1
更新：clEnqueueReadBuffer(command_queue, c_mem_obj, CL_TRUE, 0, LIST_SIZE * sizeof(double), C, 0, NULL, NULL);正在返回-5,CL_OUT_OF_RESOURCES。這個功能/調用不應該返回這個！OpenCL限制循環大小？
我已經開始使用OpenCL並遇到了問題。如果我允許一個for循環（在內核中）運行10000次，如果我允許循環運行8000次，則所有C都爲0，結果都是正確的。
我已經添加了圍繞內核的等待以確保它完成，認爲我在完成前拉出數據並嘗試了Clwaitforevent和CLFinish。任何通話都不會發出錯誤信號。當我使用ints for循環將工作在4000000的大小。浮動和雙打有同樣的問題，但浮動工作在10000，但不是在20000，當我使用浮動我刪除#pragma OPENCL EXTENSION cl_khr_fp64 : enable檢查是不是問題。
這是一些奇怪的記憶事情，我使用OpenCL錯了嗎？我意識到在大多數內核中，我沒有爲這樣的循環實現，但這似乎是一個問題。我也刪除__private，看看這是不是問題，沒有改變。那麼OpenCL內核中for循環的大小是否有限制？具體是硬件嗎？或者這是一個錯誤？內核是一個簡單的內核，它將兩個數組（A + B）加在一起並輸出另一個（C）。爲了獲得性能感覺，我在每次計算中都放了一個for循環來減慢/增加每次運行的操作次數。
爲內核的代碼如下：
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
__kernel void vector_add(__global double *A, __global double *B, __global double *C)
{
// Get the index of the current element
int i = get_global_id(0);
// Do the operation
for (__private unsigned int j = 0; j < 10000; j++)
{
C[i] = A[i] + B[i];
}
}
我跑的代碼如下：（我保證，當我float和double之間切換的變量的代碼兩片之間保持一致）
#include <stdio.h>
#include <stdlib.h>
#include <iostream>
#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 = 4000000;
double *A = (double*)malloc(sizeof(double)*LIST_SIZE);
double *B = (double*)malloc(sizeof(double)*LIST_SIZE);
for(i = 0; i < LIST_SIZE; i++) {
A[i] = static_cast<double>(i);
B[i] = static_cast<double>(LIST_SIZE - i);
}
// Load the kernel source code into the array source_str
FILE *fp;
char *source_str;
size_t source_size;
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;
// clGetPlatformIDs(1, &platform_id, NULL);
//clGetDeviceIDs(platform_id, CL_DEVICE_TYPE_GPU, 1, &device_id, ret_num_devices);
cl_int ret = clGetPlatformIDs(1, &platform_id, NULL);
if (ret != CL_SUCCESS) {
printf("Error: Failed to get platforms! (%d) \n", ret);
return EXIT_FAILURE;
}
ret = clGetDeviceIDs(platform_id, CL_DEVICE_TYPE_GPU, 1, &device_id, &ret_num_devices);
if (ret != CL_SUCCESS) {
printf("Error: Failed to query platforms to get devices! (%d) \n", ret);
return EXIT_FAILURE;
}
/*
cl_int ret = clGetPlatformIDs(1, &platform_id, NULL);
if (ret != CL_SUCCESS) {
printf("Error: Failed to get platforms! (%d) \n", ret);
return EXIT_FAILURE;
}
ret = clGetDeviceIDs(platform_id, CL_DEVICE_TYPE_CPU, 1,
&device_id, &ret_num_devices);
if (ret != CL_SUCCESS) {
printf("Error: Failed to query platforms to get devices! (%d) \n", ret);
return EXIT_FAILURE;
}
*/
// 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(double), NULL, &ret);
cl_mem b_mem_obj = clCreateBuffer(context, CL_MEM_READ_ONLY,
LIST_SIZE * sizeof(double), NULL, &ret);
cl_mem c_mem_obj = clCreateBuffer(context, CL_MEM_WRITE_ONLY,
LIST_SIZE * sizeof(double), NULL, &ret);
if (ret != CL_SUCCESS) {
printf("Error: Buffer Fail! (%d) \n", ret);
return EXIT_FAILURE;
}
