Explicit Data Layout Management for Autotuning Exploration on Complex Memory Topologies

Perarnau, Swann; Videau, Brice; Denoyelle, Nicolas; Monna, Florence; Iskra, Kamil; Beckman, Pete

doi:10.1109/mchpc49590.2019.00015

Cited by 3 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its focus is on data-intensive processing and mixed workloads and the close integration of HPC with data analytics. At a lower level, Perarneau et al [17] and Unat et al [22] have been working on low-level abstraction of data layout in memory. Work on SharP also brings a low-level abstraction layer for data management [24].…”

Section: Related Workmentioning

confidence: 99%

A Middleware Supporting Data Movement in Complex and Software-Defined Storage and Memory Architectures

Haine¹,

Haus²,

Martinasso

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

A Middleware Supporting Data Movement in Complex and Software-Defined Storage and Memory Architectures

Haine¹,

Haus²,

Martinasso

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Numa-Aware Data Management for Neutron Cross Section Data in Continuous Energy Monte Carlo Neutron Transport Simulation

et al. 2021

View full text Add to dashboard Cite

The calculation of macroscopic neutron cross-sections is a fundamental part of the continuous-energy Monte Carlo (MC) neutron transport algorithm. MC simulations of full nuclear reactor cores are computationally expensive, making high-accuracy simulations impractical for most routine reactor analysis tasks because of their long time to solution. Thus, preparation of MC simulation algorithms for next generation supercomputers is extremely important as improvements in computational performance and efficiency will directly translate into improvements in achievable simulation accuracy. Due to the stochastic nature of the MC algorithm, cross-section data tables are accessed in a highly randomized manner, resulting in frequent cache misses and latency-bound memory accesses. Furthermore, contemporary and next generation non-uniform memory access (NUMA) computer architectures, featuring very high latencies and less cache space per core, will exacerbate this behaviour. The absence of a topology-aware allocation strategy in existing high-performance computing (HPC) programming models is a major source of performance problems in NUMA systems. Thus, to improve performance of the MC simulation algorithm, we propose a topology-aware data allocation strategies that allow full control over the location of data structures within a memory hierarchy. A new memory management library, known as AML, has recently been created to facilitate this mapping. To evaluate the usefulness of AML in the context of MC reactor simulations, we have converted two existing MC transport cross-section lookup “proxy-applications” (XSBench and RSBench) to utilize the AML allocation library. In this study, we use these proxy-applications to test several continuous-energy cross-section data lookup strategies (the nuclide grid, unionized grid, logarithmic hash grid, and multipole methods) with a number of AML allocation schemes on a variety of node architectures. We find that the AML library speeds up cross-section lookup performance up to 2x on current generation hardware (e.g., a dual-socket Skylake-based NUMA system) as compared with naive allocation. These exciting results also show a path forward for efficient performance on next-generation exascale supercomputer designs that feature even more complex NUMA memory hierarchies.

show abstract

Mamba: Portable Array-based Abstractions for Heterogeneous High-Performance Systems

Dykes¹,

Foyer

Richardson³

et al. 2021

2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC)

View full text Add to dashboard Cite

Explicit Data Layout Management for Autotuning Exploration on Complex Memory Topologies

Cited by 3 publications

References 23 publications

A Middleware Supporting Data Movement in Complex and Software-Defined Storage and Memory Architectures

A Middleware Supporting Data Movement in Complex and Software-Defined Storage and Memory Architectures

Numa-Aware Data Management for Neutron Cross Section Data in Continuous Energy Monte Carlo Neutron Transport Simulation

Mamba: Portable Array-based Abstractions for Heterogeneous High-Performance Systems

Contact Info

Product

Resources

About