Char not accepting numeric value

Accelerated Computing CUDA CUDA Programming and Performance
1

I am having a problem I just can’t figure out. In my kernel I want to use a char array to hold numeric values but am unable to do so, when I read back the char array on the host side it has no values in it. I have a simple test kernel that tries to fill the output char array with the char values 1 through 10 as an example of my problem and have tested it on Apples OpenCL implementation as well as NVIDIA’s. I have checked for error messages and OpenCL returns none. If I make the output array of type int it works correctly. Any idea what’s wrong?

This code uses the Khronos C++ bindings:

kernel.cl

[codebox]#pragma OPENCL EXTENSION cl_khr_byte_addressable_store : enable

__constant char charArray = {1,2,3,4,5,6,7,8,9,10};

__kernel void testKernel(__global char * out)

{

size_t tid = get_global_id(0);

out[tid] = charArray[tid];

}[/codebox]

main.cpp

[codebox]#include

#include

#include “cl.hpp”

int main(void)

{

cl_int err = CL_SUCCESS;

cl::Context context(CL_DEVICE_TYPE_GPU, 0, NULL, NULL, &err);

std::vectorcl::Device devices = context.getInfo<CL_CONTEXT_DEVICES>();

char * outH = new char[10];

cl::Buffer outCL(context,CL_MEM_WRITE_ONLY| CL_MEM_USE_HOST_PTR,sizeof(cl_char)*10,outH,

               &err);

std::ifstream file(“kernel.cl”);

std::string prog(std::istreambuf_iterator(file),(std::istreambuf_iterator()));

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

cl::Program program(context, source);

program.build(devices,“”);

cl::Kernel kernel(program, “testKernel”, &err);

kernel.setArg(0, outCL);

cl::CommandQueue queue(context, devices[0], 0, &err);

cl::Event event;

queue.enqueueNDRangeKernel(kernel,

                       cl::NullRange,

                       cl::NDRange(10),

                       cl::NDRange(1, 1), 

                       NULL, 

                       &event);

event.wait();

queue.enqueueReadBuffer(outCL,CL_TRUE,0,sizeof(cl_char)*10,o

utH);

for (int i=0; i<10; i++) {

  std::cout<<outH[i]<<std::endl;

}

return 0;

}[/codebox]

2

Try this

__constant char charArray[] = {'1','2','3','4','5','6','7','8','9','10'};
3

On NVIDIA and Apple implementations the result is that all ten elements of the output array have value ‘1’, and produces the following warning on the Apple implementation:

:3:68: warning: multi-character character constant [-Wmultichar]

__constant char charArray = {‘1’,‘2’,‘3’,‘4’,‘5’,‘6’,‘7’,‘8’,‘9’,‘10’};

4

‘10’ is not a char, it’s a string of two chars :)

5

Sorry, I think I was making a boneheaded mistake in that I believe it is necessary to cast to an int before I print out the array values. cout<<(int)charArray[1]; where as cout<<charArray[1]; tries to print out an ascii character and not the integer value.