Implement instanced rendering for simple shapes

src/gpu/GrInstancedRendering.h

Index: src/gpu/GrInstancedRendering.h
diff --git a/src/gpu/GrInstancedRendering.h b/src/gpu/GrInstancedRendering.h
new file mode 100644
index 0000000000000000000000000000000000000000..367342f89dbfde7b7545d6799eb4c81d225cbc15
--- /dev/null
+++ b/src/gpu/GrInstancedRendering.h
@@ -0,0 +1,216 @@
+/*
+ * Copyright 2016 Google Inc.
+ *
+ * Use of this source code is governed by a BSD-style license that can be
+ * found in the LICENSE file.
+ */
+
+#ifndef GrInstancedRendering_DEFINED
+#define GrInstancedRendering_DEFINED
+
+#include "GrAllocator.h"
+#include "GrInstancedRenderingTypes.h"
+#include "batches/GrDrawBatch.h"
+
+class GrInstanceProcessor;
+class GrResourceProvider;
+
+/**
+ * This class serves as a centralized clearinghouse for instanced rendering. It accumulates data for
+ * instanced draws into one location, and creates special batches that pull from this data. The
+ * nature of instanced rendering allows these batches to combine well and render efficiently.
+ *
+ * During a flush, this class assembles the accumulated draw data into a single vertex and texel
+ * buffer, and its subclass draws the batches using backend-specific instanced rendering APIs.
+ *
+ * This class is responsible for the CPU side of instanced rendering. Shaders are implemented by
+ * GrInstanceProcessor.
+ */
+class GrInstancedRendering : public SkNoncopyable, protected GrInstancedRenderingTypes {
+public:
+    virtual ~GrInstancedRendering() { SkASSERT(State::kRecordingDraws == fState); }
+
+    GrGpu* gpu() const { return fGpu; }
+
+    /**
+     * Flags that describe relevant external pipeline conditions. These are used to select
+     * appropriate antialias modes, shader strategies, etc.
+     */
+    enum Flags {
+        kStencilWrite_Flag       = (1 << 0),
+        kStencilBufferMSAA_Flag  = (1 << 1),
+        kColorWrite_Flag         = (1 << 2),
+        kColorBufferMSAA_Flag    = (1 << 3),
+        /**
+         * This should not be set if the fragment shader uses derivatives, automatic mipmap LOD, or
+         * other features that depend on neighboring pixels.
+         */
+        kUseDiscard_Flag         = (1 << 4)
+    };
+
+    /**
+     * These methods make a new record internally for an instanced draw, and return a batch that is
+     * effectively just an index to that record. The returned batch is not self-contained, but
+     * rather relies on this class to handle the rendering. The client must call beginFlush() on
+     * this class before attempting to flush batches returned by it. It is invalid to record new
+     * draws between beginFlush() and endFlush().
+     */
+    GrDrawBatch* SK_WARN_UNUSED_RESULT recordRect(const SkRect&, const SkMatrix&, GrColor,
+                                                  bool antialias, uint32_t flags, bool* useHWAA);
+
+    GrDrawBatch* SK_WARN_UNUSED_RESULT recordRect(const SkRect&, const SkMatrix&, GrColor,
+                                                  const SkRect& localRect, bool antialias,
+                                                  uint32_t flags, bool* useHWAA);
+
+    GrDrawBatch* SK_WARN_UNUSED_RESULT recordRect(const SkRect&, const SkMatrix&, GrColor,
+                                                  const SkMatrix& localMatrix, bool antialias,
+                                                  uint32_t flags, bool* useHWAA);
+
+    GrDrawBatch* SK_WARN_UNUSED_RESULT recordOval(const SkRect&, const SkMatrix&, GrColor,
+                                                  bool antialias, uint32_t flags, bool* useHWAA);
+
+    GrDrawBatch* SK_WARN_UNUSED_RESULT recordRRect(const SkRRect&, const SkMatrix&, GrColor,
+                                                   bool antialias, uint32_t flags, bool* useHWAA);
+
+    GrDrawBatch* SK_WARN_UNUSED_RESULT recordDRRect(const SkRRect& outer, const SkRRect& inner,
+                                                    const SkMatrix&, GrColor, bool antialias,
+                                                    uint32_t flags, bool* useHWAA);
+
+    /**
+     * Compiles all recorded draws into GPU buffers and allows the client to begin flushing the
+     * batches created by this class.
+     */
+    void beginFlush(GrResourceProvider*);
+
+    /**
+     * Called once the batches created previously by this class have all been released. Allows the
+     * client to begin recording draws again.
+     */
+    void endFlush();
+
+    enum class ResetType : bool {
+        kDestroy,
+        kAbandon
+    };
+
+    /**
+     * Resets all GPU resources, including those that are held long term. They will be lazily
+     * reinitialized if the class begins to be used again.
