12ms  @99 4.59ms  @100
    [blendmode_mask_Exclusion]  9.27ms  @0  11.2ms  @99 11.6ms  @100
    [blendmode_rect_Difference] 5.37ms  @0  6.58ms  @99 6.6ms   @100
    [blendmode_mask_Difference] 11ms    @0  12.1ms  @99 12.6ms  @100

Change-Id: I03f32368244d4f979cfee83723fd78dfbc7d5fc1
Reviewed-on: https://skia-review.googlesource.com/33980
Commit-Queue: Florin Malita <fmalita@chromium.org>
Reviewed-by: Florin Malita <fmalita@chromium.org>

1 files changed, 15 insertions, 5 deletions

diff --git a/src/jumper/SkJumper_stages_8bit.cpp b/src/jumper/SkJumper_stages_8bit.cpp
index cf037b0209..3d9fec0dbb 100644
--- a/src/jumper/SkJumper_stages_8bit.cpp
+++ b/src/jumper/SkJumper_stages_8bit.cpp
@@ -421,14 +421,24 @@ SI V srcover_alpha(V src, V dst, V rgb) {
 STAGE(darken)  { src = srcover_alpha(src, dst, src + (dst - max(src*alpha(dst), dst*alpha(src)))); }
 STAGE(lighten) { src = srcover_alpha(src, dst, src + (dst - min(src*alpha(dst), dst*alpha(src)))); }
 
-STAGE(difference) {
-    V min_ = min(src*alpha(dst), dst*alpha(src));
-    src    = srcover_alpha(src, dst, (src - min_) + (dst - min_));
-}
+SI V zero_alpha(V rgba) { return rgba.u32 & 0x00ffffff; }
 
 STAGE(exclusion) {
+    // We could do exclusion with srcover_alpha(), but can fold a little more math through:
+    //     rgb   = Sc + Dc - 2*Sc*Dc
+    //     alpha = Sa + Da -   Sa*Da
+    // So we just subtract two sd from rgb, and one from alpha.
     V sd = src*dst;
-    src  = srcover_alpha(src, dst, (src - sd) + (dst - sd));
+    src = (src - sd) + (dst - zero_alpha(sd));
+}
+STAGE(difference) {
+    // Like exclusion, we can fold math through with the same trick:
+    //     rgb   = Sc + Dc - 2*min(Sc*Da, Dc*Sa)
+    //     alpha = Sa + Da -       Sa*Da
+    // Here notice (Sa*Da) == min(Sa*Da, Da*Sa) for alpha,
+    // so again we subtract two from rgb, one from alpha.
+    V min_ = min(src*alpha(dst), dst*alpha(src));
+    src = (src - min_) + (dst - zero_alpha(min_));
 }
 
 #undef BLEND_MODE