Skip to Main content Skip to Navigation
Conference papers

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

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.
Complete list of metadata

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/hal-01798726
Contributor : Equipe Roma <>
Submitted on : Wednesday, May 23, 2018 - 7:03:22 PM
Last modification on : Monday, November 16, 2020 - 9:58:11 AM
Long-term archiving on: : Friday, August 24, 2018 - 11:01:01 PM

File

icpp18-hal.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

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⟩

Share

Metrics

Record views

206

Files downloads

418