use new shuffle to speed up affine matrix mappts

src/opts/SkMatrix_opts.h

 /*
  * Copyright 2015 Google Inc.
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #ifndef SkMatrix_opts_DEFINED
 #define SkMatrix_opts_DEFINED
 
@@ skipping 71 matching lines @@
         SkScalar kx = m.getSkewX();
         SkScalar ky = m.getSkewY();
         if (count & 1) {
             dst->set(src->fX * sx + src->fY * kx + tx,
                      src->fX * ky + src->fY * sy + ty);
             src += 1;
             dst += 1;
         }
         Sk4s trans4(tx, ty, tx, ty);
         Sk4s scale4(sx, sy, sx, sy);
-        Sk4s  skew4(kx, ky, kx, ky);    // applied to swizzle of src4
+        Sk4s  skew4(ky, kx, ky, kx);    // applied src4, then x/y swapped
         count >>= 1;
         for (int i = 0; i < count; ++i) {
             Sk4s src4 = Sk4s::Load(&src->fX);
-            Sk4s swz4(src[0].fY, src[0].fX, src[1].fY, src[1].fX);  // need ABCD -> BADC
-            (src4 * scale4 + swz4 * skew4 + trans4).store(&dst->fX);
+            (trans4 + src4 * scale4 + SkNx_shuffle<1,0,3,2>(src4 * skew4)).store(&dst->fX);
             src += 2;
             dst += 2;
         }
     }
 }
 
 } // namespace SK_OPTS_NS
 
 #endif//SkMatrix_opts_DEFINED