我正在使用CUDA编写渲染系统,希望通过OpenGL快速显示结果,而不触及主内存。我的基本思路如下:
创建并初始化OpenGL纹理,并将其在CUDA中注册为cudaGraphicsResource。
GLuint viewGLTexture;
cudaGraphicsResource_t viewCudaResource;
void initialize() {
glEnable(GL_TEXTURE_2D);
glGenTextures(1, &viewGLTexture);
glBindTexture(GL_TEXTURE_2D, viewGLTexture);
{
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA, view.getWidth(), view.getHeight(), 0, GL_RGBA, GL_UNSIGNED_BYTE, NULL);
}
glBindTexture(GL_TEXTURE_2D, 0);
cudaGraphicsGLRegisterImage(&viewCudaResource, viewGLTexture, GL_TEXTURE_2D, cudaGraphicsRegisterFlagsWriteDiscard)
}
每当视图被调整大小时,我会相应地调整视口和纹理图像的大小:
void resize() {
glViewport(0, 0, view.getWidth(), view.getHeight());
glBindTexture(GL_TEXTURE_2D, viewGLTexture);
{
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA, view.getWidth(), view.getHeight(), 0, GL_RGBA, GL_UNSIGNED_BYTE, NULL);
}
glBindTexture(GL_TEXTURE_2D, 0);
}
然后我将graphicsResource映射为cudaArray上的cudaSurfaceObject,对其调用渲染内核,在渲染完成后取消映射并同步以便让OpenGL使用此纹理绘制全屏四边形:
void renderFrame() {
cudaGraphicsMapResources(1, &viewCudaResource);
{
cudaArray_t viewCudaArray;
cudaGraphicsSubResourceGetMappedArray(&viewCudaArray, viewCudaResource, 0, 0);
cudaResourceDesc viewCudaArrayResourceDesc;
{
viewCudaArrayResourceDesc.resType = cudaResourceTypeArray;
viewCudaArrayResourceDesc.res.array.array = viewCudaArray;
}
cudaSurfaceObject_t viewCudaSurfaceObject;
cudaCreateSurfaceObject(&viewCudaSurfaceObject, &viewCudaArrayResourceDesc);
{
invokeRenderingKernel(viewCudaSurfaceObject);
}
cudaDestroySurfaceObject(viewCudaSurfaceObject));
}
cudaGraphicsUnmapResources(1, &viewCudaResource);
cudaStreamSynchronize(0);
glBindTexture(GL_TEXTURE_2D, viewGLTexture);
{
glBegin(GL_QUADS);
{
glTexCoord2f(0.0f, 0.0f); glVertex2f(-1.0f, -1.0f);
glTexCoord2f(1.0f, 0.0f); glVertex2f(+1.0f, -1.0f);
glTexCoord2f(1.0f, 1.0f); glVertex2f(+1.0f, +1.0f);
glTexCoord2f(0.0f, 1.0f); glVertex2f(-1.0f, +1.0f);
}
glEnd();
}
glBindTexture(GL_TEXTURE_2D, 0);
glFinish();
}
问题是:每当视图被调整大小时,所有CUDA调用都开始喷出“未知错误”,并且在视觉上看来,纹理实际上没有被调整大小,只是跨越整个视图被拉伸。为什么会发生这种情况,我该如何解决?