Exploring manycore architectures for next-generation HPC systems through the MANGO approach

Autor: José María Torralba Martínez, Giovanni Agosta, Anna Pupykina, Daniel Hofman, Tomas Picornell, Marina Zapater, Leon Dragić, Ermis Papastefanakis, Gerald Guillaume, Igor Piljić, Jose Flich, Simone Libutti, Alessandro Cilardo, Edoardo Fusella, Mirko Gagliardi, Michele Zanella, Davide Zoni, Alexandre Dray, Ynse Hoornenborg, Bruno Maitre, Hrvoje Mlinarić, Carlo Brandolese, Philipp Ampletzer, Arman Iranfar, Mario Kovač, Federico Reghenzani, Giuseppe Massari, Isabelle Staub, Rafael Tornero, William Fornaciari, Etienne Cappe, Alen Duspara, Koen Meinds, David Alonso
Jazyk: angličtina
Rok vydání: 2018
Předmět:
Computer Networks and Communications
Computer science
Distributed computing
Parallel programming
02 engineering and technology
Multi many cores
01 natural sciences
run time management
high performance computing
heterogeneous architectures
parallel programming
programming model
resource management
power modeling
memory management
thermal management
Artificial Intelligence
0103 physical sciences
0202 electrical engineering
electronic engineering
information engineering
Resource management
power optimizaton
010302 applied physics
Quality of service
Heterogeneous architectures
Power modeling
Supercomputer
020202 computer hardware & architecture
ARQUITECTURA Y TECNOLOGIA DE COMPUTADORES
Memory management
Programming model
Hardware and Architecture
HPC
Programming paradigm
High performance computing
Thermal management
Software
performance
System software
Multi many cores
run time management
power optimizaton
HPC
Zdroj: RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
Microprocessors and Microsystems
Popis: [EN] The Horizon 2020 MANGO project aims at exploring deeply heterogeneous accelerators for use in High-Performance Computing systems running multiple applications with different Quality of Service (QoS) levels. The main goal of the project is to exploit customization to adapt computing resources to reach the desired QoS. For this purpose, it explores different but interrelated mechanisms across the architecture and system software. In particular, in this paper we focus on the runtime resource management, the thermal management, and support provided for parallel programming, as well as introducing three applications on which the project foreground will be validated.
This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 671668.
Databáze: OpenAIRE
Externí odkaz: