國立高雄大學圖資館 |

Language: English

Back

Statistical inference for efficient ...

Harvard University.

Statistical inference for efficient microarchitectural analysis.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Statistical inference for efficient microarchitectural analysis.
Author:	Lee, Benjamin Chi-Chung.
Description:	168 p.
Notes:	Adviser: David M. Brooks.
Notes:	Source: Dissertation Abstracts International, Volume: 69-04, Section: B, page: 2419.
Contained By:	Dissertation Abstracts International69-04B.
Subject:	Engineering, Electronics and Electrical.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3312433
ISBN:	9780549614098

Statistical inference for efficient microarchitectural analysis.
Lee, Benjamin Chi-Chung.

Statistical inference for efficient microarchitectural analysis. - 168 p.

Adviser: David M. Brooks.

Thesis (Ph.D.)--Harvard University, 2008.

Furthermore, inferential models enable qualitatively new capabilities in optimization for emerging design priorities. Not only do these models answer prior questions far more quickly, they answer new questions previously intractable with detailed simulation. This dissertation implements robust optimization techniques to assess multiprocessor heterogeneity and microarchitectural adaptivity, quantifying trends and limits in performance and power efficiency from these design paradigms. The capabilities from inference scale to multi-billion point design spaces, giving designers the holistic view necessary to successfully implement the transition to multiprocessors.

ISBN: 9780549614098Subjects--Topical Terms:

226981
Engineering, Electronics and Electrical.

Statistical inference for efficient microarchitectural analysis.
LDR:03313nmm _2200301 _450 001 206859
005 20090413125836.5
008 090730s2008 ||||||||||||||||| ||eng d
020 $a 9780549614098
035 $a 00372071
040 $a UMI $c UMI
100 $a Lee, Benjamin Chi-Chung. $3 321794
245 1 0 $a Statistical inference for efficient microarchitectural analysis.
300 $a 168 p.
500 $a Adviser: David M. Brooks.
500 $a Source: Dissertation Abstracts International, Volume: 69-04, Section: B, page: 2419.
502 $a Thesis (Ph.D.)--Harvard University, 2008.
520 $a Furthermore, inferential models enable qualitatively new capabilities in optimization for emerging design priorities. Not only do these models answer prior questions far more quickly, they answer new questions previously intractable with detailed simulation. This dissertation implements robust optimization techniques to assess multiprocessor heterogeneity and microarchitectural adaptivity, quantifying trends and limits in performance and power efficiency from these design paradigms. The capabilities from inference scale to multi-billion point design spaces, giving designers the holistic view necessary to successfully implement the transition to multiprocessors.
520 $a The transition to multiprocessors expands the space of viable core designs and requires sophisticated optimization over multiple design metrics. However, microarchitectural design space exploration is often inefficient and ad hoc due to the significant computational costs of hardware simulators. Long simulation times cause designers to subjectively constrain the design space considered. However, by pruning the design space with intuition before a study, the designer risks obtaining conclusions that simply reinforce prior intuition, thereby limiting the study's value. Addressing these fundamental challenges in microarchitectural analysis becomes increasingly urgent as the semiconductor industry moves into new domains where tried and tested intuition becomes less effective.
520 $a This dissertation presents the case for statistical inference in microarchitectural design, proposing a simulation paradigm that (1) defines a comprehensive design space, (2) simulates sparse samples from that space, and (3) derives inferential regression models to reveal salient trends. These regression models accurately capture performance and power associations for comprehensive multi-billion point design spaces. Moreover, they are capable of thousand's of predictions per second.
520 $a Used as computationally efficient surrogates for detailed simulation, regression models enable previously intractable analyses of performance and power. Leveraging model efficiency, this dissertation demonstrates qualitatively new capabilities by using pareto frontiers to identify power-efficient designs, contour maps to visualize bottlenecks, and roughness metrics to quantify non-monotonicity in design topologies.
590 $a School code: 0084.
650 $a Engineering, Electronics and Electrical. $3 226981
650 $a Computer Science. $3 212513
690 $a 0544
690 $a 0984
710 $a Harvard University. $3 212445
773 0 $g 69-04B. $t Dissertation Abstracts International
790 $a 0084
790 1 0 $a Brooks, David M., $e advisor
791 $a Ph.D.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3312433 $z http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3312433