OpenCL 对循环大小的限制
OpenCL Limit on for loop size?
>更新:clEnqueueReadBuffer(command_queue, c_mem_obj, CL_TRUE, 0, LIST_SIZE * sizeof(double), C, 0, NULL, NULL);
返回 -5,CL_OUT_OF_RESOURCES
。此功能/调用永远不应该返回此函数!
我开始使用 OpenCL 并遇到了一个问题。如果我允许 for 循环(在内核中)运行 10000 次,如果我允许循环运行 8000 次,则所有 C 都是 0,结果都是正确的。
我在内核周围添加了等待以确保它完成,认为我在完成之前提取了数据,并尝试了 Clwaitforevent 和 CLFinish。任何调用都不会发出任何错误信号。当我使用 ints 时,for 循环将以 4000000 的大小工作。浮点数和双精度有同样的问题,但是浮点数在 10000 时工作,但在 20000 时不工作,当我使用浮点数时,我#pragma OPENCL EXTENSION cl_khr_fp64 : enable
删除以检查这不是问题。
这是不是一些奇怪的内存问题,我用错了 OpenCL?我意识到在大多数内核中,我都没有为这样的循环实现,但这似乎是一个问题。我还删除了__private
,看看这是否是问题所在,没有变化。那么 OpenCL 内核中 for 循环的大小是否有限制?硬件是否特定于?还是这是一个错误?
内核是一个简单的内核,它将 2 个数组 (A+B) 加在一起并输出另一个 (C)。为了感受性能,我在每个计算周围放置了一个 for 循环,以减慢/增加每次运行的操作数。
内核的代码如下:
#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];
}
}
我正在运行的代码如下:(当我在浮点数和双精度之间切换时,我确保两段代码之间的变量是一致的)
#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;
}
我在互联网上看了一下,找不到有类似问题的人,这是一个问题,因为它可能会导致代码在扩展之前运行良好......
我正在运行 Ubuntu 14.04,并且有一个用于 RC520 的笔记本电脑显卡,我用大黄蜂/optirun 运行。如果此错误在其他循环大小不超过 4000000 的机器上不可重现,那么我将使用 bumblebee/optirun 记录一个错误。
干杯
我发现了这个问题,连接到显示器/活动 VGA/等的 GPU 有一个看门狗计时器,在 ~5 秒后超时。非特斯拉的卡就是这种情况,它们具有此功能要关闭。在辅助卡上运行是一种解决方法。这很糟糕,需要尽快修复。这绝对是一个NVidia问题,不确定AMD,无论哪种方式,这都很糟糕。
解决方法是在Windows中更改注册表,在Linux/Ubuntu中更改X conf并放置:
选项"交互式"0"
但是,在与显卡的差距中,X conf 现在不会在更高版本中生成,可能需要手动创建。如果有人对此有复制和粘贴控制台代码修复程序,那将是很好且更好的答案。
- 如何循环打印顶点结构
- 如何在C++中从两个单独的for循环中添加两个数组
- C++我的数学有什么问题,为什么我的代码不能正确循环
- 正在尝试了解输入验证循环
- 使用std::vector的OpenCL矩阵乘法
- std::map<struct,struct>::find 找不到匹配项,但是如果我循环通过 begin() 到 end(),我在那里看到匹配项
- 循环后如何继续阅读
- Ardunio UNO解决了多个重叠的定时器循环
- Eigen如何在容器循环中干净地附加矩阵
- OpenCL仅在循环呼叫时停止运行
- 为什么 OpenCL 嵌套循环仅适用于某些元素
- 如何准确测量和比较opencl速度以实现循环功能的简单速度
- OpenCL:循环内核
- 奇怪的OpenCL调用C++上的副作用来提高循环性能
- OpenCL-循环的矢量化与线程内
- 2d循环OpenCl程序不工作
- OpenCL 对循环大小的限制
- OpenCL实现的算法比正常循环慢
- OpenCL: for循环中的CL_OUT_OF_RESOURCES
- 使用OpenCL在2D中嵌套循环求和