Sunday 1 January 2017

Exploring the Contrast on GPGPU Computing through CUDA and OpenCL

Vol. 9  Issue 1
Year:2014
Issue:Jul-Sep
Title:Exploring the Contrast on GPGPU Computing through CUDA and OpenCL
Author Name:Bala Dhandayuthapani Veerasamy and Nasira G.M
Synopsis:
In the recent years, Multi-core to Many-core processors computing became most significant in High Performance Computing (HPC). Increasing parallelism rather than increasing clock rate has become the primary engine of processor performance growth and this trend is likely to continue. Particularly, today's Graphics Processing Units (GPU) became most significant in favour of HPC. General Purpose GPU (GPGPU) computing has allowed the GPU to emerge as successful co-processors that can be employed to improve the performance of many different non-graphical applications with high parallel requirements that make them suitable for many HPC workloads. CUDA and OpenCL offer two different interfaces for programming GPUs. OpenCL is an open standard that can be used to program CPUs, GPUs, and other devices from different vendors, while CUDA is specific to NVIDIA GPUs. In this research paper, the authors have explored the contrast between CUDA and OpenCL, which helps the HPC programmers to familiarize with GPGPU.

No comments:

Post a Comment