OpenCL program uses only 1 core from 192 cuda cores
-
I made following program to use opencl library supplied with Nvidia cuda 7.5. As result I obtained: Num of devices=1 Device name= quadro K600 Device vendor=NVIDIA Corporation Device Version=OPENCL 1.2 CUDA Driver Version= 353.90 DEVICE_MAX_COMPUTE_UNITS = 1 !!!!!!!!!!!!!!!!!!!!!!!!!! DEVICE_MAX_CLOCK_FREQUENCY = 875 MHZ DEVICE_GLOBAL_MEM_SIZE= 1073741824 Only 1 compute unit at 875 Mhz???? I read that K600 has 192
#include
#define __CL_ENABLE_EXCEPTIONS
#pragma warning(disable:4996)
#include
#include
#include
#include
#include#define LOCAL_SIZE 512
#define WIDTH_A (4096*2)
#define HEIGHT_A (4096*2)float *matrix_A;
float *vector_B;
float *result_vector;
float *result_vector_host;#define MAX_SOURCE_SIZE (0x100000)
int main()
{
cl_platform_id platform_id = NULL;
cl_device_id device_id = NULL;
cl_context context = NULL;
cl_command_queue command_queue = NULL;
cl_mem Amobj = NULL;
cl_mem Bmobj = NULL;
cl_mem Cmobj = NULL;
cl_program program = NULL;
cl_kernel kernel = NULL;
cl_uint ret_num_devices;
cl_uint ret_num_platforms;
cl_int ret;int i, j; /\* Get Platform/Device Information\*/ ret = clGetPlatformIDs(1, &platform\_id, &ret\_num\_platforms); ret = clGetDeviceIDs(platform\_id, CL\_DEVICE\_TYPE\_DEFAULT, 1, &device\_id, &ret\_num\_devices); /\* Create OpenCL Context \*/ context = clCreateContext(NULL, 1, &device\_id, NULL, NULL, &ret); char buffer\[10240\]; cl\_uint buf\_uint; cl\_ulong buf\_ulong; printf("Num of devices=%i", ret\_num\_devices); for (i = 0; i < ret\_num\_devices; i++) { printf(" -- %d --\\n", i); clGetDeviceInfo(device\_id, CL\_DEVICE\_NAME, sizeof(buffer), buffer, NULL); printf(" DEVICE\_NAME = %s\\n", buffer); clGetDeviceInfo(device\_id, CL\_DEVICE\_VENDOR, sizeof(buffer), buffer, NULL); printf(" DEVICE\_VENDOR = %s\\n", buffer); clGetDeviceInfo(device\_id, CL\_DEVICE\_VERSION, sizeof(buffer), buffer, NULL); printf(" DEVICE\_VERSION = %s\\n", buffer); clGetDeviceInfo(device\_id, CL\_DRIVER\_VERSION, sizeof(buffer), buffer, NULL); printf(" DRIVER\_VERSION = %s\\n", buffer); clGetDeviceInfo(device\_id, CL\_DEVICE\_MAX\_COMPUTE\_UNITS, sizeof(buf\_uint), &buf\_uint, NULL); printf(" DEVICE\_MAX\_COMPUTE\_UNITS = %u\\n", (unsigned int)buf\_uint); clGetDeviceInfo(device\_id, CL\_DEVICE\_MAX\_CLOCK\_FREQUENCY, sizeof(buf\_uint), &buf\_uint, NULL); printf(" DEVICE\_MAX\_CLOCK\_FREQUENCY = %u\\n", (unsigned int)buf\_uint); clGetDeviceIn -
I made following program to use opencl library supplied with Nvidia cuda 7.5. As result I obtained: Num of devices=1 Device name= quadro K600 Device vendor=NVIDIA Corporation Device Version=OPENCL 1.2 CUDA Driver Version= 353.90 DEVICE_MAX_COMPUTE_UNITS = 1 !!!!!!!!!!!!!!!!!!!!!!!!!! DEVICE_MAX_CLOCK_FREQUENCY = 875 MHZ DEVICE_GLOBAL_MEM_SIZE= 1073741824 Only 1 compute unit at 875 Mhz???? I read that K600 has 192
#include
#define __CL_ENABLE_EXCEPTIONS
#pragma warning(disable:4996)
#include
#include
#include
#include
#include#define LOCAL_SIZE 512
#define WIDTH_A (4096*2)
#define HEIGHT_A (4096*2)float *matrix_A;
