Sign in to follow this  
assainator

OpenGL OpenCL OpenGL interop

Recommended Posts

Hello all,

I've been trying to work together an OpenCL particle demo but I get an error of which I have no idea what causes it and thus no idea how to fix it.

 

Once it get to the call of clEnqueueNDRangeKernel(...) I get an error "Access violation writing location 0xFFFFFFFD", yet none of the arguments I pass have that value.

 

I am kind of at a loss here so I have no idea what the problem is.

 

My particles update code:

void UpdateFunc(int)
{
	glutTimerFunc(30, UpdateFunc, 30);

	// Get workgroup size
	size_t global = NUM_PARTICLES;
	size_t local;
	cl_int err = clGetKernelWorkGroupInfo(kernel, deviceID, CL_KERNEL_WORK_GROUP_SIZE, sizeof(local), &local, nullptr);
	if(err != CL_SUCCESS)
	{
		std::cout << "Couldn't get work group info!" << std::endl;
		getchar();
		exit(-1);
	}

	// Aquire position vbo.
	err = clEnqueueAcquireGLObjects(commandQueue, 1, &PositionArray, 0, nullptr, nullptr);
	if(err != CL_SUCCESS)
	{
		std::cout << "Error when aquiring OGL object." << std::endl;
		getchar();
		exit(-1);
	}

	// run kernel.
	cl_event wait;
	err = clEnqueueNDRangeKernel(commandQueue, kernel, 1, nullptr, &global, &local, 0, nullptr, &wait);
	if(err != CL_SUCCESS)
	{
		std::cout << "Error when running kernel." << std::endl;
		getchar();
		exit(-1);
	}
	clWaitForEvents(1, &wait);
	clFinish(commandQueue);

	// release position vbo.
	err = clEnqueueReleaseGLObjects(commandQueue, 1, &PositionArray, 0, nullptr, nullptr);

	if(err != CL_SUCCESS)
	{
		std::cout << "Error when releasing OGL object." << std::endl;
		getchar();
		exit(-1);
	}

	glutPostRedisplay();
}

 

And my whole source:

#include <iostream>
#include <GL/glew.h>
#include <GL/glut.h>
#include <CL/cl.h>
#include <CL/cl_gl.h>

#define NUM_PARTICLES 1024

cl_platform_id platformID;
cl_device_id deviceID;
cl_program program;
cl_context context;
cl_command_queue commandQueue;
cl_kernel kernel;
cl_mem VelocityArray;
cl_mem PositionArray;
cl_event event;

GLuint vbo;

void RenderFunc();
void UpdateFunc(int);

char* getDeviceName(cl_device_id device);

int main(int argc, char **argv)
{
	std::cout << "Starting..." << std::endl;
	std::cout << "Using GPU config for acceleration." << std::endl;

	std::cout << "Simulating with " << NUM_PARTICLES << " particles." << std::endl;
	

	// Initialize glut.
	glutInit(&argc, argv);
	glutInitDisplayMode(GLUT_RGB | GLUT_DOUBLE | GLUT_DEPTH);
	glutInitWindowSize(1024, 768);
	glutInitWindowPosition(0,0);

	glutCreateWindow("OpenCL + OpenGL particles");

	// intialize glew
	glewInit();


	// Get first OpenCL platform.
	cl_int err = clGetPlatformIDs(1, &platformID, nullptr);
	if(err != CL_SUCCESS)
	{
		std::cout << "Couldn't find an OpenCL platform!" << std::endl;
		getchar();
		return -1;
	}

	// Get first OpenCL gpu device.
	err = clGetDeviceIDs(platformID, CL_DEVICE_TYPE_GPU, 1, &deviceID, nullptr);
	if(err != CL_SUCCESS)
	{
		std::cout << "Couldn't find a OpenCL enabled GPU!" << std::endl;
		getchar();
		return -1;
	}
	std::cout << "Using OpenCL device: " << getDeviceName(deviceID) << std::endl;

	// Create OpenCL create properties
	cl_context_properties props[] =
	{
		CL_GL_CONTEXT_KHR, (cl_context_properties)wglGetCurrentContext(),
		CL_WGL_HDC_KHR, (cl_context_properties)wglGetCurrentDC(),
		CL_CONTEXT_PLATFORM, (cl_context_properties)platformID,
		0
	};

	// Create an OpenCL context.
	context = clCreateContext(props, 1, &deviceID, nullptr, nullptr, &err);
	if(!context || err != CL_SUCCESS)
	{
		std::cout << "Couldn't create an OpenCL context." << std::endl;
		getchar();
		return -1;
	}

