Maximizing Throughput on a Dragonfly Network

Jain, Nikhil; Bhatelé, Abhinav; Ni, Xiang; Wright, Nicholas J.; Kalé, Laxmikant V.

doi:10.1109/sc.2014.33

Cited by 47 publications

(20 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 demonstrates runtime variability when running fast Fourier Transform programs [9,10] for solving the Navier-Stokes equations on Hazelhen and Shaheen II. Both these computers use adaptive routing and job placement to speed up job throughput [18], but this can result in some run time variability, a subject of current research [7,28,35,38,39].…”

Section: Lessons Learnedmentioning

confidence: 99%

Reproducibility in Benchmarking Parallel Fast Fourier Transform based Applications

Aseeri

Muite

Takahashi

2019

Companion of the 2019 ACM/SPEC International Conference on Performance Engineering

View full text Add to dashboard Cite

An overview of concerns observed in allowing for reproducibility in parallel applications that heavily depend on the three dimensional distributed memory fast Fourier transform are summarized. Suggestions for reproducibility categories for benchmark results are given. CCS CONCEPTS• Mathematics of computing → Computation of transforms;• Theory of computation → Massively parallel algorithms;• Software and its engineering → Software performance; • Hardware → Testing with distributed and parallel systems.

show abstract

Section: Lessons Learnedmentioning

confidence: 99%

Reproducibility in Benchmarking Parallel Fast Fourier Transform based Applications

Aseeri

Muite

Takahashi

2019

Companion of the 2019 ACM/SPEC International Conference on Performance Engineering

View full text Add to dashboard Cite

show abstract

“…Instead, algorithms like the local variant of Universal Globally-Adaptive Load-balanced routing [30,29] are used in practice. The complexity of this issue is exacerbated by the fact that the adaptive routing algorithm's performance depends in part on the workload [31].…”

Section: Topologies and Routingmentioning

confidence: 99%

Understanding congestion in high performance interconnection networks using sampling

Taffet

Mellor-Crummey

2019

Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis

View full text Add to dashboard Cite

Understanding Congestion in High Performance Interconnection Networks Using Sampling by Philip A. Taffet The computational needs of many applications outstrip the capabilities of a single compute node. Communication is necessary to employ multiple nodes, but slow communication often limits application performance on multiple nodes. To improve communication performance, developers need tools that enable them to understand how their application's communication patterns interact with the network, especially when those interactions result in congestion. Since communication performanceis difficult to reason about analytically and simulation is costly, measurement-based approaches are needed. This thesis describes a new sampling-based technique to collect information about the path a packet takes and congestion it encounters. Experiments with simulations show that this strategy can distinguish problems with an application's communication patterns, its mapping onto a parallel system, and outside interference. We describe a variant of this scheme that requires only 5-6 bits of information in a monitored packet, making it practical for use in next-generation networks.

show abstract

“…is paper focuses on fat-tree because of the multiplicity of design options available for it [20,34]. For analysis and prediction of performance on HPC networks, several approaches ranging from analytical modeling [12,26,36,38] to it and packet-level simulations [18,28,35,41] have been proposed. We deploy trace-driven packet-level simulations because they allow for use of existing codes for simulating their communication complexity.…”

Section: Related Workmentioning

confidence: 99%

Predicting the performance impact of different fat-tree configurations

Jain

Bhatelé

Howell

et al. 2017

Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis

Self Cite

View full text Add to dashboard Cite

e fat-tree topology is one of the most commonly used network topologies in HPC systems. Vendors support several options that can be congured when deploying fat-tree networks on production systems, such as link bandwidth, number of rails, number of planes, and tapering. is paper showcases the use of simulations to compare the impact of these design options on representative production HPC applications, libraries, and multi-job workloads. We present advances in the TraceR-CODES simulation framework that enable this analysis and evaluate its prediction accuracy against experiments on a production fat-tree network. In order to understand the impact of dierent network congurations on various anticipated scenarios, we study workloads with dierent communication paerns, computation-to-communication ratios, and scaling characteristics. Using multi-job workloads, we also study the impact of inter-job interference on performance and compare the cost-performance tradeos.

show abstract

Maximizing Throughput on a Dragonfly Network

Cited by 47 publications

References 25 publications

Reproducibility in Benchmarking Parallel Fast Fourier Transform based Applications

Reproducibility in Benchmarking Parallel Fast Fourier Transform based Applications

Understanding congestion in high performance interconnection networks using sampling

Predicting the performance impact of different fat-tree configurations

Contact Info

Product

Resources

About