The compiler can generate smulbb perfectly well nowadays.

src/opts/SkBlitRow_opts_arm_neon.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 "SkBlitRow_opts_arm_neon.h"
 
 #include "SkBlitMask.h"
@@ skipping 696 matching lines @@
             count -= 8;
         } while (count >= 8);
     }
 
     // leftovers
     while (count-- > 0) {
         SkPMColor sc = *src++;
         if (sc) {
             uint16_t dc = *dst;
             unsigned dst_scale = 255 - SkMulDiv255Round(SkGetPackedA32(sc), alpha);
-            unsigned dr = SkMulS16(SkPacked32ToR16(sc), alpha) + SkMulS16(SkGetPackedR16(dc), dst_scale);
-            unsigned dg = SkMulS16(SkPacked32ToG16(sc), alpha) + SkMulS16(SkGetPackedG16(dc), dst_scale);
-            unsigned db = SkMulS16(SkPacked32ToB16(sc), alpha) + SkMulS16(SkGetPackedB16(dc), dst_scale);
+            unsigned dr = (SkPacked32ToR16(sc) * alpha) + (SkGetPackedR16(dc) * dst_scale);
+            unsigned dg = (SkPacked32ToG16(sc) * alpha) + (SkGetPackedG16(dc) * dst_scale);
+            unsigned db = (SkPacked32ToB16(sc) * alpha) + (SkGetPackedB16(dc) * dst_scale);
             *dst = SkPackRGB16(SkDiv255Round(dr), SkDiv255Round(dg), SkDiv255Round(db));
         }
         dst += 1;
     }
 }
 
 /* dither matrix for Neon, derived from gDitherMatrix_3Bit_16.
  * each dither value is spaced out into byte lanes, and repeated
  * to allow an 8-byte load from offsets 0, 1, 2 or 3 from the
  * start of each row.
@@ skipping 862 matching lines @@
     invA += invA >> 7;
     SkASSERT(invA < 256);  // Our caller has already handled the alpha == 0 case.
 
     Sk16h colorHighAndRound = Sk4px::DupPMColor(color).widenHi() + Sk16h(128);
     Sk16b invA_16x(invA);
 
     Sk4px::MapSrc(count, dst, src, [&](const Sk4px& src4) -> Sk4px {
         return (src4 * invA_16x).addNarrowHi(colorHighAndRound);
     });
 }