	// Create a command queue.
	commandQueue = clCreateCommandQueue(context, deviceID, 0, &err);
	if(!commandQueue || err != CL_SUCCESS)
	{
		std::cout << "Couldn't create a command queue for OpenCL." << std::endl;
		getchar();
		return -1;
	}

	// Load OpenCL code.
	FILE* stream = fopen("particles.kernel.cl", "rb");
	fseek(stream, 0, SEEK_END);
	unsigned int len = ftell(stream);
	fseek(stream, 0, SEEK_SET);
	char * KernelSource = (char*)malloc(len + 1);
	fread(KernelSource, sizeof(char), len, stream);
	KernelSource[len] = '\0';
	fclose(stream);

	// Create a program.
	program = clCreateProgramWithSource(context, 1, (const char**)&KernelSource, nullptr, &err);
	if(!program || err != CL_SUCCESS)
	{
		std::cout << "Couldn't create a program." << std::endl;
		getchar();
		return -1;
	}

	// Build the program.
	err = clBuildProgram(program, 0, nullptr, nullptr, nullptr, nullptr);
	if(err != CL_SUCCESS)
	{
		std::cout << "Couldn't build the program:" << std::endl;
		std::cout << "Build log:" << std::endl;

		char buffer[2048];
		clGetProgramBuildInfo(program, deviceID, CL_PROGRAM_BUILD_LOG, sizeof(buffer), buffer, nullptr);
		std::cout << buffer << std::endl << "-- End of build log -- " << std::endl;

		getchar();
		return -1;
	}

	// Create a kernel.
	kernel = clCreateKernel(program, "particle_cycle", &err);
	if(!kernel || err != CL_SUCCESS)
	{
		std::cout << "Couldn't create a kernel from the program.";
		getchar();
		return -1;
	}

	
	glutDisplayFunc(RenderFunc);
	glutTimerFunc(30, UpdateFunc, 30);

	// initialize opengl
	glClearColor(0,0,0,0);
	glViewport(0,0,1024, 768);

	glMatrixMode(GL_PROJECTION);
	glLoadIdentity();
	gluPerspective(90.0, (float)1024/768, 0.1, 1000.0);

	glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
	glMatrixMode(GL_MODELVIEW);
	glLoadIdentity();
	glTranslatef(0,0, -1.0f);

	// Create position VBO
	glGenBuffers(1, &vbo);
	glBindBuffer(GL_ARRAY_BUFFER, vbo);

	float* initialPos = new float[4 * sizeof(float) * NUM_PARTICLES];
	for(unsigned int i = 0; i < NUM_PARTICLES; i++)
	{
		initialPos[i] = rand() / (float)RAND_MAX;
	}

	// Upload data to OGL
	glBufferData(GL_ARRAY_BUFFER, 4 * sizeof(float) * NUM_PARTICLES, initialPos, GL_DYNAMIC_DRAW);

	// Bind vbo to cl buffer
	PositionArray = clCreateFromGLBuffer(context, CL_MEM_READ_WRITE, vbo, nullptr);

	// Create velocity array.
	float *velocity = new float[4 * sizeof(float) * NUM_PARTICLES];
	for(unsigned int i = 0; i < NUM_PARTICLES; i++)
	{
		initialPos[i] = rand() / (float)RAND_MAX;
	}

	// Create OpenCL buffer object.
	VelocityArray = clCreateBuffer(context, CL_MEM_READ_ONLY, 4 * sizeof(float) * NUM_PARTICLES, nullptr, nullptr);
	if(!VelocityArray)
	{
		std::cout << "Couldn't create a buffer for the particle velocities." << std::endl;
		getchar();
		return -1;
	}

	// Upload data and associate buffer with the context.
	err = clEnqueueWriteBuffer(commandQueue, VelocityArray, CL_TRUE, 0, 4 * sizeof(float) * NUM_PARTICLES, velocity, 0, nullptr, nullptr);
	if(err != CL_SUCCESS)
	{
		std::cout << "Couldn't upload particle velocities to the context." << std::endl;
		getchar();
		return -1;
	}

	// Set the kernel arguments.
	float dt = 0.03;
	clSetKernelArg(kernel, 0, sizeof(vbo), &vbo); 
	clSetKernelArg(kernel, 1, sizeof(cl_mem), &VelocityArray);
	clSetKernelArg(kernel, 2, sizeof(float), &dt);

	// start application
	glutMainLoop();
}

void RenderFunc()
{
	// Clear
	glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);

