Using OpenCL: Programming Massively Parallel Computers

allocated array block buffer object calculation char cl_context cl_context_properties cl_device_id cl_event cl_float cl_int cl_mem CL_MEM_COPY_HOST_PTR cl::Buffer cl::Kernel cl::NullRange cl::Program command queue compilation const int created CUDA data parallel defined dim3 enqueue error example extensions genetic algorithm get_global_id(0 global float global memory hardware header files host code host memory host program initialization iteration kernel execution kernel object kernel void Linux list of available matrix matrix multiplication memory access memory buffer memory pools method MinGW multiple NDRange NULL NVIDIA NVIDIA Corporation OpenCL application OpenCL context OpenCL device OpenCL implementation OpenCL platform OpenCL program OpenCL standard OpenMP operation parallel computing parameter performance pointer prefix sum printf processors profiling programming language random seed SAXPY seen in listing shown in listing size_t sizeof(cl_float source code specimen std::cout std::endl stored synchronization texture threads tion uint variable vector work-group work-item