Islands-of-Cores Approach for Harnessing SMP/NUMA Architectures in Heterogeneous Stencil Computations

Szustak, Łukasz; Wyrzykowski, Roman; Jakl, Ondřej

doi:10.1007/978-3-319-62932-2_34

Cited by 4 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous works [7,14,15], we proposed methods for the adaptation of MPDATA to multi-/manycore systems. These methods contribute to ease memory and communication bounds and to better exploit computation resources of sharedmemory systems, including CPUs and Intel Xeon Phi.…”

Section: Adaptation Of Data-flow Synchronization Strategy To Mpdatamentioning

confidence: 99%

Strategy for data-flow synchronizations in stencil parallel computations on multi-/manycore systems

Szustak

2018

J Supercomput

Self Cite

View full text Add to dashboard Cite

In this paper, an innovative strategy for the data-flow synchronization in shared-memory systems is proposed. This strategy assumes to synchronize only interdependent threads instead of using the barrier approach that-in contrast to our approach-synchronize all threads. We demonstrate the adaptation of the data-flow synchronization strategy to two complex scientific applications based on stencil codes. An algorithm for the data-flow synchronization is developed and successfully used for both applications. The proposed approach is evaluated for various Intel microarchitectures released in the last 5 years, including the newest processors: Skylake and Knights Landing. The important part of this assessment is the performance comparison of the proposed data-flow synchronization with the OpenMP barrier. The experimental results show that the performance of the studied applications can be accelerated up to 1.3 times using the proposed data-flow synchronizations strategy.

show abstract

Section: Adaptation Of Data-flow Synchronization Strategy To Mpdatamentioning

confidence: 99%

Strategy for data-flow synchronizations in stencil parallel computations on multi-/manycore systems

Szustak

2018

J Supercomput

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to overcome the described shortcoming and improve the efficiency of the MPDATA application, we proposed the islands-of-cores strategy [18] dedicated to heterogeneous stencils such as those of MPDATA. This strategy exposes the correlation between computation and communication for heterogeneous stencils, enabling a better management of the trade-off between computation and communication costs in accordance with features of various shared memory systems.…”

Section: Islands-of-cores Strategymentioning

confidence: 99%

“…An example of advanced SGI's product series is SGI UV ("Ultra Violet"), and in particular, SGI UV 2000 [18] and UV 3000 [14] servers. Based on Intel multicore CPUs and the high-speed NUMAlink system interconnect, they offer up to thousands of cores in a single system which shares large main memory.…”

Section: Introductionmentioning

confidence: 99%

“…In our previous work [18], we have taken up the challenge of harnessing the heterogeneous nature of communications in SGI SMP/NUMA platforms for the MPDATA application (Multidimensional Positive Definite Advection Transport Algorithm), which consists of a set of heterogeneous stencil kernels. The islands-of-cores approach (strategy) was proposed for heterogeneous stencils, based on replacement of implicit data transfers between caches of adjacent processors at the cost of extra computations.…”

Section: Introductionmentioning

confidence: 99%

“…However, it does not permit avoiding significant performance losses for larger multiprocessor architectures [18]. The (3+1)D decomposition improves both cache reusing and the data locality, but results in an intensive intra-and inter-cache communication between cores and processors.…”

Section: Introduction To Parallelization Of Mpdata Application On Shamentioning

confidence: 99%

See 2 more Smart Citations

Unleashing the performance of ccNUMA multiprocessor architectures in heterogeneous stencil computations

et al. 2018

Self Cite

View full text Add to dashboard Cite

This paper meets the challenge of harnessing the heterogeneous communication architecture of ccNUMA multiprocessors for heterogeneous stencil computations, an important example of which is the Multidimensional Positive Definite Advection Transport Algorithm (MPDATA). We propose a method for optimization of parallel implementation of heterogeneous stencil computations that is a combination of the islands-of-core strategy and (3+1)D decomposition. The method allows a flexible management of the trade-off between computation and communication costs in accordance with features of modern ccNUMA architectures. Its efficiency is demonstrated for the implementation of MPDATA on the SGI UV 2000 and UV 3000 servers, as well as for 2-and 4-socket ccNUMA platforms based on various Intel CPU architectures, including Skylake, Broadwell, and Haswell.

show abstract

Correlation of Performance Optimizations and Energy Consumption for Stencil-Based Application on Intel Xeon Scalable Processors

Szustak

Wyrzykowski

Olas

et al. 2020

IEEE Trans. Parallel Distrib. Syst.

Self Cite

View full text Add to dashboard Cite

This article provides a comprehensive study of the impact of performance optimizations on the energy efficiency of a real-world CFD application called MPDATA, as well as an insightful analysis of performance-energy interaction of these optimizations with the underlying hardware that represents the first generation of Intel Xeon Scalable processors. Considering the MPDATA iterative application as a use case, we explore the fundamentals of energy and performance analysis for a memory-bound application when exposed to a set of optimization steps that increase the application performance, by improving the operational intensity of code and utilizing resources more efficiently. It is shown that for memory-bound applications, optimizing toward high performance could be a powerful strategy for improving the energy efficiency as well. In fact, for the considered performance optimizations, the energy gain is correlated with the performance gain but with varying degrees. As a result, these optimizations allow improving both performance and energy consumption radically, up to about 10.9 and 8.8 times, respectively. The impact of the Intel AVX-512 SIMD extension on the energy consumption and performance is demonstrated. Also, we discover limitations on the usability of CPU frequency scaling as a tool for balancing energy savings with admissible performance losses.

show abstract

Islands-of-Cores Approach for Harnessing SMP/NUMA Architectures in Heterogeneous Stencil Computations

Cited by 4 publications

References 19 publications

Strategy for data-flow synchronizations in stencil parallel computations on multi-/manycore systems

Strategy for data-flow synchronizations in stencil parallel computations on multi-/manycore systems

Unleashing the performance of ccNUMA multiprocessor architectures in heterogeneous stencil computations

Correlation of Performance Optimizations and Energy Consumption for Stencil-Based Application on Intel Xeon Scalable Processors

Contact Info

Product

Resources

About