revise row blits to keep intermediate precision so that color is preserved when blended against its…

src/opts/SkBlitRow_opts_SSE2.cpp

 /*
  * Copyright 2012 The Android Open Source Project
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #include <emmintrin.h>
 #include "SkBitmapProcState_opts_SSE2.h"
 #include "SkBlitRow_opts_SSE2.h"
 #include "SkColorPriv.h"
 #include "SkColor_opts_SSE2.h"
 #include "SkDither.h"
 #include "SkMSAN.h"
 #include "SkUtils.h"
 
 /* SSE2 version of S32_Blend_BlitRow32()
  * portable version is in core/SkBlitRow_D32.cpp
  */
 void S32_Blend_BlitRow32_SSE2(SkPMColor* SK_RESTRICT dst,
                               const SkPMColor* SK_RESTRICT src,
                               int count, U8CPU alpha) {
     SkASSERT(alpha <= 255);
     if (count <= 0) {
         return;
     }
 
     uint32_t src_scale = SkAlpha255To256(alpha);
-    uint32_t dst_scale = 256 - src_scale;
 
     if (count >= 4) {
         SkASSERT(((size_t)dst & 0x03) == 0);
         while (((size_t)dst & 0x0F) != 0) {
-            *dst = SkAlphaMulQ(*src, src_scale) + SkAlphaMulQ(*dst, dst_scale);
+            *dst = SkPMLerp(*src, *dst, src_scale);
             src++;
             dst++;
             count--;
         }
 
         const __m128i *s = reinterpret_cast<const __m128i*>(src);
         __m128i *d = reinterpret_cast<__m128i*>(dst);
 
         while (count >= 4) {
             // Load 4 pixels each of src and dest.
             __m128i src_pixel = _mm_loadu_si128(s);
             __m128i dst_pixel = _mm_load_si128(d);
 
-            src_pixel = SkAlphaMulQ_SSE2(src_pixel, src_scale);
-            dst_pixel = SkAlphaMulQ_SSE2(dst_pixel, dst_scale);
-
-            // Add result
-            __m128i result = _mm_add_epi8(src_pixel, dst_pixel);
+            __m128i result = SkPMLerp_SSE2(src_pixel, dst_pixel, src_scale);
             _mm_store_si128(d, result);
             s++;
             d++;
             count -= 4;
         }
         src = reinterpret_cast<const SkPMColor*>(s);
         dst = reinterpret_cast<SkPMColor*>(d);
     }
 
     while (count > 0) {
-        *dst = SkAlphaMulQ(*src, src_scale) + SkAlphaMulQ(*dst, dst_scale);
+        *dst = SkPMLerp(*src, *dst, src_scale);
         src++;
         dst++;
         count--;
     }
 }
 
 void S32A_Blend_BlitRow32_SSE2(SkPMColor* SK_RESTRICT dst,
                                const SkPMColor* SK_RESTRICT src,
                                int count, U8CPU alpha) {
     SkASSERT(alpha <= 255);
@@ skipping 912 matching lines @@
                 uint32_t dst_expanded = SkExpand_rgb_16(*dst);
                 dst_expanded = dst_expanded * (SkAlpha255To256(255 - a) >> 3);
                 // now src and dst expanded are in g:11 r:10 x:1 b:10
                 *dst = SkCompact_rgb_16((src_expanded + dst_expanded) >> 5);
             }
             dst += 1;
             DITHER_INC_X(x);
         } while (--count != 0);
     }
 }