Sign in to follow this  

OpenGL OpenCL OpenGL interop

This topic is 1723 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

If you intended to correct an error in the post then please contact us.

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
1) clSetKernelArg(kernel, 0, sizeof(vbo), &vbo) should be: clSetKernelArg(kernel, 0, sizeof(cl_mem), &PositionArray) 2) remove clWaitForEvents(1, &wait) (it is not necessary) 3) clEnqueueNDRangeKernel can take NULL as a local size argument

Share this post


Link to post
Share on other sites

This topic is 1723 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

If you intended to correct an error in the post then please contact us.

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  

  • Similar Content

    • By xhcao
      Does sync be needed to read texture content after access texture image in compute shader?
      My simple code is as below,
      glUseProgram(program.get());
      glBindImageTexture(0, texture[0], 0, GL_FALSE, 3, GL_READ_ONLY, GL_R32UI);
      glBindImageTexture(1, texture[1], 0, GL_FALSE, 4, GL_WRITE_ONLY, GL_R32UI);
      glDispatchCompute(1, 1, 1);
      // Does sync be needed here?
      glUseProgram(0);
      glBindFramebuffer(GL_READ_FRAMEBUFFER, framebuffer);
      glFramebufferTexture2D(GL_READ_FRAMEBUFFER, GL_COLOR_ATTACHMENT0,
                                     GL_TEXTURE_CUBE_MAP_POSITIVE_X + face, texture[1], 0);
      glReadPixels(0, 0, kWidth, kHeight, GL_RED_INTEGER, GL_UNSIGNED_INT, outputValues);
       
      Compute shader is very simple, imageLoad content from texture[0], and imageStore content to texture[1]. Does need to sync after dispatchCompute?
    • By Jonathan2006
      My question: is it possible to transform multiple angular velocities so that they can be reinserted as one? My research is below:
      // This works quat quaternion1 = GEQuaternionFromAngleRadians(angleRadiansVector1); quat quaternion2 = GEMultiplyQuaternions(quaternion1, GEQuaternionFromAngleRadians(angleRadiansVector2)); quat quaternion3 = GEMultiplyQuaternions(quaternion2, GEQuaternionFromAngleRadians(angleRadiansVector3)); glMultMatrixf(GEMat4FromQuaternion(quaternion3).array); // The first two work fine but not the third. Why? quat quaternion1 = GEQuaternionFromAngleRadians(angleRadiansVector1); vec3 vector1 = GETransformQuaternionAndVector(quaternion1, angularVelocity1); quat quaternion2 = GEQuaternionFromAngleRadians(angleRadiansVector2); vec3 vector2 = GETransformQuaternionAndVector(quaternion2, angularVelocity2); // This doesn't work //quat quaternion3 = GEQuaternionFromAngleRadians(angleRadiansVector3); //vec3 vector3 = GETransformQuaternionAndVector(quaternion3, angularVelocity3); vec3 angleVelocity = GEAddVectors(vector1, vector2); // Does not work: vec3 angleVelocity = GEAddVectors(vector1, GEAddVectors(vector2, vector3)); static vec3 angleRadiansVector; vec3 angularAcceleration = GESetVector(0.0, 0.0, 0.0); // Sending it through one angular velocity later in my motion engine angleVelocity = GEAddVectors(angleVelocity, GEMultiplyVectorAndScalar(angularAcceleration, timeStep)); angleRadiansVector = GEAddVectors(angleRadiansVector, GEMultiplyVectorAndScalar(angleVelocity, timeStep)); glMultMatrixf(GEMat4FromEulerAngle(angleRadiansVector).array); Also how do I combine multiple angularAcceleration variables? Is there an easier way to transform the angular values?
    • By dpadam450
      I have this code below in both my vertex and fragment shader, however when I request glGetUniformLocation("Lights[0].diffuse") or "Lights[0].attenuation", it returns -1. It will only give me a valid uniform location if I actually use the diffuse/attenuation variables in the VERTEX shader. Because I use position in the vertex shader, it always returns a valid uniform location. I've read that I can share uniforms across both vertex and fragment, but I'm confused what this is even compiling to if this is the case.
       
      #define NUM_LIGHTS 2
      struct Light
      {
          vec3 position;
          vec3 diffuse;
          float attenuation;
      };
      uniform Light Lights[NUM_LIGHTS];
       
       
    • By pr033r
      Hello,
      I have a Bachelor project on topic "Implenet 3D Boid's algorithm in OpenGL". All OpenGL issues works fine for me, all rendering etc. But when I started implement the boid's algorithm it was getting worse and worse. I read article (http://natureofcode.com/book/chapter-6-autonomous-agents/) inspirate from another code (here: https://github.com/jyanar/Boids/tree/master/src) but it still doesn't work like in tutorials and videos. For example the main problem: when I apply Cohesion (one of three main laws of boids) it makes some "cycling knot". Second, when some flock touch to another it scary change the coordination or respawn in origin (x: 0, y:0. z:0). Just some streng things. 
      I followed many tutorials, change a try everything but it isn't so smooth, without lags like in another videos. I really need your help. 
      My code (optimalizing branch): https://github.com/pr033r/BachelorProject/tree/Optimalizing
      Exe file (if you want to look) and models folder (for those who will download the sources):
      http://leteckaposta.cz/367190436
      Thanks for any help...

    • By Andrija
      I am currently trying to implement shadow mapping into my project , but although i can render my depth map to the screen and it looks okay , when i sample it with shadowCoords there is no shadow.
      Here is my light space matrix calculation
      mat4x4 lightViewMatrix; vec3 sun_pos = {SUN_OFFSET * the_sun->direction[0], SUN_OFFSET * the_sun->direction[1], SUN_OFFSET * the_sun->direction[2]}; mat4x4_look_at(lightViewMatrix,sun_pos,player->pos,up); mat4x4_mul(lightSpaceMatrix,lightProjMatrix,lightViewMatrix); I will tweak the values for the size and frustum of the shadow map, but for now i just want to draw shadows around the player position
      the_sun->direction is a normalized vector so i multiply it by a constant to get the position.
      player->pos is the camera position in world space
      the light projection matrix is calculated like this:
      mat4x4_ortho(lightProjMatrix,-SHADOW_FAR,SHADOW_FAR,-SHADOW_FAR,SHADOW_FAR,NEAR,SHADOW_FAR); Shadow vertex shader:
      uniform mat4 light_space_matrix; void main() { gl_Position = light_space_matrix * transfMatrix * vec4(position, 1.0f); } Shadow fragment shader:
      out float fragDepth; void main() { fragDepth = gl_FragCoord.z; } I am using deferred rendering so i have all my world positions in the g_positions buffer
      My shadow calculation in the deferred fragment shader:
      float get_shadow_fac(vec4 light_space_pos) { vec3 shadow_coords = light_space_pos.xyz / light_space_pos.w; shadow_coords = shadow_coords * 0.5 + 0.5; float closest_depth = texture(shadow_map, shadow_coords.xy).r; float current_depth = shadow_coords.z; float shadow_fac = 1.0; if(closest_depth < current_depth) shadow_fac = 0.5; return shadow_fac; } I call the function like this:
      get_shadow_fac(light_space_matrix * vec4(position,1.0)); Where position is the value i got from sampling the g_position buffer
      Here is my depth texture (i know it will produce low quality shadows but i just want to get it working for now):
      sorry because of the compression , the black smudges are trees ... https://i.stack.imgur.com/T43aK.jpg
      EDIT: Depth texture attachment:
      glTexImage2D(GL_TEXTURE_2D, 0,GL_DEPTH_COMPONENT24,fbo->width,fbo->height,0,GL_DEPTH_COMPONENT,GL_FLOAT,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_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE); glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE); glFramebufferTexture2D(GL_FRAMEBUFFER, GL_DEPTH_ATTACHMENT, GL_TEXTURE_2D, fbo->depthTexture, 0);
  • Popular Now