	//Enable blending, set point size
	glEnable(GL_BLEND);
	glBlendFunc(GL_SRC_ALPHA, GL_ONE_MINUS_SRC_ALPHA);
	glEnable(GL_POINT_SMOOTH);
	glPointSize(5.0f);

	// Bind buffer
	glBindBuffer(GL_ARRAY_BUFFER, vbo);

	// Enable drawing
	glVertexPointer(4, GL_FLOAT, 0, nullptr);
	glEnableClientState(GL_VERTEX_ARRAY);

	// Draw the array.
	glDrawArrays(GL_POINTS, 0, NUM_PARTICLES);

	// Disable drawing.
	glDisableClientState(GL_VERTEX_ARRAY);
	glBindBuffer(GL_ARRAY_BUFFER, 0);

	// Swap buffers
	glutSwapBuffers();
}

void UpdateFunc(int)
{
	glutTimerFunc(30, UpdateFunc, 30);

	// Get workgroup size
	size_t global = NUM_PARTICLES;
	size_t local;
	cl_int err = clGetKernelWorkGroupInfo(kernel, deviceID, CL_KERNEL_WORK_GROUP_SIZE, sizeof(local), &local, nullptr);
	if(err != CL_SUCCESS)
	{
		std::cout << "Couldn't get work group info!" << std::endl;
		getchar();
		exit(-1);
	}

	// Aquire position vbo.
	err = clEnqueueAcquireGLObjects(commandQueue, 1, &PositionArray, 0, nullptr, nullptr);
	if(err != CL_SUCCESS)
	{
		std::cout << "Error when aquiring OGL object." << std::endl;
		getchar();
		exit(-1);
	}

	// run kernel.
	cl_event wait;
	err = clEnqueueNDRangeKernel(commandQueue, kernel, 1, nullptr, &global, &local, 0, nullptr, nullptr);
	if(err != CL_SUCCESS)
	{
		std::cout << "Error when running kernel." << std::endl;
		getchar();
		exit(-1);
	}
	clWaitForEvents(1, &wait);
	clFinish(commandQueue);

	// release position vbo.
	err = clEnqueueReleaseGLObjects(commandQueue, 1, &PositionArray, 0, nullptr, nullptr);

	if(err != CL_SUCCESS)
	{
		std::cout << "Error when releasing OGL object." << std::endl;
		getchar();
		exit(-1);
	}

	glutPostRedisplay();
}

char* getDeviceName(cl_device_id device)
{
	char deviceName[512];
	size_t deviceNameSize;
	cl_int err = clGetDeviceInfo(device, CL_DEVICE_NAME, sizeof(deviceName), deviceName, &deviceNameSize);

	if(err != CL_SUCCESS)
	{
		return nullptr;
	}
	else
	{
		return strdup(deviceName);
	}
}

The kernel:

__kernel void particle_cycle(__global float4* pos, __read_only __global float4* vel, __read_only float dt)
{
	const size_t i = get_global_id(0);

	float4 v = vel[i];
	float4 p = pos[i];

	p += (v * dt);

	pos[i] = p;
}

 

EDIT:

I forgot my setup:

- Windows 8 Pro x64

- Visual Studio 2012 Express

- AMD APP SDK v2.8

- AMD Radeon HD 7850

 

 

Thanks a lot in advance for any help.

Edited by assainator

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

Sign in to follow this  

  • Announcements

  • Forum Statistics

    • Total Topics
      628350
    • Total Posts
      2982211
  • Similar Content

    • By test opty
      Hi all,
       
      I'm starting OpenGL using a tut on the Web. But at this point I would like to know the primitives needed for creating a window using OpenGL. So on Windows and using MS VS 2017, what is the simplest code required to render a window with the title of "First Rectangle", please?
       
