Problems additionVector with OpenCL - opencl

Question

I want to learn OpenCL so i read a tutorial with a simple vector addition https://www.eriksmistad.no/getting-started-with-opencl-and-gpu-computing/
Im working with ubuntu
Distributor ID: Ubuntu
Description: Ubuntu 22.04.1 LTS
Release: 22.04
Codename: jammy
And i have a RTX 3080Ti known by my computer
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 525.85.05 Driver Version: 525.85.05 CUDA Version: 12.0 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA GeForce ... Off | 00000000:02:00.0 On | N/A |
| 0% 54C P8 38W / 350W | 634MiB / 12288MiB | 2% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 1766 G /usr/lib/xorg/Xorg 312MiB |
| 0 N/A N/A 2087 G /usr/bin/gnome-shell 105MiB |
| 0 N/A N/A 3343 G ...5/usr/lib/firefox/firefox 183MiB |
+-----------------------------------------------------------------------------+
give by an nvidia-smi
I installed OpenCL with apt-get install opencl-headers and cuda for OpenCL drivers.
Here is the code :
#include <stdio.h>
#include <stdlib.h>
#ifdef __APPLE__
#include <OpenCL/opencl.h>
#else
#include <CL/cl.h>
#endif
#define MAX_SOURCE_SIZE (0x100000)
int main(void) {
// Create the two input vectors
int i;
const int LIST_SIZE = 10;
int *A = (int*)malloc(sizeof(int)*LIST_SIZE);
int *B = (int*)malloc(sizeof(int)*LIST_SIZE);
for(i = 0; i < LIST_SIZE; i++) {
A[i] = i;
B[i] = i;
}
// Load the kernel source code into the array source_str
FILE *fp;
char *source_str;
size_t source_size;
char str_buffer[1024];
fp = fopen("vector_add_kernel.cl", "r");
if (!fp) {
fprintf(stderr, "Failed to load kernel.\n");
exit(1);
}
source_str = (char*)malloc(MAX_SOURCE_SIZE);
source_size = fread( source_str, 1, MAX_SOURCE_SIZE, fp);
fclose( fp );
// Get platform and device information
cl_platform_id platform_id = NULL;
cl_device_id device_id = NULL;
cl_uint ret_num_devices;
cl_uint ret_num_platforms;
cl_int ret = clGetPlatformIDs(1, &platform_id, &ret_num_platforms);
ret = clGetDeviceIDs( platform_id, CL_DEVICE_TYPE_GPU, 1,
&device_id, &ret_num_devices);
// Create an OpenCL context
cl_context context = clCreateContext( NULL, 1, &device_id, NULL, NULL, &ret);
// Create a command queue
cl_command_queue command_queue = clCreateCommandQueue(context, device_id, 0, &ret);
// Create memory buffers on the device for each vector
cl_mem a_mem_obj = clCreateBuffer(context, CL_MEM_READ_ONLY,
LIST_SIZE * sizeof(int), NULL, &ret);
cl_mem b_mem_obj = clCreateBuffer(context, CL_MEM_READ_ONLY,
LIST_SIZE * sizeof(int), NULL, &ret);
cl_mem c_mem_obj = clCreateBuffer(context, CL_MEM_WRITE_ONLY,
LIST_SIZE * sizeof(int), NULL, &ret);
// Copy the lists A and B to their respective memory buffers
ret = clEnqueueWriteBuffer(command_queue, a_mem_obj, CL_TRUE, 0,
LIST_SIZE * sizeof(int), A, 0, NULL, NULL);
ret = clEnqueueWriteBuffer(command_queue, b_mem_obj, CL_TRUE, 0,
LIST_SIZE * sizeof(int), B, 0, NULL, NULL);
// Create a program from the kernel source
cl_program program = clCreateProgramWithSource(context, 1,
(const char **)&source_str, (const size_t *)&source_size, &ret);
// Build the program
ret = clBuildProgram(program, 1, &device_id, NULL, NULL, NULL);
