A Pattern-Based Comparison of OpenACC and OpenMP for Accelerator Computing

Wienke, Sandra; Terboven, Christian; Beyer, James C.; Müller, Matthias S.

doi:10.1007/978-3-319-09873-9_68

Cited by 28 publications

(24 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An in-depth investigation performed by Wienke et al [9] analysed the differences between OpenACC and OpenMP 4.0 and suggested that, while they are similar, OpenACC was slightly ahead of OpenMP 4.0 in terms of features. For instance, OpenACC 2.0 offers the tile and cache directives for optimisations, which are not present in OpenMP 4.0, however it does not include support for tasks or a mature implementation for targeting the CPU.…”

Section: Openacc and Cudamentioning

confidence: 99%

“…Dietrich et al [19] implemented a performance measurement library that allowed measurement of OpenMP 4.0 code running on the KNC architecture. Wienke et al [9] compared OpenMP 4.0 and OpenACC, predicting that OpenMP 4.0 would likely achieve best adoption in the long-term because it is such a prominent standard, and proposing performance evaluations as important future work.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Evaluating OpenMP 4.0's Effectiveness as a Heterogeneous Parallel Programming Model

Martineau¹,

McIntosh–Smith²,

Gaudin

2016

2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)

View full text Add to dashboard Cite

Abstract-Although the OpenMP 4.0 standard has been available since 2013, support for GPUs has been absent up until very recently, with only a handful of experimental compilers available. In this work we evaluate the performance of Cray's new NVIDIA GPU targeting implementation of OpenMP 4.0, with the mini-apps TeaLeaf, CloverLeaf and BUDE. We successfully port each of the applications, using a simple and consistent design throughout, and achieve performance on an NVIDIA K20X that is comparable to Cray's OpenACC in all cases. BUDE, a compute bound code, required 2.2x the runtime of an equivalently optimised CUDA code, which we believe is caused by an inflated frequency of control flow operations and less efficient arithmetic optimisation. Impressively, both TeaLeaf and CloverLeaf, memory bandwidth bound codes, only required 1.3x the runtime of hand-optimised CUDA implementations. Overall, we find that OpenMP 4.0 is a highly usable open standard capable of performant heterogeneous execution, making it a promising option for scientific application developers.

show abstract

Section: Openacc and Cudamentioning

confidence: 99%

mentioning

confidence: 99%

Evaluating OpenMP 4.0's Effectiveness as a Heterogeneous Parallel Programming Model

Martineau¹,

McIntosh–Smith²,

Gaudin

2016

2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)

View full text Add to dashboard Cite

show abstract

“…The reader may have noticed that OpenACC is similar to the OpenMP (Open Multi-Processing) language in several ways [14]; both environments are directive based, but OpenACC targets accelerators in general, while at this stage OpenMP targets mainly multi-core CPUs, even if the OpenMP project is clearly moving towards accelerators support. Regular C/C++ or Fortran code, already developed and tested on traditional CPU architectures, can be annotated with OpenACC pragma directives (e.g.…”

Section: Openaccmentioning

confidence: 99%

Development of Scientific Software for HPC Architectures Using Open ACC: The Case of LQCD

Bonati

Calore

Coscetti

et al. 2015

2015 IEEE/ACM 1st International Workshop on Software Engineering for High Performance Computing in Science

View full text Add to dashboard Cite

Many scientific software applications, that solve complex compute-or data-intensive problems, such as large parallel simulations of physics phenomena, increasingly use HPC systems in order to achieve scientifically relevant results. An increasing number of HPC systems adopt heterogeneous node architectures, combining traditional multi-core CPUs with energy-efficient massively parallel accelerators, such as GPUs. The need to exploit the computing power of these systems, in conjunction with the lack of standardization in their hardware and/or programming frameworks, raises new issues with respect to scientific software development choices, which strongly impact software maintainability, portability and performance. Several new programming environments have been introduced recently, in order to address these issues. In particular, the OpenACC programming standard has been designed to ease the software development process for codes targeted for heterogeneous machines, helping to achieve code and performance portability. In this paper we present, as a specific OpenACC use case, an example of design, porting and optimization of an LQCD Monte Carlo code intended to be portable across present and future heterogeneous HPC architectures; we describe the design process, the most critical design choices and evaluate the tradeoff between portability and efficiency.

show abstract

“…OpenACC is similar to the OpenMP (Open Multi-Processing) framework widely used to manage parallel codes on multi-core CPUs in several ways 6 ; both frameworks are directive based, but OpenACC targets accelerators in general, while at this stage OpenMP targets mainly multi-core CPUs; the latest release of OpenMP4 standard has introduced directives to manage also accelerators, but currently, compilers support is still limited. Regular C/C++ or Fortran code, already developed and tested on traditional CPU architectures, can be annotated with OpenACC pragma directives (e.g.…”

Section: Current Trends In Hpcmentioning

confidence: 99%

“…OpenMP 4 and OpenACC 5 are among the most common such programming models, already used by a wide scientific community. Both are based on directives: OpenMP was introduced to manage parallelism on traditional multi-core CPUs, while OpenACC is mainly used to target GPUs (although designed to be architecture agnostic) 6 . These two frameworks are in fact converging and extending their scope to cover a large subset of HPC applications and architectures: OpenMP version 4 has been designed to support also accelerators, while compilers supporting OpenACC (such as the PGI 8 ) are starting to use directives also to target multi-core CPUs.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Design and optimization of a portable LQCD Monte Carlo code using OpenACC

Bonati

Coscetti

D’Elia

et al. 2017

Int. J. Mod. Phys. C

View full text Add to dashboard Cite

The present panorama of HPC architectures is extremely heterogeneous, ranging from traditional multi-core CPU processors, supporting a wide class of applications but delivering moderate computing performance, to many-core GPUs, exploiting aggressive data-parallelism and delivering higher performances for streaming computing applications. In this scenario, code portability (and performance portability) become necessary for easy maintainability of applications; this is very relevant in scientific computing where code changes are very frequent, making it tedious and prone to error to keep different code versions aligned. In this work we present the design and optimization of a state-of-the-art production-level LQCD Monte Carlo application, using the directivebased OpenACC programming model. OpenACC abstracts parallel programming to a descriptive level, relieving programmers from specifying how codes should be mapped onto the target architecture. We describe the implementation of a code fully written in OpenACC, and show that we are able to target several different architectures, including state-of-the-art traditional CPUs and GPUs, with the same code. We also measure performance, evaluating the computing efficiency of our OpenACC code on several architectures, comparing with GPU-specific implementations and showing that a good level of performance-portability can be reached.

show abstract

A Pattern-Based Comparison of OpenACC and OpenMP for Accelerator Computing

Cited by 28 publications

References 10 publications

Evaluating OpenMP 4.0's Effectiveness as a Heterogeneous Parallel Programming Model

Evaluating OpenMP 4.0's Effectiveness as a Heterogeneous Parallel Programming Model

Development of Scientific Software for HPC Architectures Using Open ACC: The Case of LQCD

Design and optimization of a portable LQCD Monte Carlo code using OpenACC

Contact Info

Product

Resources

About