Optimize color xforms with 2.2 gammas for SSE2

bench/ColorCodecBench.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 "ColorCodecBench.h"
 #include "Resources.h"
 #include "SkCodec.h"
@@ skipping 154 matching lines @@
     fSrcData = codec->getICCData();
     sk_sp<SkData> dstData = SkData::MakeFromFileName(
             GetResourcePath("monitor_profiles/HP_ZR30w.icc").c_str());
     SkASSERT(dstData);
 
 
 #if defined(SK_TEST_QCMS)
     if (FLAGS_qcms) {
         fDstSpaceQCMS.reset(qcms_profile_from_memory(dstData->data(), dstData->size()));
         SkASSERT(fDstSpaceQCMS);
+
+        // This call takes a non-trivial amount of time, but I think it's the most fair to
+        // treat it as overhead.  It only needs to happen once.
+        qcms_profile_precache_output_transform(fDstSpaceQCMS);
     } else
 #endif
     {
         fDstSpace = SkColorSpace::NewICC(dstData->data(), dstData->size());
         SkASSERT(fDstSpace);
     }
 }
 
 void ColorCodecBench::onDraw(int n, SkCanvas*) {
     for (int i = 0; i < n; i++) {
 #if defined(SK_TEST_QCMS)
         if (FLAGS_qcms) {
             if (FLAGS_xform_only) {
                 this->xformOnlyQCMS();
             } else {
                 this->decodeAndXformQCMS();
             }
         } else
 #endif
         {
             if (FLAGS_xform_only) {
                 this->xformOnly();
             } else {
                 this->decodeAndXform();
             }
         }
     }
 }