2017 Euromicro Conference on Digital System Design (DSD) 2017
DOI: 10.1109/dsd.2017.37
|View full text |Cite
|
Sign up to set email alerts
|

Paving the Way Towards a Highly Energy-Efficient and Highly Integrated Compute Node for the Exascale Revolution: The ExaNoDe Approach

Abstract: Abstract-Power consumption and high compute density are the key factors to be considered when building a compute node for the upcoming Exascale revolution. Current architectural design and manufacturing technologies are not able to provide the requested level of density and power efficiency to realise an operational Exascale machine. A disruptive change in the hardware design and integration process is needed in order to cope with the requirements of this forthcoming computing target. This paper presents the E… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
18
0

Year Published

2018
2018
2020
2020

Publication Types

Select...
3
3
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 24 publications
(18 citation statements)
references
References 11 publications
0
18
0
Order By: Relevance
“…ExaNoDe [16] focuses on the design of a highly energy efficient and highly integrated heterogeneous compute node targeting exascale level computing. The design of the target node mixes low-power processors, heterogeneous co-processors and includes advanced hardware integration technologies with a novel memory system.…”
Section: Related Workmentioning
confidence: 99%
“…ExaNoDe [16] focuses on the design of a highly energy efficient and highly integrated heterogeneous compute node targeting exascale level computing. The design of the target node mixes low-power processors, heterogeneous co-processors and includes advanced hardware integration technologies with a novel memory system.…”
Section: Related Workmentioning
confidence: 99%
“…By appropriately configuring the cache policy each remote memory access can be cached locally. This work was continued in the ExaNoDe [34] and EuroEXA [31] projects. The dReDBox project [4] also proposes a customizable low-power architecture comprised of hot-pluggable modules that provide compute, memory and accelerators resources.…”
Section: Introductionmentioning
confidence: 99%
“…In the disaggregated design, individual components such as processor, memory and storage are interconnected over a network [14,21,28,36,40] rather than being restricted to a bus on a single board [33]. The EuroEXA family of projects [14,34], for instance, provides a global physical address space in which cores can access remote memory via RDMA and direct load-store instructions. In comparison with traditional shared memory processors, the focus is on sharing of memory capacity, rather than coherent sharing of data.…”
mentioning
confidence: 99%
“…These advancements have become even more prominent as we rapidly approach the dawn of exascale computing, with machines capable of performing a million trillion floating-point calculations per second. [1][2][3] However, to enable these massive calculations, recent exascale computing guidelines [4][5][6] have strongly cautioned that this increase in computing power should only require a modest increase in power consumption (to offset both operation costs and deleterious climate change effects).…”
Section: Introductionmentioning
confidence: 99%