A Microbenchmark Suite for Mixed-Mode OpenMP/MPI

Bull, J. Mark; Enright, James P.; Ameer, Nadia

doi:10.1007/978-3-642-02303-3_10

Cited by 14 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rabenseifner et al [12] look at the problems associated with trying to match hybrid model parallelism to multi-core cluster architecture and examine the performance of different methods of hybrid implementations. Bull et al describe a microbenchmark suite for analysing hybrid code performance and present results of the suite in [13]. In [16] Brunst and Mohr describe the profiling of hybrid codes with Vampir NG.…”

Section: Previous Workmentioning

confidence: 98%

See 1 more Smart Citation

Performance analysis of a hybrid MPI/OpenMP application on multi-core clusters

Chorley

Walker

2010

Journal of Computational Science

View full text Add to dashboard Cite

a b s t r a c tThe mixing of shared memory and message passing programming models within a single application has often been suggested as a method for improving scientific application performance on clusters of shared memory or multi-core systems. DL POLY, a large scale molecular dynamics application programmed using message passing programming has been modified to add a layer of shared memory threading and the performance analysed on two multi-core clusters. At lower processor numbers, the extra overheads from shared memory threading in the hybrid code outweigh performance benefits gained over the pure MPI code. On larger core counts the hybrid model performs better than pure MPI, with reduced communication time decreasing the overall runtime.

show abstract

Section: Previous Workmentioning

confidence: 98%

“…Recently the hybrid model has also been discussed on clusters of multi-core nodes [12,13]. The use of the hybrid model on multi-core clusters, and the performance of the model on such systems has been looked at in general terms with different test tools and performance models.…”

Section: Previous Workmentioning

confidence: 99%

Performance analysis of a hybrid MPI/OpenMP application on multi-core clusters

Chorley

Walker

2010

Journal of Computational Science

View full text Add to dashboard Cite

show abstract

“…MPI Fault Tolerance Benchmarking. There have been many benchmark suites [39], [40], [41] developed for MPI performance modeling. SKaMPI [42] is an early benchmark suite that evaluates different implementations of MPI.…”

Section: E Use Of Matchmentioning

confidence: 99%

MATCH: An MPI Fault Tolerance Benchmark Suite

Guo

Georgakoudis

Parasyris

et al. 2020

2020 IEEE International Symposium on Workload Characterization (IISWC)

View full text Add to dashboard Cite

MPI has been ubiquitously deployed in flagship HPC systems aiming to accelerate distributed scientific applications running on tens of hundreds of processes and compute nodes. Maintaining the correctness and integrity of MPI application execution is critical, especially for safety-critical scientific applications. Therefore, a collection of effective MPI fault tolerance techniques have been proposed to enable MPI application execution to efficiently resume from system failures. However, there is no structured way to study and compare different MPI fault tolerance designs, so to guide the selection and development of efficient MPI fault tolerance techniques for distinct scenarios. To solve this problem, we design, develop, and evaluate a benchmark suite called MATCH to characterize, research, and comprehensively compare different combinations and configurations of MPI fault tolerance designs. Our investigation derives useful findings: (1) Reinit recovery in general performs better than ULFM recovery; (2) Reinit recovery is independent of the scaling size and the input problem size, whereas ULFM recovery is not; (3) Using Reinit recovery with FTI checkpointing is a highly efficient fault tolerance design. MATCH code is available at https://github.com/kakulo/MPI-FT-Bench.

show abstract

“…(Note that for the Barrier benchmark, no data is involved). For further details of the benchmark design, see [3].…”

Section: Collective Operationsmentioning

confidence: 99%

“…To fill this gap, we have designed and implemented a suite of microbenchmarks for mixed-mode OpenMP/MPI programming [3]. The utility of such a suite is demonstrated by the results presented in [12], which demonstrate how the available communication bandwidth between nodes can depend on the mix of MPI processes and OpenMP threads employed.…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Mixed-Mode OpenMP/MPI Implementations

Bull

Enright

Guo

et al. 2010

Int J Parallel Prog

Self Cite

View full text Add to dashboard Cite

With the current prevalence of multi-core processors in HPC architectures, mixed-mode programming, using both MPI and OpenMP in the same application, is seen as an important technique for achieving high levels of scalability. As there are few standard benchmarks written in this paradigm, it is difficult to assess the likely performance of such programs. To help address this, we examine the performance of mixed-mode OpenMP/MPI on a number of popular HPC architectures, using a synthetic benchmark suite and two large-scale applications. We find performance characteristics which differ significantly between implementations, and which highlight possible areas for improvement, especially when multiple OpenMP threads communicate simultaneously via MPI.

show abstract

A Microbenchmark Suite for Mixed-Mode OpenMP/MPI

Cited by 14 publications

References 5 publications

Performance analysis of a hybrid MPI/OpenMP application on multi-core clusters

Performance analysis of a hybrid MPI/OpenMP application on multi-core clusters

MATCH: An MPI Fault Tolerance Benchmark Suite

Performance Evaluation of Mixed-Mode OpenMP/MPI Implementations

Contact Info

Product

Resources

About