Hello Im using 9800GT and 9500GT in windows platform. Following is my code.
// includes, system
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
// includes, GL
#include <GL/glew.h>
//#include <GL/freeglut.h>
#include <GL/glut.h>
#include <cuda.h>
#include <cudaGL.h>
// includes CUDA <--> C++ interlops
#include <cuda_runtime.h>
#include <cutil_inline.h>
#include <cutil_gl_inline.h>
#include <cutil_gl_error.h>
#include <cuda_gl_interop.h>
//define variables
#define XDIM 1000 //original value 1000
#define YDIM 1024 //original value 1024
const unsigned int window_width = 1000;
const unsigned int window_height = 1024;
float4 *d_vbo_buffer;
// pbo variables
GLuint pbo;
struct cudaGraphicsResource *cuda_pbo_resource;
extern "C"
void launch_kernel(int* sum, float* original_data, int* frame_num, cuComplex* d, float* k_resamp, float* dc_subtracted, float* resample, float4 *ptr);
//simply use cudaGraphicsMapFlagsWriteDiscard as cudaGraphicsResource
void createVBO(GLuint* pixel_buffer, struct cudaGraphicsResource **cuda_pixel_resource)
{
if(pixel_buffer){
// create buffer object
glGenBuffers(1, pixel_buffer);
glBindBuffer(GL_ARRAY_BUFFER, *pixel_buffer);
//register buffer on cuda
unsigned int size = XDIM * YDIM * 4 * sizeof(float);
glBufferData(GL_ARRAY_BUFFER, size, 0, GL_DYNAMIC_DRAW);
glBindBuffer(GL_ARRAY_BUFFER, 0);
cutilSafeCall(cudaGraphicsGLRegisterBuffer(cuda_pixel_resource, *pixel_buffer, cudaGraphicsMapFlagsWriteDiscard));
}
else{
cutilSafeCall( cudaMalloc( (void **)&d_vbo_buffer, XDIM*YDIM*4*sizeof(float) ) );
}
}
void display() {
// Map buffer object for writing from CUDA
float4* pix_buff;
cudaGraphicsMapResources(1, &cuda_pbo_resource, 0);
size_t num_bytes;
cudaGraphicsResourceGetMappedPointer((void**)&pix_buff, &num_bytes, cuda_pbo_resource);
// Execute kernel
// will execute by calling kernel.cu file
if(pbo)
launch_kernel(dev_sum, dev_original, dev_frame, d_in, dev_k_resampledspacing, dc_subtracted, dev_resamp, pix_buff);
else launch_kernel(dev_sum, dev_original, dev_frame, d_in, dev_k_resampledspacing, dc_subtracted, dev_resamp, d_vbo_buffer);
// Unmap buffer object
cudaGraphicsUnmapResources(1, &cuda_pbo_resource, 0);
// copy to Open_gl texture
// Render from buffer object
glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
glBindBuffer(GL_ARRAY_BUFFER, pbo);
glVertexPointer(4, GL_FLOAT, 0, 0);
glEnableClientState(GL_VERTEX_ARRAY);
glDrawArrays(GL_POINTS, 0, XDIM * YDIM);
glDisableClientState(GL_VERTEX_ARRAY);
// Swap buffers
glutSwapBuffers();
glutPostRedisplay();
}
void deleteVBO() {
cudaGraphicsUnregisterResource(cuda_pbo_resource);
glDeleteBuffers(1, &pbo);
}
int main(int argc, char *argv[]) {
// Pre-Calculation
readData();
convertor(); //convert values into single float
calc_resample_coefficients();
//Cuda Memory Allocation
int frame = 0, sum =0;
cudaMalloc((void**)&dev_frame, sizeof(int));
cudaMalloc((void**)&dev_sum, sizeof(int));
cudaMalloc((void**)&dev_original, sizeof(float)*FRAMES*XDIM*YDIM);
cudaMalloc((void**)&d_in,sizeof(cuComplex)*YDIM*XDIM);
cudaMalloc((void**)&dev_resamp, sizeof(float)*LINE_LENGTH*2);
cudaMalloc((void**)&dev_k_resampledspacing, sizeof(float));
cudaMalloc((void**)&dc_subtracted, sizeof(float)*XDIM*YDIM);
cudaMemcpy(dev_k_resampledspacing, &k_resampledspacing, sizeof(float), cudaMemcpyHostToDevice);
cudaMemcpy(dev_resamp, resamp_1D, sizeof(float)*LINE_LENGTH*2, cudaMemcpyHostToDevice);
cudaMemcpy(dev_original, original_cpu, sizeof(float)*FRAMES*XDIM*YDIM, cudaMemcpyHostToDevice);
cudaMemcpy(dev_frame, &frame, sizeof(int), cudaMemcpyHostToDevice);
cudaMemcpy(dev_sum, &sum, sizeof(int), cudaMemcpyHostToDevice);
// Explicitly set device
cudaGLSetGLDevice(2);
glutInit(&argc, argv);
glutInitDisplayMode(GLUT_RGBA | GLUT_DOUBLE);
glutInitWindowSize(window_width, window_height);
glutCreateWindow("Cuda GL Interop (VBO)");
glutDisplayFunc(display);
glewInit();
CUcontext *pCtx = NULL;
cuInit(0);
cuCtxCreate(pCtx, CU_CTX_MAP_HOST, 0);
cuGLInit();
cuGLCtxCreate(pCtx, CU_CTX_MAP_HOST, 0);
// Create buffer object and register it with CUDA
createVBO(&pbo, &cuda_pbo_resource);
// Loop
glutMainLoop();
deleteVBO();
cudaThreadExit();
}
my code shoots me unspecified device error at
cutilSafeCall(cudaGraphicsGLRegisterBuffer(cuda_pixel_resource, *pixel_buffer, cudaGraphicsMapFlagsWriteDiscard));
of creatVBO function. Someone said to use other debugging tool rather than cutilSafeCall but I dont know what to use so Im confused with my
error messages. Can somebody help me with this? Thank you.
