Research Article
OpenCL Performance Evaluation on Modern Multicore CPUs
Algorithm 2
Code snippet of simple application.
/*First Kernel: Vector Addition.*/ | #pragma omp parallel for shared(, , ) private () | for (int ; < MAX_INDEX; ++){ | = + ; | | /*(a) Aligned Second Kernel: Vector Multiplication.*/ | #pragma omp parallel for shared(, , ) private () | for (int ; < MAX_INDEX; ++){ | = + ; | | /*(b) Misaligned Second Kernel: Vector Multiplication.*/ | #pragma omp parallel for shared(, , ) private () | for (int ; < MAX_INDEX; ++){ | int = ; | = + ; | |
|