       
    • By DejayHextrix
      Hi, New here. 
      I need some help. My fiance and I like to play this mobile game online that goes by real time. Her and I are always working but when we have free time we like to play this game. We don't always got time throughout the day to Queue Buildings, troops, Upgrades....etc.... 
      I was told to look into DLL Injection and OpenGL/DirectX Hooking. Is this true? Is this what I need to learn? 
      How do I read the Android files, or modify the files, or get the in-game tags/variables for the game I want? 
      Any assistance on this would be most appreciated. I been everywhere and seems no one knows or is to lazy to help me out. It would be nice to have assistance for once. I don't know what I need to learn. 
      So links of topics I need to learn within the comment section would be SOOOOO.....Helpful. Anything to just get me started. 
      Thanks, 
      Dejay Hextrix 
    • By mellinoe
      Hi all,
      First time poster here, although I've been reading posts here for quite a while. This place has been invaluable for learning graphics programming -- thanks for a great resource!
      Right now, I'm working on a graphics abstraction layer for .NET which supports D3D11, Vulkan, and OpenGL at the moment. I have implemented most of my planned features already, and things are working well. Some remaining features that I am planning are Compute Shaders, and some flavor of read-write shader resources. At the moment, my shaders can just get simple read-only access to a uniform (or constant) buffer, a texture, or a sampler. Unfortunately, I'm having a tough time grasping the distinctions between all of the different kinds of read-write resources that are available. In D3D alone, there seem to be 5 or 6 different kinds of resources with similar but different characteristics. On top of that, I get the impression that some of them are more or less "obsoleted" by the newer kinds, and don't have much of a place in modern code. There seem to be a few pivots:
      The data source/destination (buffer or texture) Read-write or read-only Structured or unstructured (?) Ordered vs unordered (?) These are just my observations based on a lot of MSDN and OpenGL doc reading. For my library, I'm not interested in exposing every possibility to the user -- just trying to find a good "middle-ground" that can be represented cleanly across API's which is good enough for common scenarios.
      Can anyone give a sort of "overview" of the different options, and perhaps compare/contrast the concepts between Direct3D, OpenGL, and Vulkan? I'd also be very interested in hearing how other folks have abstracted these concepts in their libraries.
    • By aejt
      I recently started getting into graphics programming (2nd try, first try was many years ago) and I'm working on a 3d rendering engine which I hope to be able to make a 3D game with sooner or later. I have plenty of C++ experience, but not a lot when it comes to graphics, and while it's definitely going much better this time, I'm having trouble figuring out how assets are usually handled by engines.
      I'm not having trouble with handling the GPU resources, but more so with how the resources should be defined and used in the system (materials, models, etc).
      This is my plan now, I've implemented most of it except for the XML parts and factories and those are the ones I'm not sure of at all:
      I have these classes:
      For GPU resources:
      Geometry: holds and manages everything needed to render a geometry: VAO, VBO, EBO. Texture: holds and manages a texture which is loaded into the GPU. Shader: holds and manages a shader which is loaded into the GPU. For assets relying on GPU resources:
      Material: holds a shader resource, multiple texture resources, as well as uniform settings. Mesh: holds a geometry and a material. Model: holds multiple meshes, possibly in a tree structure to more easily support skinning later on? For handling GPU resources:
      ResourceCache<T>: T can be any resource loaded into the GPU. It owns these resources and only hands out handles to them on request (currently string identifiers are used when requesting handles, but all resources are stored in a vector and each handle only contains resource's index in that vector) Resource<T>: The handles given out from ResourceCache. The handles are reference counted and to get the underlying resource you simply deference like with pointers (*handle).  
      And my plan is to define everything into these XML documents to abstract away files:
      Resources.xml for ref-counted GPU resources (geometry, shaders, textures) Resources are assigned names/ids and resource files, and possibly some attributes (what vertex attributes does this geometry have? what vertex attributes does this shader expect? what uniforms does this shader use? and so on) Are reference counted using ResourceCache<T> Assets.xml for assets using the GPU resources (materials, meshes, models) Assets are not reference counted, but they hold handles to ref-counted resources. References the resources defined in Resources.xml by names/ids. The XMLs are loaded into some structure in memory which is then used for loading the resources/assets using factory classes:
      Factory classes for resources:
      For example, a texture factory could contain the texture definitions from the XML containing data about textures in the game, as well as a cache containing all loaded textures. This means it has mappings from each name/id to a file and when asked to load a texture with a name/id, it can look up its path and use a "BinaryLoader" to either load the file and create the resource directly, or asynchronously load the file's data into a queue which then can be read from later to create the resources synchronously in the GL context. These factories only return handles.
      Factory classes for assets:
      Much like for resources, these classes contain the definitions for the assets they can load. For example, with the definition the MaterialFactory will know which shader, textures and possibly uniform a certain material has, and with the help of TextureFactory and ShaderFactory, it can retrieve handles to the resources it needs (Shader + Textures), setup itself from XML data (uniform values), and return a created instance of requested material. These factories return actual instances, not handles (but the instances contain handles).
       
       
      Is this a good or commonly used approach? Is this going to bite me in the ass later on? Are there other more preferable approaches? Is this outside of the scope of a 3d renderer and should be on the engine side? I'd love to receive and kind of advice or suggestions!
      Thanks!
    • By nedondev
      I 'm learning how to create game by using opengl with c/c++ coding, so here is my fist game. In video description also have game contain in Dropbox. May be I will make it better in future.
      Thanks.
  • Popular Now