An investigation of the performance portability of OpenCL

Pennycook, John; Hammond, Simon David; Wright, Steven A.; Herdman, J. A.; Miller, Ian D.; Jarvis, Stephen A.

doi:10.1016/j.jpdc.2012.07.005

Cited by 50 publications

(24 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The work presented by Pennycook et al 14 shows how performance can suffer when bad values are chosen for various parameters, which supports the claim that autotuning is needed. However, they concentrate on a Message Passing Interface (MPI)/OpenCL approach, whereas we are benchmarking using only OpenCL.…”

Section: Related Workmentioning

confidence: 61%

Integrating the Nqueens Algorithm into a Parameterized Benchmark Suite

Infantolino¹,

Malley²

2016

View full text Add to dashboard Cite

Public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing the burden, to Department of Defense, Washington Headquarters Services, Directorate for Information Operations and Reports (0704-0188), 1215 Jefferson Davis Highway, Suite 1204, Arlington, VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to any penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. PLEASE DO NOT RETURN YOUR FORM TO THE ABOVE ADDRESS.

show abstract

Section: Related Workmentioning

confidence: 61%

Integrating the Nqueens Algorithm into a Parameterized Benchmark Suite

Infantolino¹,

Malley²

2016

View full text Add to dashboard Cite

show abstract

“…A device-specific program, when executed directly on another device, typically cannot achieve good performance [20], [21]. With poor performance portability, the use of multiple heterogeneous devices will not be beneficial but cause performance penalties.…”

Section: Discussion and Future Workmentioning

confidence: 99%

Enabling a Uniform OpenCL Device View for Heterogeneous Platforms

Huang

Xun

et al. 2015

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYAiming to ease the parallel programming for heterogeneous architectures, we propose and implement a high-level OpenCL runtime that conceptually merges multiple heterogeneous hardware devices into one virtual heterogeneous compute device (VHCD). Moreover, automated workload distribution among the devices is based on offline profiling, together with new programming directives that define the deviceindependent data access range per work-group. Therefore, an OpenCL program originally written for a single compute device can, after inserting a small number of programming directives, run efficiently on a platform consisting of heterogeneous compute devices. Performance is ensured by introducing the technique of virtual cache management, which minimizes the amount of host-device data transfer. Our new OpenCL runtime is evaluated by a diverse set of OpenCL benchmarks, demonstrating good performance on various configurations of a heterogeneous system.

show abstract

“…The NPB [19,20] consists of five kernels including IS, EP, CG, MG, and FT and three pseudo applications including SP, BT, and LU. The OpenCL version of NPB was created by SNU [16].…”

Section: Evaluation Algorithmmentioning

confidence: 99%

A Two-Level Task Scheduler on Multiple DSP System for OpenCL

Tian

Cai

Zhou

2014

Advances in Mechanical Engineering

View full text Add to dashboard Cite

This paper addresses the problem that multiple DSP system does not support OpenCL programming. With the compiler, runtime, and the kernel scheduler proposed, an OpenCL application becomes portable not only between multiple CPU and GPU, but also between embedded multiple DSP systems. Firstly, the LLVM compiler was imported for source-to-source translation in which the translated source was supported by CCS. Secondly, two-level schedulers were proposed to support efficient OpenCL kernel execution. The DSP/BIOS is used to schedule system level tasks such as interrupts and drivers; however, the synchronization mechanism resulted in heavy overhead during task switching. So we designed an efficient second level scheduler especially for OpenCL kernel work-item scheduling. The context switch process utilizes the 8 functional units and cross path links which was superior to DSP/BIOS in the aspect of task switching. Finally, dynamic loading and software managed CACHE were redesigned for OpenCL running on multiple DSP system. We evaluated the performance using some common OpenCL kernels from NVIDIA, AMD, NAS, and Parboil benchmarks. Experimental results show that the DSP OpenCL can efficiently exploit the computing resource of multiple cores.

show abstract

An investigation of the performance portability of OpenCL

Abstract: The version presented here is a working paper or pre-print that may be later published elsewhere. If a published version is known of, the above WRAP url will contain details on finding it.

Cited by 50 publications

References 14 publications

Integrating the Nqueens Algorithm into a Parameterized Benchmark Suite

Integrating the Nqueens Algorithm into a Parameterized Benchmark Suite

Enabling a Uniform OpenCL Device View for Heterogeneous Platforms

A Two-Level Task Scheduler on Multiple DSP System for OpenCL

Contact Info

Product

Resources

About