Resource Type

Journal Article 1

Year

2015 1

Keywords

Analysis-based transformation 1

Multi-core/many-core CPU 1

OpenCL 1

Performance portability 1

Search scope:

排序： Display mode:

Improving performance portability for GPU-specific OpenCL kernels onmulti-core/many-coreCPUs by analysis-based

Mei WEN,Da-fei HUANG,Chang-qing XUN,Dong CHEN

Frontiers of Information Technology & Electronic Engineering 2015, Volume 16, Issue 11,   Pages 899-916 doi: 10.1631/FITEE.1500032

Abstract: OpenCL is an open heterogeneous programming framework.Although OpenCL programs are functionally portable, they do not provide performance portability, so codeWhen adapting GPU-specific OpenCL kernels to run on multi-core/many-core CPUs, coarsening the threadHowever, locality concerns exposed in GPU-specific OpenCL code are usually inherited without analysiskernels into a CPU-friendly form, which is accompanied with a scheduler that forms a new OpenCL runtime

Keywords： OpenCL     Performance portability     Multi-core/many-core CPU     Analysis-based transformation    

HTML PDF Collect

Title Author Date Type Operation

Improving performance portability for GPU-specific OpenCL kernels onmulti-core/many-coreCPUs by analysis-based

Mei WEN,Da-fei HUANG,Chang-qing XUN,Dong CHEN

Journal Article