Multithreaded dng host implementation

src/codec/SkRawCodec.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 "SkCodec.h"
 #include "SkCodecPriv.h"
 #include "SkColorPriv.h"
 #include "SkData.h"
 #if !defined(GOOGLE3)
 #include "SkJpegCodec.h"
 #endif
 #include "SkRawCodec.h"
 #include "SkRefCnt.h"
 #include "SkStream.h"
 #include "SkStreamPriv.h"
 #include "SkSwizzler.h"
+#include "SkTaskGroup.h"
 #include "SkTemplates.h"
 #include "SkTypes.h"
 
+#include "dng_area_task.h"
 #include "dng_color_space.h"
 #include "dng_exceptions.h"
 #include "dng_host.h"
 #include "dng_info.h"
 #include "dng_memory.h"
 #include "dng_render.h"
 #include "dng_stream.h"
 
 #include "src/piex.h"
 
 #include <cmath>  // for std::round,floor,ceil
 #include <limits>
 
 namespace {
 
+// Caluclates the number of tiles of tile_size that fit into the area in vertical and horizontal
+// directions.
+dng_point num_tiles_in_area(const dng_point &areaSize,
+                            const dng_point_real64 &tileSize) {
+  return dng_point((areaSize.v + tileSize.v - 1) / tileSize.v,
+                   (areaSize.h + tileSize.h - 1) / tileSize.h);
+}
+
+int num_threads_required(const dng_point& tilesInThread,
+                         const dng_point& tilesInArea) {
+  return ((tilesInArea.v + tilesInThread.v - 1) / tilesInThread.v) *
+         ((tilesInArea.h + tilesInThread.h - 1) / tilesInThread.h);
+}
+
+// Calculate the number of tiles to process per thread, taking into account the maximum number of
+// threads.
+dng_point num_tiles_per_thread(const int maxThreads,
+                               const dng_point &tilesInArea) {
+  dng_point tilesInThread = {1, 1};
+  while (num_threads_required(tilesInThread, tilesInArea) > maxThreads) {
+      if (tilesInThread.h < tilesInArea.h) {
+          ++tilesInThread.h;
+      } else if (tilesInThread.v < tilesInArea.v) {
+          ++tilesInThread.v;
+      } else {
+          ThrowProgramError("num_tiles_per_thread calculation is wrong.");
+      }
+  }
+  return tilesInThread;
+}
+
+class SkDngHost : public dng_host {
+public:
+    using dng_host::dng_host;
+
+    void PerformAreaTask(dng_area_task& task, const dng_rect& area) override {
+        const int maxThreads = static_cast<int>(kMaxMPThreads);
+        SkTaskGroup taskGroup;
+
+        const dng_point tileSize(task.FindTileSize(area));
+        const dng_point tilesInArea = num_tiles_in_area(area.Size(), tileSize);
+
+        const dng_point tilesInThread = num_tiles_per_thread(maxThreads, tilesInArea);
+        const dng_point threadAreaSize(tilesInThread.v * tileSize.v, tilesInThread.h * tileSize.h);
+        dng_rect threadArea = dng_rect(threadAreaSize) + area.TL();
+
+        const int numThreads = num_threads_required(tilesInThread, tilesInArea);
+
+        task.Start(numThreads, tileSize, &Allocator(), Sniffer());
+        int taskIndex = 0;
+        for (int v = 0; v < tilesInArea.v; v += tilesInThread.v) {
+            for (int h = 0; h < tilesInArea.h; h += tilesInThread.h) {
+                threadArea.l = area.l + h * tileSize.h;
+                threadArea.t = area.t + v * tileSize.v;
+                threadArea.r = Min_int32(threadArea.l + threadAreaSize.h, area.r);
+                threadArea.b = Min_int32(threadArea.t + threadAreaSize.v, area.b);
+
+                taskGroup.add([&task, this, taskIndex, threadArea, tileSize] {
+                    task.ProcessOnThread(taskIndex, threadArea, tileSize, this->Sniffer());
+                });
+            }
+            ++taskIndex;

[adaubert, 2016/01/26 14:20:24]

++taskIndex; should be in the inner scope.

[ebrauer, 2016/01/26 14:28:17]

Done.

+        }
+
+        taskGroup.wait();
+        task.Finish(numThreads);
+    }
+
+    uint32 PerformAreaTaskThreads() override {
+        return kMaxMPThreads;
+    }
+
+private:
+    typedef dng_host INHERITED;
+};
+
 // T must be unsigned type.
 template <class T>
 bool safe_add_to_size_t(T arg1, T arg2, size_t* result) {
     SkASSERT(arg1 >= 0);
     SkASSERT(arg2 >= 0);
     if (arg1 >= 0 && arg2 <= std::numeric_limits<T>::max() - arg1) {
         T sum = arg1 + arg2;
         if (sum <= std::numeric_limits<size_t>::max()) {
             *result = static_cast<size_t>(sum);
             return true;
@@ skipping 233 matching lines @@
         return fIsScalable;
     }
 
     bool isXtransImage() const {
         return fIsXtransImage;
     }
 
 private:
     bool readDng() {
         // Due to the limit of DNG SDK, we need to reset host and info.
-        fHost.reset(new dng_host(&fAllocator));
+        fHost.reset(new SkDngHost(&fAllocator));
         fInfo.reset(new dng_info);
         fDngStream.reset(new SkDngStream(fStream));
         try {
             fHost->ValidateSizes();
             fInfo->Parse(*fHost, *fDngStream);
             fInfo->PostParse(*fHost);
             if (!fInfo->IsValidDNG()) {
                 return false;
             }
 
@@ skipping 164 matching lines @@
     SkISize sizeFloor = this->onGetScaledDimensions(1.f / std::floor(fullShortEdge / shortEdge));
     SkISize sizeCeil = this->onGetScaledDimensions(1.f / std::ceil(fullShortEdge / shortEdge));
     return sizeFloor == dim || sizeCeil == dim;
 }
 
 SkRawCodec::~SkRawCodec() {}
 
 SkRawCodec::SkRawCodec(SkDngImage* dngImage)
     : INHERITED(dngImage->getImageInfo(), nullptr)
     , fDngImage(dngImage) {}