Managing Heterogeneous Resources in HPC Systems

Lecture Notes in Computer Science

et al. 2019

Self Cite

High-Performance Computing (HPC) is rapidly moving towards the adoption of nodes characterized by an heterogeneous set of processing resources. This has already shown benefits in terms of both performance and energy efficiency. On the other side, heterogeneous systems are challenging from the application development and the resource management perspective. In this work, we discuss some outcomes of the MANGO project, showing the results of the execution of real applications on a emulated deeply heterogeneous systems for HPC. Moreover, we assessed the achievements of a proposed resource allocation policy, aiming at identifying a priori the best resource allocation options for a starting application.

Section: Resource Managementmentioning

confidence: 99%

Predictive Resource Management for Next-Generation High-Performance Computing Heterogeneous Platforms

Massari

Pupykina

Lecture Notes in Computer Science

et al. 2019

Self Cite

“…However, programming on top of those runtimes is complex and when heterogeneity is involved, one code must be written for each target. This problem is common also to parallel programming models such as OpenCL [3,5,4]. Our approach aims to provide transparent compilation for heterogeneous targets, with direct support of data flow runtime, for an high-level DSL like R. To ease the achievement of these goals, we define our own programming model, which relies on the following concepts:…”

Section: Accelerating Data Analytics R Applicationmentioning

confidence: 99%

Accelerating Automotive Analytics: The M2DC Appliance Approach

Lecture Notes in Computer Science

Brandolese

Fornaciari

et al. 2019

Self Cite

The Modular Microserver DataCenter (M2DC) project provides lowenergy, configurable, heterogeneous servers for applications that focus on the elaboration of large data sets, but can take advantage of performance enhancement provided by transparent acceleration techniques. In this paper, we exemplify the M2DC approach through one of the project's use cases, namely automotive Internet of Things analytics. We present the main goals of the use case and we show how an appropriate M2DC microserver can be used to accelerate the application without significant modifications to its code.

“…cloud-based solutions [2], potentially open to a large audience of HPC users. These emerging scenarios require that new HPC platforms are able to support multiple applications running concurrently, possibly with conflicting Quality of Service requirements [3][4][5][6][7]. In addition, at the technology level, RECIPE addresses deep heterogeneity, based on dedicated accelerators like GPUs and FPGAs, as an enabling factor for improved energy efficiency, building on the results collected from previous research projects [8,9].…”

Section: Introduction and Long-term Objectivesmentioning

confidence: 99%

The RECIPE approach to challenges in deeply heterogeneous high performance systems

Microprocessors and Microsystems

Fornaciari

Atienza

et al. 2020

Self Cite

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.