Apply linear gradient premul in 4f

src/effects/gradients/SkLinearGradient.cpp

 /*
  * Copyright 2012 Google Inc.
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #include "Sk4fLinearGradient.h"
 #include "SkLinearGradient.h"
 #include "SkRefCnt.h"
@@ skipping 509 matching lines @@
         rec -= 1;
         SkASSERT(rec[0].fPos >= 0 && rec[0].fPos <= 1);
         SkASSERT(rec[1].fPos >= 0 && rec[1].fPos <= 1);
         SkASSERT(rec[0].fPos <= rec[1].fPos);
     }
     return rec;
 }
 
 template <bool apply_alpha> SkPMColor trunc_from_255(const Sk4f& x) {
     SkPMColor c;
+
+#ifdef SK_SUPPORT_LEGACY_GRADIENT_PREMUL
     SkNx_cast<uint8_t>(x).store(&c);
     if (apply_alpha) {
         c = SkPreMultiplyARGB(SkGetPackedA32(c), SkGetPackedR32(c),
                               SkGetPackedG32(c), SkGetPackedB32(c));
     }
+#else
+    Sk4f c4f255;
+    if (!apply_alpha) {
+        c4f255 = x;
+    } else {
+        // We have to pin, due to dithering bias.
+        c4f255 = Sk4f::Min(Sk4f::Max(x, Sk4f(0)), Sk4f(255));

[reed1, 2016/10/10 18:20:17]

does the store() call also pin? Why don't we have to pin in the non-alpha case?

[f(malita), 2016/10/10 18:33:18]

Good question.

Doesn't look like it pins, just truncates - but somehow we don't run into
trouble in that case (maybe because all values are biased the same way).

When we apply the premul in 4f though we seem to sometimes end up breaking the
premul invariant (rgb > a) without a pin, presumably because after premul the
channels truncate differently.  This manifests as dithery-looking artifacts in
the output.

Also, I seem to recall we pre-bias all values by 0.5 to prepare for truncate --
so maybe we only need an upper clamp on alpha?  Let me see if I tweak this some
more.

+        const float scale = c4f255[SkPM4f::A] * 1.f / 255;
+        c4f255 *= Sk4f(scale, scale, scale, 1);
+    }
+    SkNx_cast<uint8_t>(c4f255).store(&c);
+#endif
     return c;
 }
 
 template <bool apply_alpha> void fill(SkPMColor dst[], int count,
                                       const Sk4f& c4, const Sk4f& c4other) {
     sk_memset32_dither(dst, trunc_from_255<apply_alpha>(c4),
                        trunc_from_255<apply_alpha>(c4other), count);
 }
 
 template <bool apply_alpha> void fill(SkPMColor dst[], int count, const Sk4f& c4) {
@@ skipping 215 matching lines @@
             this->shade4_dx_clamp<false, true>(dstC, count, fx, dx, invDx, dither);
         }
     } else {
         if (fApplyAlphaAfterInterp) {
             this->shade4_dx_clamp<true, false>(dstC, count, fx, dx, invDx, dither);
         } else {
             this->shade4_dx_clamp<false, false>(dstC, count, fx, dx, invDx, dither);
         }
     }
 }