skcpu: sse4.1 floor, f16c f16<->f32

src/core/SkXfermodeF16.cpp

 /*
  * Copyright 2016 Google Inc.
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #include "SkHalf.h"
 #include "SkPM4fPriv.h"
 #include "SkUtils.h"
@@ skipping 116 matching lines @@
             dst[i] = SkFloatToHalf_01(lerp_by_coverage(r4, d4, aa[i]));
         } else {
             dst[i] = SkFloatToHalf_01(r4);
         }
     }
 }
 
 static void srcover_n(const SkXfermode*, uint64_t dst[], const SkPM4f src[], int count,
                       const SkAlpha aa[]) {
     for (int i = 0; i < count; ++i) {
-        const Sk4f s4 = Sk4f::Load(src[i].fVec);
-        const Sk4f dst_scale = Sk4f(1 - get_alpha(s4));
-        const Sk4f d4 = SkHalfToFloat_01(dst[i]);
-        const Sk4f r4 = s4 + d4 * dst_scale;
+        Sk4f s = Sk4f::Load(src+i),
+             d = SkHalfToFloat_01(dst+i),
+             r = s + d*(1.0f - SkNx_shuffle<3,3,3,3>(s));
         if (aa) {
-            dst[i] = SkFloatToHalf_01(lerp_by_coverage(r4, d4, aa[i]));
-        } else {
-            dst[i] = SkFloatToHalf_01(r4);
+            r = lerp_by_coverage(r, d, aa[i]);
         }
+        SkFloatToHalf_01(r, dst+i);
     }
 }
 
 const SkXfermode::F16Proc gProcs_SrcOver[] = { srcover_n, src_n, srcover_1, src_1 };
 
 ///////////////////////////////////////////////////////////////////////////////////////////////////
 
 static SkXfermode::F16Proc find_proc(SkXfermode::Mode mode, uint32_t flags) {
     SkASSERT(0 == (flags & ~3));
     flags &= 3;
@@ skipping 13 matching lines @@
     SkASSERT(0 == (flags & ~3));
     flags &= 3;
 
     Mode mode;
     return this->asMode(&mode) ? find_proc(mode, flags) : gProcs_General[flags];
 }
 
 SkXfermode::F16Proc SkXfermode::GetF16Proc(SkXfermode* xfer, uint32_t flags) {
     return xfer ? xfer->onGetF16Proc(flags) : find_proc(SkXfermode::kSrcOver_Mode, flags);
 }