From 3b748a44c6bd2ea05fe16839caf73dbe50bd7ae9 Mon Sep 17 00:00:00 2001 From: Romain Guy Date: Wed, 17 Apr 2013 18:54:38 -0700 Subject: Pack preloaded framework assets in a texture atlas When the Android runtime starts, the system preloads a series of assets in the Zygote process. These assets are shared across all processes. Unfortunately, each one of these assets is later uploaded in its own OpenGL texture, once per process. This wastes memory and generates unnecessary OpenGL state changes. This CL introduces an asset server that provides an atlas to all processes. Note: bitmaps used by skia shaders are *not* sampled from the atlas. It's an uncommon use case and would require extra texture transforms in the GL shaders. WHAT IS THE ASSETS ATLAS The "assets atlas" is a single, shareable graphic buffer that contains all the system's preloaded bitmap drawables (this includes 9-patches.) The atlas is made of two distinct objects: the graphic buffer that contains the actual pixels and the map which indicates where each preloaded bitmap can be found in the atlas (essentially a pair of x and y coordinates.) HOW IS THE ASSETS ATLAS GENERATED Because we need to support a wide variety of devices and because it is easy to change the list of preloaded drawables, the atlas is generated at runtime, during the startup phase of the system process. There are several steps that lead to the atlas generation: 1. If the device is booting for the first time, or if the device was updated, we need to find the best atlas configuration. To do so, the atlas service tries a number of width, height and algorithm variations that allows us to pack as many assets as possible while using as little memory as possible. Once a best configuration is found, it gets written to disk in /data/system/framework_atlas 2. Given a best configuration (algorithm variant, dimensions and number of bitmaps that can be packed in the atlas), the atlas service packs all the preloaded bitmaps into a single graphic buffer object. 3. The packing is done using Skia in a temporary native bitmap. The Skia bitmap is then copied into the graphic buffer using OpenGL ES to benefit from texture swizzling. HOW PROCESSES USE THE ATLAS Whenever a process' hardware renderer initializes its EGL context, it queries the atlas service for the graphic buffer and the map. It is important to remember that both the context and the map will be valid for the lifetime of the hardware renderer (if the system process goes down, all apps get killed as well.) Every time the hardware renderer needs to render a bitmap, it first checks whether the bitmap can be found in the assets atlas. When the bitmap is part of the atlas, texture coordinates are remapped appropriately before rendering. Change-Id: I8eaecf53e7f6a33d90da3d0047c5ceec89ea3af0 --- libs/hwui/Program.cpp | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) (limited to 'libs/hwui/Program.cpp') diff --git a/libs/hwui/Program.cpp b/libs/hwui/Program.cpp index 14a23765b301..c127d684be32 100644 --- a/libs/hwui/Program.cpp +++ b/libs/hwui/Program.cpp @@ -15,6 +15,9 @@ */ #define LOG_TAG "OpenGLRenderer" +#define ATRACE_TAG ATRACE_TAG_VIEW + +#include #include "Program.h" @@ -25,7 +28,6 @@ namespace uirenderer { // Base program /////////////////////////////////////////////////////////////////////////////// -// TODO: Program instance should be created from a factory method Program::Program(const ProgramDescription& description, const char* vertex, const char* fragment) { mInitialized = false; mHasColorUniform = false; @@ -50,7 +52,9 @@ Program::Program(const ProgramDescription& description, const char* vertex, cons texCoords = -1; } + ATRACE_BEGIN("linkProgram"); glLinkProgram(mProgramId); + ATRACE_END(); GLint status; glGetProgramiv(mProgramId, GL_LINK_STATUS, &status); @@ -87,6 +91,9 @@ Program::Program(const ProgramDescription& description, const char* vertex, cons Program::~Program() { if (mInitialized) { + // This would ideally happen after linking the program + // but Tegra drivers, especially when perfhud is enabled, + // sometimes crash if we do so glDetachShader(mProgramId, mVertexShader); glDetachShader(mProgramId, mFragmentShader); @@ -132,6 +139,8 @@ int Program::getUniform(const char* name) { } GLuint Program::buildShader(const char* source, GLenum type) { + ATRACE_CALL(); + GLuint shader = glCreateShader(type); glShaderSource(shader, 1, &source, 0); glCompileShader(shader); @@ -153,20 +162,24 @@ GLuint Program::buildShader(const char* source, GLenum type) { void Program::set(const mat4& projectionMatrix, const mat4& modelViewMatrix, const mat4& transformMatrix, bool offset) { - mat4 p(projectionMatrix); - if (offset) { - // offset screenspace xy by an amount that compensates for typical precision - // issues in GPU hardware that tends to paint hor/vert lines in pixels shifted - // up and to the left. - // This offset value is based on an assumption that some hardware may use as - // little as 12.4 precision, so we offset by slightly more than 1/16. - p.translate(.065, .065, 0); + if (projectionMatrix != mProjection) { + if (CC_LIKELY(!offset)) { + glUniformMatrix4fv(projection, 1, GL_FALSE, &projectionMatrix.data[0]); + } else { + mat4 p(projectionMatrix); + // offset screenspace xy by an amount that compensates for typical precision + // issues in GPU hardware that tends to paint hor/vert lines in pixels shifted + // up and to the left. + // This offset value is based on an assumption that some hardware may use as + // little as 12.4 precision, so we offset by slightly more than 1/16. + p.translate(.065, .065, 0); + glUniformMatrix4fv(projection, 1, GL_FALSE, &p.data[0]); + } + mProjection = projectionMatrix; } mat4 t(transformMatrix); t.multiply(modelViewMatrix); - - glUniformMatrix4fv(projection, 1, GL_FALSE, &p.data[0]); glUniformMatrix4fv(transform, 1, GL_FALSE, &t.data[0]); } -- cgit v1.2.3-59-g8ed1b