gpu opencl 向量加_OpenCL，简单的向量加法但输出错误，输入大

因此，花了几个小时的阅读和理解之后，我终于做出了我的第一个OpenCL程序，它实际上做了一些事情，这是它向文件添加了两个向量和输出。

#include

#include

#include

#include

#include

#define __CL_ENABLE_EXCEPTIONS

#include

int main(int argc, char *argv[])

{

try

{

// get platforms, devices and display their info.

std::vector<:platform> platforms;

cl::Platform::get(&platforms);

std::vector<:platform>::iterator i=platforms.begin();

std::cout<getInfo()<<:endl>

std::cout<getInfo()<<:endl>

std::cout<getInfo()<<:endl>

std::cout<getInfo()<<:endl>

// get devices

std::vector<:device> devices;

i->getDevices(CL_DEVICE_TYPE_ALL,&devices);

int o=99;

std::cout<

// iterate over available devices

for(std::vector<:device>::iterator j=devices.begin(); j!=devices.end(); j++)

{

std::cout<getInfo()<<:endl>

std::cout<getInfo()<<:endl>

std::cout<getInfo()<<:endl>

std::cout<getInfo()<<:endl>

std::cout<getInfo()/(1024*1024)<

std::cout<getInfo()/1024<

std::cout<getInfo()<<:endl>

std::cout<getInfo()<

}

std::cout<

//MAIN CODE BEGINS HERE

//get Kernel

std::ifstream ifs("vector_add_kernel.cl");

std::string kernelSource((std::istreambuf_iterator(ifs)), std::istreambuf_iterator());

std::cout<

//Create context, select device and command queue.

cl::Context context(devices);

cl::Device &device=devices.front();

cl::CommandQueue cmdqueue(context,device);

// Generate Source vector and push the kernel source in it.

cl::Program::Sources sourceCode;

sourceCode.push_back(std::make_pair(kernelSource.c_str(), kernelSource.size()));

//Generate program using sourceCode

cl::Program program=cl::Program(context, sourceCode);

//Build program..

try

{

program.build(devices);

}

catch(cl::Error &err)

{

std::cerr<

<

<

<(devices.front());

}

//Declare and initialize vectors

std::vectorB(993448,1.3);

std::vectorC(993448,1.3);

std::vectorA(993448,1.3);

cl_int N=A.size();

//Declare and intialize proper work group size and global size. Global size raised to the nearest multiple of workGroupSize.

int workGroupSize=128;

int GlobalSize;

if(N%workGroupSize) GlobalSize=N - N%workGroupSize + workGroupSize;

else GlobalSize=N;

//Declare buffers.

cl::Buffer vecA(context, CL_MEM_READ_WRITE, sizeof(cl_float)*N);

cl::Buffer vecB(context, CL_MEM_READ_ONLY , (B.size())*sizeof(cl_float));

cl::Buffer vecC(context, CL_MEM_READ_ONLY , (C.size())*sizeof(cl_float));

//Write vectors into buffers

cmdqueue.enqueueWriteBuffer(vecB, 0, 0, (B.size())*sizeof(cl_float), &B[0] );

cmdqueue.enqueueWriteBuffer(vecB, 0, 0, (C.size())*sizeof(cl_float), &C[0] );

//Executing kernel

cl::Kernel kernel(program, "vector_add");

cl::KernelFunctor kernel_func=kernel.bind(cmdqueue, cl::NDRange(GlobalSize), cl::NDRange(workGroupSize));

kernel_func(vecA, vecB, vecC, N);

//Reading back values into vector A

cmdqueue.enqueueReadBuffer(vecA,true,0,N*sizeof(cl_float), &A[0]);

cmdqueue.finish();

//Saving into file.

std::ofstream output("vectorAdd.txt");

for(int i=0;i

}

catch(cl::Error& err)

{

std::cerr << "OpenCL error: " << err.what() << "(" << err.err() <<

")" << std::endl;

return EXIT_FAILURE;

}

return EXIT_SUCCESS;

}问题是，对于较小的N值，我得到的正确结果是2.6

但对于较大的值，如上面代码(993448)中的那样，我得到的垃圾输出在1到2.4之间变化。

这是内核代码：

__kernel void vector_add(__global float *A, __global float *B, __global float *C, int N) {

// Get the index of the current element

int i = get_global_id(0);

//Do the operation

if(i

}更新：好吧，看来代码现在正在工作。我在上面的代码中修复了一些小错误

1)GlobalSize初始化的部分已被修复。

2)enqueueWriteBuffer中的错误(给出了错误的参数)

现在它正在输出正确的结果，N值很大。