// Copy the lists A and B to their respective memory buffers
ret = clEnqueueWriteBuffer(command_queue, a_mem_obj, CL_TRUE, 0,
LIST_SIZE * sizeof(double), A, 0, NULL, NULL);
ret = clEnqueueWriteBuffer(command_queue, b_mem_obj, CL_TRUE, 0,
LIST_SIZE * sizeof(double), B, 0, NULL, NULL);
std::cout << "Begin Compile" << "\n";
// Create a program from the kernel source
cl_program program = clCreateProgramWithSource(context, 1,
(const char **)&source_str, (const size_t *)&source_size, &ret);
if (ret != CL_SUCCESS) {
printf("Error: Program Fail! (%d) \n", ret);
return EXIT_FAILURE;
}
// Build the program
ret = clBuildProgram(program, 1, &device_id, NULL, NULL, NULL);
if (ret != CL_SUCCESS) {
printf("Error: ProgramBuild Fail! (%d) \n", ret);
return EXIT_FAILURE;
}
// Create the OpenCL kernel
cl_kernel kernel = clCreateKernel(program, "vector_add", &ret);
if (ret != CL_SUCCESS) {
printf("Error: Kernel Build Fail! (%d) \n", ret);
return EXIT_FAILURE;
}
std::cout << "End Compile" << "\n";
std::cout << "Begin Data Move" << "\n";
// 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);
std::cout << "End Data Move" << "\n";
// Execute the OpenCL kernel on the list
size_t global_item_size = LIST_SIZE; // Process the entire lists
size_t local_item_size = 64; // Process in groups of 64
std::cout << "Begin Execute" << "\n";
cl_event event;
ret = clEnqueueNDRangeKernel(command_queue, kernel, 1, NULL,
&global_item_size, &local_item_size, 0, NULL, &event);
clFinish(command_queue);
//clWaitForEvents(1, &event);
std::cout << "End Execute" << "\n";
if (ret != CL_SUCCESS) {
printf("Error: Execute Fail! (%d) \n", ret);
return EXIT_FAILURE;
}
// Read the memory buffer C on the device to the local variable C
std::cout << "Begin Data Move" << "\n";
double *C = (double*)malloc(sizeof(double)*LIST_SIZE);
ret = clEnqueueReadBuffer(command_queue, c_mem_obj, CL_TRUE, 0,
LIST_SIZE * sizeof(double), C, 0, NULL, NULL);
if (ret != CL_SUCCESS) {
printf("Error: Read Fail! (%d) \n", ret);
return EXIT_FAILURE;
}
clFinish(command_queue);
std::cout << "End Data Move" << "\n";
std::cout << "Done" << "\n";
std::cin.get();
// Display the result to the screen
for(i = 0; i < LIST_SIZE; i++)
printf("%f + %f = %f \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);
std::cout << "Number of Devices: " << ret_num_devices << "\n";
std::cin.get();
return 0;
}
我已經在互聯網上一看，並不能找到有類似問題的人來說，這是一個問題，因爲它可能會導致該直到擴大行之有效代碼...
我正在運行Ubuntu 14.04，並且有一臺筆記本電腦顯卡，用於與大黃蜂/ optirun一起運行的RC520。如果這個錯誤在其他機器上無法重現，最大4000000的循環大小，那麼我將記錄一個bug，使用bumblebee/optirun。
乾杯
C++ or C？如果你不確定：除了最後的'cout'（並且用'printf'替換它們不會改變一件事物），它看起來像純C一樣可疑。 – usr2564301
@Jongware它是C++的，因爲cout，但是，它並不重要？正如我在帖子中提到的，我只關心內核在某些情況下無法正常工作。只要c/C++代碼沒有使用OpenCL api錯誤，它可能是python中我所關心的。 – Thorrex
'沒有任何錯誤通過任何調用發出.'您發佈的代碼實際上並不檢查OpenCL調用的所有結果。這是你測試的代碼嗎？ –