我有一个500万像素的纹理,更新时遇到问题。纹理显示在与视频流没有什么不同的矩形上。
OpenGL命令执行速度很快,但实际纹理更新率是次优的,可能每秒只有3个实际帧。使用较小的纹理(500x500(时会有一些变化,但变化不大。
该机器具有NVIDIA gtx 570
我最初的努力是使用glTexSubImage2D
和glBufferSubData
,但它们的性能比内存映射方案稍差。
有没有办法强制显卡更新纹理?视频流软件是如何编写的?
渲染循环
void glStream::paintGL()
{
glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
glLoadIdentity();
program1.bind();
program1.setUniformValue("texture", 0);
program1.enableAttributeArray(vertexAttr1);
program1.enableAttributeArray(vertexTexr1);
program1.setAttributeArray(vertexAttr1, vertices.constData());
program1.setAttributeArray(vertexTexr1, texCoords.constData());
//
glECheck();
glBindTexture(GL_TEXTURE_2D, textures[0]);
glBindBuffer(GL_PIXEL_UNPACK_BUFFER_ARB,pbos[0]);
void* memory = glMapBuffer(GL_PIXEL_UNPACK_BUFFER_ARB,GL_WRITE_ONLY);
device->fillBuffer((unsigned char *)memory,heightGL,widthGL); // takes 2ms (not long)
glUnmapBuffer(GL_PIXEL_UNPACK_BUFFER_ARB);
glTexSubImage2D(GL_TEXTURE_2D,0,0,0,widthGL,heightGL,GL_LUMINANCE,GL_UNSIGNED_BYTE, NULL);
glDrawArrays(GL_TRIANGLES, 0, vertices.size());
glBindBuffer(GL_PIXEL_UNPACK_BUFFER_ARB,0);
glBindTexture(GL_TEXTURE_2D,0);
//
program1.disableAttributeArray(vertexTexr1);
program1.disableAttributeArray(vertexAttr1);
program1.release();
glECheck();//no errors
}
纹理保留
void glStream::reserveTextures()
{
assert(numGLFrames>0);
assert(glGenBuffers);
displayBuff = (GLubyte*) calloc(numGLFrames*widthGL*heightGL,sizeof(GLubyte));//GL_RGB8
memset(displayBuff,100,numGLFrames*widthGL*heightGL*sizeof(GLubyte));
glGenBuffers(1,&pbos[0]);
glBindBuffer(GL_PIXEL_UNPACK_BUFFER_ARB, pbos[0]);
glBufferData(GL_PIXEL_UNPACK_BUFFER_ARB,
numGLFrames*widthGL*heightGL*sizeof(GLubyte),
&displayBuff[0], GL_STREAM_DRAW);
glBindBuffer(GL_PIXEL_UNPACK_BUFFER_ARB, 0);
glGenTextures(1,&textures[0]);
glBindTexture(GL_TEXTURE_2D,textures[0]);
glTexImage2D(GL_TEXTURE_2D,0,GL_LUMINANCE,
widthGL,heightGL,0,GL_LUMINANCE,GL_UNSIGNED_BYTE,NULL);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR);
glTexParameteri(GL_TEXTURE_2D, GL_GENERATE_MIPMAP, GL_FALSE);
glBindTexture(GL_TEXTURE_2D,0);
}
初始化
void glStream::initializeGL()
{
GLenum err = glewInit();
if (GLEW_OK != err)
{
const char * emssage = (const char*)glewGetErrorString(err);
QMessageBox::information(0, "OpenGL 3.x Context Example",
emssage);
exit(20);
}
glDisable(GL_DEPTH_TEST);
QGLShader *vshader1 = new QGLShader(QGLShader::Vertex, this);
const char *vsrc1 =
"attribute vec2 coord2d; n"
"attribute mediump vec4 texCoord;n"
"varying mediump vec4 texc;n"
"void main() n"
"{ n"
" gl_Position = vec4(coord2d, 0.0, 1.0); n"
" texc = texCoord;n"
"} n";
vshader1->compileSourceCode(vsrc1);
QGLShader *fshader1 = new QGLShader(QGLShader::Fragment, this);
const char *fsrc1 =
"uniform sampler2D texture;n"
"varying mediump vec4 texc;n"
"void main(void)n"
"{n"
" gl_FragColor = texture2D(texture, texc.st);n"
"}n";
fshader1->compileSourceCode(fsrc1);
program1.addShader(vshader1);
program1.addShader(fshader1);
program1.link();
vertexAttr1 = program1.attributeLocation( "coord2d");
vertexTexr1 = program1.attributeLocation( "texCoord");
// Create the vertex buffer.
vertices.clear();
float u=1;
#define AVEC -u,u
#define BVEC -u,-u
#define CVEC u,u
#define DVEC u,-u
vertices << QVector2D(AVEC);vertices << QVector2D(BVEC);
vertices << QVector2D(CVEC);vertices << QVector2D(BVEC);
vertices << QVector2D(DVEC);vertices << QVector2D(CVEC);
// Create the texture vertex buffer
#define TAVEC 0,1
#define TBVEC 0,0
#define TCVEC 1,1
#define TDVEC 1,0
texCoords << QVector2D(TAVEC);texCoords << QVector2D(TBVEC);
texCoords << QVector2D(TCVEC);texCoords << QVector2D(TBVEC);
texCoords << QVector2D(TDVEC);texCoords << QVector2D(TCVEC);
glECheck();
reserveTextures();
}
编辑1
我相信填充缓冲区会产生一个新的纹理,因为在代码的其他部分,我将这个纹理写入文件,它确实不同。当我的文件IO比OpenGL纹理更快时,这是一个悲伤的日子。
编辑2我尝试了FRAPS,并验证了渲染循环的速度约为18 FPS,但可见更新速度较慢(可能为3 FPS(。什么能解释这样的差异?
在对glBufferData:的调用中,PBO比纹理大得多
numGLFrames*widthGL*heightGL*sizeof(GLubyte)
您正在为多个纹理(帧(分配足够大的PBO,但只能读取/写入一帧的数据。
如果您使PBO与纹理大小相同,并使用glTexImage2D而不是glTexSubImage2D,它会更快吗?