float *vector_B;
float *result_vector;
float *result_vector_host;#define MAX_SOURCE_SIZE (0x100000)
int main()
{
cl_platform_id platform_id = NULL;
cl_device_id device_id = NULL;
cl_context context = NULL;
cl_command_queue command_queue = NULL;
cl_mem Amobj = NULL;
cl_mem Bmobj = NULL;
cl_mem Cmobj = NULL;
cl_program program = NULL;
cl_kernel kernel = NULL;
cl_uint ret_num_devices;
cl_uint ret_num_platforms;
cl_int ret;int i, j; /\* Get Platform/Device Information\*/ ret = clGetPlatformIDs(1, &platform\_id, &ret\_num\_platforms); ret = clGetDeviceIDs(platform\_id, CL\_DEVICE\_TYPE\_DEFAULT, 1, &device\_id, &ret\_num\_devices); /\* Create OpenCL Context \*/ context = clCreateContext(NULL, 1, &device\_id, NULL, NULL, &ret); char buffer\[10240\]; cl\_uint buf\_uint; cl\_ulong buf\_ulong; printf("Num of devices=%i", ret\_num\_devices); for (i = 0; i < ret\_num\_devices; i++) { printf(" -- %d --\\n", i); clGetDeviceInfo(device\_id, CL\_DEVICE\_NAME, sizeof(buffer), buffer, NULL); printf(" DEVICE\_NAME = %s\\n", buffer); clGetDeviceInfo(device\_id, CL\_DEVICE\_VENDOR, sizeof(buffer), buffer, NULL); printf(" DEVICE\_VENDOR = %s\\n", buffer); clGetDeviceInfo(device\_id, CL\_DEVICE\_VERSION, sizeof(buffer), buffer, NULL); printf(" DEVICE\_VERSION = %s\\n", buffer); clGetDeviceInfo(device\_id, CL\_DRIVER\_VERSION, sizeof(buffer), buffer, NULL); printf(" DRIVER\_VERSION = %s\\n", buffer); clGetDeviceInfo(device\_id, CL\_DEVICE\_MAX\_COMPUTE\_UNITS, sizeof(buf\_uint), &buf\_uint, NULL); printf(" DEVICE\_MAX\_COMPUTE\_UNITS = %u\\n", (unsigned int)buf\_uint); clGetDeviceInfo(device\_id, CL\_DEVICE\_MAX\_CLOCK\_FREQUENCY, sizeof(buf\_uint), &buf\_uint, NULL); printf(" DEVICE\_MAX\_CLOCK\_FREQUENCY = %u\\n", (unsigned int)buf\_uint); clGetDeviceInHow is this:
printf(" DEVICE_MAX_CLOCK_FREQUENCY = %u\n", (unsigned int)buf_uint);printing this: DEVICE_MAX_CLOCK_FREQUENCY = 875 MHZ Perhaps the code you are using and the code you pasted are not the same? Have you tried asking your question here?"One man's wage rise is another man's price increase." - Harold Wilson
"Fireproof doesn't mean the fire will never come. It means when the fire comes that you will be able to withstand it." - Michael Simmons
"You can easily judge the character of a man by how he treats those who can do nothing for him." - James D. Miles
-
How is this:
printf(" DEVICE_MAX_CLOCK_FREQUENCY = %u\n", (unsigned int)buf_uint);printing this: DEVICE_MAX_CLOCK_FREQUENCY = 875 MHZ Perhaps the code you are using and the code you pasted are not the same? Have you tried asking your question here?"One man's wage rise is another man's price increase." - Harold Wilson
"Fireproof doesn't mean the fire will never come. It means when the fire comes that you will be able to withstand it." - Michael Simmons
"You can easily judge the character of a man by how he treats those who can do nothing for him." - James D. Miles
I edited it after reading to make it more easy to understand. I have seen that the old video card is not very good improving the performance of the CPU.