Android/frameworks_base
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Reduce hwui CPU time by using glDrawRangeElements

Browse Source 
The CPU overhead of glDrawElements in the GPU driver is significant
with client-side vertex data (unique per draw call) as the driver has
to calculate the mininimum and maximum indices from the index buffer
in order to evaluate the range of vertex data required. This can be
avoided by keeping track of the min-max in hwui and passing it with
glDrawRangeElements. This requires OpenGL ES3.0 support (which is
already checked for elsewhere in hwui).

Test: manual - visual inspection on fugu (nexus player)

Change-Id: I57bb1ddd239a1032f74f1cd2683bbe0970e84bd9
This commit is contained in:
Arun
2017-01-23 11:41:06 +00:00
committed by John Reck
parent cba224e833
commit b0a9477c8e
3 changed files with 15 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
libs/hwui/Glop.h
View File

@@ -112,6 +112,7 @@ public:
} vertices;
int elementCount;
int vertexCount; // only used for meshes (for glDrawRangeElements)
TextureVertex mappedVertices[4];
} mesh;

1
libs/hwui/GlopBuilder.cpp
View File

@@ -210,6 +210,7 @@ GlopBuilder& GlopBuilder::setMeshVertexBuffer(const VertexBuffer& vertexBuffer)
alphaVertex ? kAlphaVertexStride : kVertexStride };
mOutGlop->mesh.elementCount = indices
? vertexBuffer.getIndexCount() : vertexBuffer.getVertexCount();
mOutGlop->mesh.vertexCount = vertexBuffer.getVertexCount(); // used for glDrawRangeElements()
return *this;
}

16
libs/hwui/renderstate/RenderState.cpp
View File

@@ -364,18 +364,28 @@ void RenderState::render(const Glop& glop, const Matrix4& orthoMatrix) {
const GLbyte* vertexData = static_cast<const GLbyte*>(vertices.position);
while (elementsCount > 0) {
GLsizei drawCount = std::min(elementsCount, (GLsizei) kMaxNumberOfQuads * 6);
GLsizei vertexCount = (drawCount / 6) * 4;
meshState().bindPositionVertexPointer(vertexData, vertices.stride);
if (vertices.attribFlags & VertexAttribFlags::TextureCoord) {
meshState().bindTexCoordsVertexPointer(
vertexData + kMeshTextureOffset, vertices.stride);
}
glDrawElements(mesh.primitiveMode, drawCount, GL_UNSIGNED_SHORT, nullptr);
if (mCaches->extensions().getMajorGlVersion() >= 3) {
glDrawRangeElements(mesh.primitiveMode, 0, vertexCount-1, drawCount, GL_UNSIGNED_SHORT, nullptr);
} else {
glDrawElements(mesh.primitiveMode, drawCount, GL_UNSIGNED_SHORT, nullptr);
}
elementsCount -= drawCount;
vertexData += (drawCount / 6) * 4 * vertices.stride;
vertexData += vertexCount * vertices.stride;
}
} else if (indices.bufferObject || indices.indices) {
glDrawElements(mesh.primitiveMode, mesh.elementCount, GL_UNSIGNED_SHORT, indices.indices);
if (mCaches->extensions().getMajorGlVersion() >= 3) {
// use glDrawRangeElements to reduce CPU overhead (otherwise the driver has to determine the min/max index values)
glDrawRangeElements(mesh.primitiveMode, 0, mesh.vertexCount-1, mesh.elementCount, GL_UNSIGNED_SHORT, indices.indices);
} else {
glDrawElements(mesh.primitiveMode, mesh.elementCount, GL_UNSIGNED_SHORT, indices.indices);
}
} else {
glDrawArrays(mesh.primitiveMode, 0, mesh.elementCount);
}