+     */
+    void resetGpuResources(ResetType);
+
+protected:
+    class Batch : public GrDrawBatch {
+    public:
+        virtual ~Batch() { fInUse = false; } // fInUse will continue to be accessed.
+
+        const char* name() const override { return "Instanced Batch"; }
+
+        void computePipelineOptimizations(GrInitInvariantOutput* color,
+                                          GrInitInvariantOutput* coverage,
+                                          GrBatchToXPOverrides*) const override;
+
+    protected:
+        Batch(uint32_t classID, GrInstancedRendering* ir, int instanceIdx)
+            : INHERITED(classID),
+              fInstancedRendering(ir),
+              fFirstInstanceIdx(instanceIdx),
+              fInUse(true) {
+#ifdef SK_DEBUG
+            fIsCombined = false;
+#endif
+        }
+
+        void initBatchTracker(const GrXPOverridesForBatch&) override;
+
+        void onPrepare(GrBatchFlushState*) override {}
+        void onDraw(GrBatchFlushState*) override;
+        void onDelete() const override;
+
+        GrInstancedRendering* const   fInstancedRendering;
+        const int                     fFirstInstanceIdx;
+        BatchInfo                     fInfo;
+        bool                          fInUse;
+#ifdef SK_DEBUG
+        bool                          fIsCombined;
+#endif
+
+        typedef GrDrawBatch INHERITED;
+
+        friend class GrInstancedRendering;
+    };
+
+    /**
+     * We allocate our own batches. This allows us to iterate through them immediately before a
+     * flush in order to compile draw buffers.
+     */
+    class BatchAllocator : public GrAllocator {
+    public:
+        BatchAllocator(size_t sizeofBatchClass)
+            : INHERITED(sizeofBatchClass, kBatchesPerBlock, nullptr) {
+            fFirstBlock = sk_malloc_throw(kBatchesPerBlock * sizeofBatchClass);
+            this->setInitialBlock(fFirstBlock);
+        }
+
+        ~BatchAllocator() {
+            sk_free(fFirstBlock);
+        }
+
+    private:
+        enum { kBatchesPerBlock = 128 };
+
+        void* fFirstBlock;
+
+        typedef GrAllocator INHERITED;
+    };
+
+    GrInstancedRendering(GrGpu* gpu, uint32_t supportedAAModes, size_t sizeofBatchClass);
+
+    const GrBuffer* vertexBuffer() const { SkASSERT(fVertexBuffer); return fVertexBuffer; }
+    const GrBuffer* indexBuffer() const { SkASSERT(fIndexBuffer); return fIndexBuffer; }
+    const GrBuffer* instanceBuffer() const { SkASSERT(fInstanceBuffer); return fInstanceBuffer; }
+    const BatchAllocator* batchAllocator() const { return &fBatchAllocator; }
+
+    virtual void onBeginFlush(GrResourceProvider*) = 0;
+    virtual void onDraw(const GrPipeline&, const GrInstanceProcessor&, const Batch*) = 0;
+    virtual void onEndFlush() = 0;
+    virtual void onResetGpuResources(ResetType) = 0;
+
+#ifdef SK_DEBUG
+    int fInUseBatchCount;
+#endif
+
+private:
+    enum class State : bool {
+        kRecordingDraws,
+        kFlushing
+    };
+
+    Batch* SK_WARN_UNUSED_RESULT recordShape(ShapeType, const SkRect& bounds,
+                                             const SkMatrix& viewMatrix, GrColor,
+                                             const SkRect& localRect, bool antialias,
+                                             uint32_t flags, bool* requireHWAA);
+
+    bool selectAntialiasMode(const SkMatrix& viewMatrix, bool antialias, uint32_t flags,
+                             AntialiasMode*, bool* requireHWAA);
+
+    void appendRRectParams(const SkRRect&, BatchInfo*);
+    void appendParamsTexel(const SkScalar* vals, int count);
+    void appendParamsTexel(SkScalar x, SkScalar y, SkScalar z, SkScalar w);
+    void appendParamsTexel(SkScalar x, SkScalar y, SkScalar z);
+
+    virtual Batch* constructBatch(void* storage, int instanceIdx) = 0;
+
+    const SkAutoTUnref<GrGpu>            fGpu;
+    const uint32_t                       fSupportedAAModes;
+    State                                fState;
+    SkSTArray<1024, Instance, true>      fInstances;
+    SkSTArray<1024, ParamsTexel, true>   fParams;
+    BatchAllocator                       fBatchAllocator;
+    SkAutoTUnref<const GrBuffer>         fVertexBuffer;
+    SkAutoTUnref<const GrBuffer>         fIndexBuffer;
+    SkAutoTUnref<const GrBuffer>         fInstanceBuffer;
+    SkAutoTUnref<GrBuffer>               fParamsBuffer;
+};
+
+#endif