Auto-Tuning OmpSs-OpenCL Kernels Across GPU Machines

Elangovan, Vinoth Krishnan; Badía, Rosa M.; Ayguadé, Eduard

doi:10.1145/2701310.2701316

Cited by 3 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are some research works on performance portability and/or automatic parameter tuning of OpenCL kernels (Nugteren and Codreanu, 2015; Bajrovic et al , 2016; Fabeiro et al , 2015; Elangovan et al , 2015). These works differ from ours, in that they use more sophisticated techniques to search for optimal parameters for specific kernel/device pairs.…”

Section: Discussionmentioning

confidence: 99%

An adaptive methodology for multi-GPU programming in OpenCL

Bueno

Rodríguez

Sotelino

2017

View full text Add to dashboard Cite

Purpose The purpose of this work is to present a methodology that harnesses the computational power of multiple graphics processing units (GPUs) and hides the complexities of tuning GPU parameters from the users. Design/methodology/approach A methodology for auto-tuning OpenCL configuration parameters has been developed. Findings This described process helps simplify coding and generates a significant gain in time for each method execution. Originality/value Most authors develop their GPU applications for specific hardware configurations. In this work, a solution is offered to make the developed code portable to any GPU hardware.

show abstract

Section: Discussionmentioning

confidence: 99%

An adaptive methodology for multi-GPU programming in OpenCL

Bueno

Rodríguez

Sotelino

2017

View full text Add to dashboard Cite

show abstract

Tuning OpenCL Applications with the Periscope Tuning Framework

Bajrovic

Mijakovic

Dokulil

et al. 2016

2016 49th Hawaii International Conference on System Sciences (HICSS)

View full text Add to dashboard Cite

Due to the complexity and diversity of new parallel architectures automatic tuning of parallel applications has become increasingly important for achieving acceptable performance levels as well as performance portability. The European AutoTune project developed a tuning framework which closely integrates and automates performance analysis and performance tuning. The Periscope Tuning Framework relies on a flexible plugin mechanism providing tuning plugins for different tuning aspects. This paper presents plugins for tuning the execution time of OpenCL kernels on three different architectures, namely standard multicore CPUs, Xeon Phi coprocessors, and GPUs. We present OpenCL tuning via the flags used during offline kernel compilation as well as through the selection of the most appropriate NDRange configuration, which defines the organization of parallel threads used for kernel execution. Both tuning plugins show significant performance impact and a clear dependence on the target architecture and thus improve performance portability via automatic tuning.

show abstract

Efficient and Portable Workgroup Size Tuning

Tsao

2020

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Auto-Tuning OmpSs-OpenCL Kernels Across GPU Machines

Cited by 3 publications

References 7 publications

An adaptive methodology for multi-GPU programming in OpenCL

An adaptive methodology for multi-GPU programming in OpenCL

Tuning OpenCL Applications with the Periscope Tuning Framework

Efficient and Portable Workgroup Size Tuning

Contact Info

Product

Resources

About