A performance model to execute workflows on high-bandwidth-memory architectures - Archive ouverte HAL Access content directly
Conference Papers Year :

A performance model to execute workflows on high-bandwidth-memory architectures

(1, 2) , (3) , (2) , (4, 2)
1
2
3
4

Abstract

This work presents a realistic performance model to execute scientific workflows on high-bandwidth-memory architectures such as the Intel Knights Landing. We provide a detailed analysis of the execution time on such platforms, taking into account transfers from both fast and slow memory and their overlap with computations. We discuss several scheduling and mapping strategies: not only tasks must be assigned to computing resources, but also one has to decide which fraction of input and output data will reside in fast memory and which will have to stay in slow memory. We use extensive simulations to assess the impact of the mapping strategies on performance. We also conduct experiments for a simple 1D Gauss-Seidel kernel, which assess the accuracy of the model and further demonstrate the importance of a tuned memory management. Our model and results lay the foundations for further studies and experiments on dual-memory systems.
Fichier principal
Vignette du fichier
icpp18-hal.pdf (826.67 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01798726 , version 1 (23-05-2018)

Identifiers

Cite

Anne Benoit, Swann Perarnau, Loïc Pottier, Yves Robert. A performance model to execute workflows on high-bandwidth-memory architectures. ICPP 2018 - 47th International Conference on Parallel Processing, Aug 2018, Eugene, OR, United States. pp.1-10, ⟨10.1145/3225058.3225110⟩. ⟨hal-01798726⟩
87 View
165 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More