// Create the OpenCL kernel
cl_kernel kernel = clCreateKernel(program, "vector_add", &ret);
// Set the arguments of the kernel
ret = clSetKernelArg(kernel, 0, sizeof(cl_mem), (void *)&a_mem_obj);
ret = clSetKernelArg(kernel, 1, sizeof(cl_mem), (void *)&b_mem_obj);
ret = clSetKernelArg(kernel, 2, sizeof(cl_mem), (void *)&c_mem_obj);
// Execute the OpenCL kernel on the list
size_t global_item_size = LIST_SIZE; // Process the entire lists
size_t local_item_size = 64; // Divide work items into groups of 64
ret = clEnqueueNDRangeKernel(command_queue, kernel, 1, NULL,
&global_item_size, &local_item_size, 0, NULL, NULL);
// Read the memory buffer C on the device to the local variable C
int *C = (int*)malloc(sizeof(int)*LIST_SIZE);
ret = clEnqueueReadBuffer(command_queue, c_mem_obj, CL_TRUE, 0,
LIST_SIZE * sizeof(int), C, 0, NULL, NULL);
// Display the result to the screen
for(i = 0; i < LIST_SIZE; i++)
printf("%d + %d = %d\n", A[i], B[i], C[i]);
// Clean up
ret = clFlush(command_queue);
ret = clFinish(command_queue);
ret = clReleaseKernel(kernel);
ret = clReleaseProgram(program);
ret = clReleaseMemObject(a_mem_obj);
ret = clReleaseMemObject(b_mem_obj);
ret = clReleaseMemObject(c_mem_obj);
ret = clReleaseCommandQueue(command_queue);
ret = clReleaseContext(context);
free(A);
free(B);
free(C);
return 0;
}
And the code of the kernel :
__kernel void vector_add(__global const int *A, __global const int *B, __global int *C) {
// Get the index of the current element to be processed
int i = get_global_id(0);
// Do the operation
C[i] = A[i] + B[i];
}
I compile with : gcc main.c -o vectorAddition -l OpenCL
And the execution of vectorAddition give me this :
platform name : NVIDIA CUDA
platform vendor : NVIDIA Corporation
Device name : NVIDIA Corporation
0 + 0 = 0
1 + 1 = 0
2 + 2 = 0
3 + 3 = 0
4 + 4 = 0
5 + 5 = 0
6 + 6 = 0
7 + 7 = 0
8 + 8 = 0
9 + 9 = 0
Thanks
I already read a post which is pretty the same than mine :
https://stackoverflow.com/questions/54606449/opencl-vector-addition-program
But i think my clCreateBuffer are good
I put these lines in my code to be sure my gpu is know :
//Get the name of the platform and device
ret = clGetPlatformInfo(0, CL_PLATFORM_NAME, sizeof(str_buffer), &str_buffer, NULL);
printf("platform name : %s\n",str_buffer);
ret = clGetPlatformInfo(0, CL_PLATFORM_VENDOR, sizeof(str_buffer), &str_buffer, NULL);
printf("platform vendor : %s\n",str_buffer);
ret = clGetDeviceInfo(0, CL_DEVICE_NAME, sizeof(str_buffer), &str_buffer, NULL);
printf("Device name : %s\n",str_buffer);
``

Answer 1

If anyone have the same issue i found out the solution. The problem is that the man who wrote the tutorial made work-groups with these lines :
size_t global_item_size = LIST_SIZE; // Process the entire lists
size_t local_item_size = 64; // Divide work items into groups of 64
ret = clEnqueueNDRangeKernel(command_queue, kernel, 1, NULL,&global_item_size, &local_item_size, 0, NULL, NULL);
You can have an unknown behavior if the local_item_size is not a multiple of list_size
So you can send a NULL argument instead of &local_item_size or chose 64,128,... for LIST_SIZE.