QGLWidget + OpenGL + CUDA

[sic(6)SaNdMaN]

Well... after nearly three weeks of unsuccessful work on this I decided to create a topic here...
Now, one day later I found my "mistake"... you have to use glTexSubImage2D() instead of glTexImage2D() wit same parameters... even if you want to read the whole image.

I don't get it... but here's some working code, for anybody, that comes across this thread (this time in CODE-tags instead of QUOTE-tags ):

void GLWidget::initializeGL()
{
	makeCurrent();
 
	cudaGLSetGLDevice(cutGetMaxGflopsDeviceId() );
 
	int c=1;
	char* dummy = "";
	glutInit( &c, &dummy );
 
	glewInit();
 
	unsigned int w, h;
	char data[1024];
	strncpy(data, getImagePath().toLatin1(), sizeof(data) - 1);
	const char* image_filename = data;
 
	if (cutLoadPPM4ub(image_filename, &pixels, &w, &h) != CUTTrue) {
		printf("Failed to load image file: %s\n", image_filename);
		exit(-1);
	}
 
 
	GLint bsize;
	setupTexture(m_pQImage.width(), m_pQImage.height(), pixels, 4);
 
	memset(pixels, 0x0, 4 * sizeof(Pixel) * m_pQImage.width() * m_pQImage.height());
 
	// use OpenGL Path
	glGenBuffers(1, &pbo_buffer);
	glBindBuffer(GL_PIXEL_UNPACK_BUFFER, pbo_buffer); 
	glBufferData(GL_PIXEL_UNPACK_BUFFER, 
					4 * sizeof(Pixel) * m_pQImage.width() * m_pQImage.height(), 
					pixels, GL_STREAM_DRAW);
 
	glGetBufferParameteriv(GL_PIXEL_UNPACK_BUFFER, GL_BUFFER_SIZE, &bsize);
	if ((GLuint)bsize != (4 * sizeof(Pixel) * m_pQImage.width() * m_pQImage.height()))
	{
		printf("Buffer object (%d) has incorrect size (%d).\n", (unsigned)pbo_buffer, (unsigned)bsize);
		cudaThreadExit();
		exit(-1);
	}
 
	glBindBuffer(GL_PIXEL_UNPACK_BUFFER, 0);
 
	// register this buffer object with CUDA
	cutilSafeCall(cudaGraphicsGLRegisterBuffer(&cuda_pbo_resource, pbo_buffer, cudaGraphicsMapFlagsWriteDiscard));	
 
 
	glGenTextures  (1, &m_pTexture);
	glBindTexture  (GL_TEXTURE_2D, m_pTexture);
	glTexImage2D   (GL_TEXTURE_2D, 0, GL_RGBA, m_pQImage.width(), m_pQImage.height(), 0, GL_RGBA, GL_UNSIGNED_BYTE, NULL);
	glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR);
	glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
	glBindTexture  (GL_TEXTURE_2D, 0);
 
	glPixelStorei  (GL_UNPACK_ALIGNMENT, 1);
	glPixelStorei  (GL_PACK_ALIGNMENT, 1);
}

void GLWidget::initializeGL()
{
	makeCurrent();

	cudaGLSetGLDevice(cutGetMaxGflopsDeviceId() );

	int c=1;
	char* dummy = "";
	glutInit( &c, &dummy );

	glewInit();

	unsigned int w, h;
	char data[1024];
	strncpy(data, getImagePath().toLatin1(), sizeof(data) - 1);
	const char* image_filename = data;

	if (cutLoadPPM4ub(image_filename, &pixels, &w, &h) != CUTTrue) {
		printf("Failed to load image file: %s\n", image_filename);
		exit(-1);
	}


	GLint bsize;
	setupTexture(m_pQImage.width(), m_pQImage.height(), pixels, 4);

	memset(pixels, 0x0, 4 * sizeof(Pixel) * m_pQImage.width() * m_pQImage.height());

	// use OpenGL Path
	glGenBuffers(1, &pbo_buffer);
	glBindBuffer(GL_PIXEL_UNPACK_BUFFER, pbo_buffer); 
	glBufferData(GL_PIXEL_UNPACK_BUFFER, 
					4 * sizeof(Pixel) * m_pQImage.width() * m_pQImage.height(), 
					pixels, GL_STREAM_DRAW);

	glGetBufferParameteriv(GL_PIXEL_UNPACK_BUFFER, GL_BUFFER_SIZE, &bsize);
	if ((GLuint)bsize != (4 * sizeof(Pixel) * m_pQImage.width() * m_pQImage.height()))
	{
		printf("Buffer object (%d) has incorrect size (%d).\n", (unsigned)pbo_buffer, (unsigned)bsize);
		cudaThreadExit();
		exit(-1);
	}

	glBindBuffer(GL_PIXEL_UNPACK_BUFFER, 0);

	// register this buffer object with CUDA
	cutilSafeCall(cudaGraphicsGLRegisterBuffer(&cuda_pbo_resource, pbo_buffer, cudaGraphicsMapFlagsWriteDiscard));	


	glGenTextures  (1, &m_pTexture);
	glBindTexture  (GL_TEXTURE_2D, m_pTexture);
	glTexImage2D   (GL_TEXTURE_2D, 0, GL_RGBA, m_pQImage.width(), m_pQImage.height(), 0, GL_RGBA, GL_UNSIGNED_BYTE, NULL);
	glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR);
	glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
	glBindTexture  (GL_TEXTURE_2D, 0);

	glPixelStorei  (GL_UNPACK_ALIGNMENT, 1);
	glPixelStorei  (GL_PACK_ALIGNMENT, 1);
}

