國立虎尾科技大學 |

Studies in Exascale Computer Architecture : = Interconnect, Resiliency, and Checkpointing.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Studies in Exascale Computer Architecture :/
Reminder of title:	Interconnect, Resiliency, and Checkpointing.
Author:	Abeyratne, Sandunmalee Nilmini.
Description:	1 online resource (154 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 78-11(E), Section: B.
Contained By:	Dissertation Abstracts International78-11B(E).
Subject:	Computer engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9781369901962

Studies in Exascale Computer Architecture : = Interconnect, Resiliency, and Checkpointing.
Abeyratne, Sandunmalee Nilmini.

Studies in Exascale Computer Architecture :Interconnect, Resiliency, and Checkpointing. - 1 online resource (154 pages)

Source: Dissertation Abstracts International, Volume: 78-11(E), Section: B.

Thesis (Ph.D.)

Includes bibliographical references

Today's supercomputers are built from the state-of-the-art components to extract as much performance as possible to solve the most computationally intensive problems in the world. Building the next generation of exascale supercomputers, however, would require re-architecting many of these components to extract over 50x more performance than the current fastest supercomputer in the United States. To contribute towards this goal, two aspects of the compute node architecture were examined in this thesis: the on-chip interconnect topology and the memory and storage checkpointing platforms.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369901962Subjects--Topical Terms:

569006
Computer engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Studies in Exascale Computer Architecture : = Interconnect, Resiliency, and Checkpointing.
LDR:03403ntm a2200361Ki 4500 001 910532
005 20180517123956.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9781369901962
035 $a (MiAaPQ)AAI10612062
035 $a (MiAaPQ)umichrackham:000708
035 $a AAI10612062
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Abeyratne, Sandunmalee Nilmini. $3 1181869
245 1 0 $a Studies in Exascale Computer Architecture : $b Interconnect, Resiliency, and Checkpointing.
264 0 $c 2017
300 $a 1 online resource (154 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 78-11(E), Section: B.
500 $a Advisers: Ronald Dreslinski Jr; Trevor N Mudge.
502 $a Thesis (Ph.D.) $c University of Michigan $d 2017.
504 $a Includes bibliographical references
520 $a Today's supercomputers are built from the state-of-the-art components to extract as much performance as possible to solve the most computationally intensive problems in the world. Building the next generation of exascale supercomputers, however, would require re-architecting many of these components to extract over 50x more performance than the current fastest supercomputer in the United States. To contribute towards this goal, two aspects of the compute node architecture were examined in this thesis: the on-chip interconnect topology and the memory and storage checkpointing platforms.
520 $a As a first step, a skeleton exascale system was modeled to meet 1 exaflop of performance along with 100 petabytes of main memory. The model revealed that large kilo-core processors would be necessary to meet the exaflop performance goal; existing topologies, however, would not scale to those levels. To address this new challenge, we investigated and proposed asymmetric high-radix topologies that decoupled local and global communications and used different radix routers for switching network traffic at each level. The proposed topologies scaled more readily to higher numbers of cores with better latency and energy consumption than before.
520 $a The vast number of components that the model revealed would be needed in these exascale systems cautioned towards better fault tolerance mechanisms. To address this challenge, we showed that local checkpoints within the compute node can be saved to a hybrid DRAM and SSD platform in order to write them faster without wearing out the SSD or consuming a lot of energy. A hybrid checkpointing platform allowed more frequent checkpoints to be made without sacrificing performance. Subsequently, we proposed switching to a DIMM-based SSD in order to perform fine-grained I/O operations that would be integral in interleaving checkpointing and computation while still providing persistence guarantees. Two more techniques that consolidate and overlap checkpointing were designed to better hide the checkpointing latency to the SSD.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
655 7 $a Electronic books. $2 local $3 554714
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Michigan. $b Computer Science and Engineering. $3 1181870
773 0 $t Dissertation Abstracts International $g 78-11B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10612062 $z click for full text (PQDT)