Hi,
I wrote a very simple code for testing share resouces. My envorinment: i7-3770k win7 64-bit Intel OpenCL SDK 2013. The attached is my project. When OpenCL kernel ran on CPU device, the results are right. However, when it ran  on GPU device, the results are wrong. Anyone can help me explain this problem?

Thanks in advance.

By the way, when I wanted to debug the OpenCL source code, the debugger doesn't work. However, on the other PC it can work. I don't know why. Can Windows update  cause this issue. I also noticed that some one  met the same problem as well. http://redfort-software.intel.com/en-us/forums/showthread.php?t=101929

Sorry. I can not attach my project. So I posted the source code directly

Main.cpp

#define __CL_ENABLE_EXCEPTIONS

#define CL_USE_DEPRECATED_OPENCL_1_1_APIS

#include

#include

#include

#define DATASIZE 512

#define WORKSIZE 32

#define LOCALSIZE 16

//#define CPU

using namespace std;

int main()

{

vector platforms;

vector cpuDevices, gpuDevices, allDevices;

cl_uint minAlign ;

try {

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

cout << "Platform number: " << platforms.size() << endl;

cout << "Platform name: " << platforms[0].getInfo()<< endl << endl;

platforms[0].getDevices(CL_DEVICE_TYPE_CPU, &cpuDevices);

cout << "CPU device number: " << cpuDevices.size() << endl;

cout << "Device CPU name: " << cpuDevices[0].getInfo() << endl;

cout << "Compute Units: " << cpuDevices[0].getInfo() << endl;

cout << "Preferred Float Vector Width: " << cpuDevices[0].getInfo() << endl << endl;

platforms[0].getDevices(CL_DEVICE_TYPE_GPU, &gpuDevices);

cout << "GPU device number: " << gpuDevices.size() << endl;

cout << "Device GPU name: " << gpuDevices[0].getInfo() << endl;

cout << "Compute Units: " << gpuDevices[0].getInfo() << endl;

cout << "Preferred Float Vector Width: " << gpuDevices[0].getInfo() << endl << endl;

platforms[0].getDevices(CL_DEVICE_TYPE_ALL, &allDevices);

size_t time_resolution = cpuDevices[0].getInfo();

cout << "cpu device profiling resolution: " << time_resolution << endl;

time_resolution = gpuDevices[0].getInfo();

cout << "gpu device profiling resolution: " << time_resolution << endl;

minAlign = cpuDevices[0].getInfo();

cout << "CPU device memory align: " << minAlign << endl;

minAlign = gpuDevices[0].getInfo();

cout << "GPU device memory align: " << minAlign << endl;

cl_float* g_pfInput = (cl_float*) _aligned_malloc(DATASIZE * sizeof(cl_float), minAlign);

cl_float* g_pfOutput = (cl_float*) _aligned_malloc(DATASIZE * sizeof(cl_float), minAlign);

for(int i = 0; i < DATASIZE; i++)

{

g_pfInput[i] = i;

g_pfOutput[i] = -1;

}

#ifdef CPU

cl::Context context(cpuDevices);

#else

cl::Context context(gpuDevices);

#endif

std::ifstream programFile("oclWriteBuffer.cl");

std::string programString(std::istreambuf_iterator(programFile), (std::istreambuf_iterator()));

cl::Program::Sources source(1, std::make_pair(programString.c_str(), programString.length()+ 1));

cl::Program program(context, source);

try {

#ifdef CPU

program.build(cpuDevices,"-g -s \\"D:\\\\Nick\\OpenCL\\\\Tutorial1\\\\oclShareMemoryTest\\\\oclShareMemoryTest\\\\oclWriteBuffer.cl\\"");

#else

program.build(gpuDevices,"-g -s \\"D:\\\\Nick\\OpenCL\\\\Tutorial1\\\\oclShareMemoryTest\\\\oclShareMemoryTest\\\\oclWriteBuffer.cl\\"");

#endif

}

catch(cl::Error e)

{

cout << "WriteBuffer: Build Error" << endl;

cout << e.what() << ": Error code " << e.err() << endl << endl;

string log;

#ifdef CPU

log = program.getBuildInfo(cpuDevices[0]);

#else

log = program.getBuildInfo(gpuDevices[0]);

#endif

cout << log << endl << endl;

}

cl::Kernel writeKernel(program, "WriteBuffer");

cl::Buffer inputBuffer(context, CL_MEM_READ_ONLY | CL_MEM_USE_HOST_PTR, DATASIZE, g_pfInput);

cl::Buffer outputBuffer(context, CL_MEM_WRITE_ONLY | CL_MEM_USE_HOST_PTR, DATASIZE, g_pfOutput);

writeKernel.setArg(0, inputBuffer);

writeKernel.setArg(1, outputBuffer);

writeKernel.setArg(2, DATASIZE);

#ifdef CPU

cl::CommandQueue cmdQueue(context, cpuDevices[0]);

#else

cl::CommandQueue cmdQueue(context, gpuDevices[0]);

#endif

cmdQueue.enqueueNDRangeKernel(writeKernel, 0, WORKSIZE, LOCALSIZE);

cmdQueue.finish();

}

catch (cl::Error e) {

cout << e.what() << ": Error code " << e.err() << endl;

}

return 0;

}

oclWriteBuffer.cl file

// TODO: Add OpenCL kernel code here.

__kernel

void WriteBuffer(__global float* pfInput, __global float* pfOutput, int nLength)

{

size_t nOffset = get_global_size(0);

size_t nGID = get_global_id(0);

for (int i = 0; i < nLength / nOffset; i++)

{

pfOutput[i * nOffset + nGID] = pfInput[i * nOffset + nGID];

}

}