To copy to clipboard, switch view to plain text mode 

void GLWidget::paintGL()
{
	makeCurrent();
 
	glMatrixMode(GL_PROJECTION);
	glLoadIdentity();
	glMatrixMode(GL_MODELVIEW);
 
	// Sobel operation
	Pixel *data = NULL;
 
	// map PBO to get CUDA device pointer
	cutilSafeCall(cudaGraphicsMapResources(1, &cuda_pbo_resource, 0));
	size_t num_bytes; 
	cutilSafeCall(cudaGraphicsResourceGetMappedPointer((void **)&data, &num_bytes,  
							   cuda_pbo_resource));
	qDebug() << QString("CUDA mapped PBO: May access %1 bytes").arg(num_bytes);
 
	sobelFilter(data, m_pQImage.width(), m_pQImage.height(), SOBELDISPLAY_IMAGE, 1.0f);
	cutilSafeCall(cudaGraphicsUnmapResources(1, &cuda_pbo_resource, 0));
 
	glClear(GL_COLOR_BUFFER_BIT);
 
	glBindTexture(GL_TEXTURE_2D, m_pTexture);
	glBindBuffer(GL_PIXEL_UNPACK_BUFFER, pbo_buffer);
	glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, m_pQImage.width(), m_pQImage.height(), 
					GL_LUMINANCE, GL_UNSIGNED_BYTE, (char *)NULL);
	glBindBuffer(GL_PIXEL_UNPACK_BUFFER, 0);
 
	glDisable(GL_DEPTH_TEST);
	glEnable(GL_TEXTURE_2D);
	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR);
	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_REPEAT);
	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_REPEAT);
 
	glBegin(GL_QUADS);
		glVertex2f(-1, -1); glTexCoord2f(0, 0);
		glVertex2f(-1,  1); glTexCoord2f(1, 0);
		glVertex2f( 1,  1); glTexCoord2f(1, 1);
		glVertex2f( 1, -1); glTexCoord2f(0, 1);
	glEnd();
 
	//glDisable(GL_TEXTURE_2D);
	glBindTexture(GL_TEXTURE_2D, 0);
 
	swapBuffers();
}

void GLWidget::paintGL()
{
	makeCurrent();

	glMatrixMode(GL_PROJECTION);
	glLoadIdentity();
	glMatrixMode(GL_MODELVIEW);

	// Sobel operation
	Pixel *data = NULL;

	// map PBO to get CUDA device pointer
	cutilSafeCall(cudaGraphicsMapResources(1, &cuda_pbo_resource, 0));
	size_t num_bytes; 
	cutilSafeCall(cudaGraphicsResourceGetMappedPointer((void **)&data, &num_bytes,  
							   cuda_pbo_resource));
	qDebug() << QString("CUDA mapped PBO: May access %1 bytes").arg(num_bytes);
	
	sobelFilter(data, m_pQImage.width(), m_pQImage.height(), SOBELDISPLAY_IMAGE, 1.0f);
	cutilSafeCall(cudaGraphicsUnmapResources(1, &cuda_pbo_resource, 0));

	glClear(GL_COLOR_BUFFER_BIT);

	glBindTexture(GL_TEXTURE_2D, m_pTexture);
	glBindBuffer(GL_PIXEL_UNPACK_BUFFER, pbo_buffer);
	glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, m_pQImage.width(), m_pQImage.height(), 
					GL_LUMINANCE, GL_UNSIGNED_BYTE, (char *)NULL);
	glBindBuffer(GL_PIXEL_UNPACK_BUFFER, 0);

	glDisable(GL_DEPTH_TEST);
	glEnable(GL_TEXTURE_2D);
	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_LINEAR);
	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_LINEAR);
	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_REPEAT);
	glTexParameterf(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_REPEAT);
		
	glBegin(GL_QUADS);
		glVertex2f(-1, -1); glTexCoord2f(0, 0);
		glVertex2f(-1,  1); glTexCoord2f(1, 0);
		glVertex2f( 1,  1); glTexCoord2f(1, 1);
		glVertex2f( 1, -1); glTexCoord2f(0, 1);
	glEnd();

	//glDisable(GL_TEXTURE_2D);
	glBindTexture(GL_TEXTURE_2D, 0);

	swapBuffers();
}

To copy to clipboard, switch view to plain text mode 

Cheers!

[jpapon]

Quick question for you about compiling this; where exactly do you use the nvcc compiler in all this?
Do you need to compile the Sobel filter separately using nvcc and then link to the library?

Thanks in advance!

[sic(6)SaNdMaN]

Quick question for you about compiling this; where exactly do you use the nvcc compiler in all this?
Do you need to compile the Sobel filter separately using nvcc and then link to the library?

Thanks in advance!

Yes, normally (!) all cu files have to be compiled with nvcc.

[jpapon]

Yeah, I just didn't see any reference to a pre compiled library in the .pro file.
I'm just adding a subdirectory, placing the kernel in it, compiling to a static lib.
Then I'm just linking to the library in the .pro file. Does that sound like the correct procedure?

Then I need to figure out how to put a command in a .pro file so the qmake generated makefile also runs the make in the subdirectory.

[Zeus13i]

Hi,

I am trying to do something similar, but I'm finding that I cannot register the cuda resource from outside of the GLWidget... if I call cudaGraphicsGLRegisterBuffer from my QGLWidget everything is fine, but I wanted to seperate the logic into a different class, say 'Worker'.

So I tried sending a signal to the main window when the QGLWidget has initialized OpenGL/VBO's and then spawn my Worker class (which is a thread and in which I wish to run my CUDA kernels).

I just get a segfault. Does anyone see why I shouldn't be able to do this?

Thanks