2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA) 2015
DOI: 10.1109/hpca.2015.7056064
|View full text |Cite
|
Sign up to set email alerts
|

Quantifying sources of error in McPAT and potential impacts on architectural studies

Abstract: Architectural power modeling tools are widely used by the computer architecture community for rapid evaluations of high-level design choices and design space explorations. Currently, McPAT [31] is the de facto power model, but the literature does not yet contain a careful examination of its modeling accuracy. In addition, the issue of how greatly power modeling error can affect architectural-level studies has not been quantified before. In this work, we present the first rigorous assessment of McPAT's core po… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
44
0

Year Published

2015
2015
2022
2022

Publication Types

Select...
4
4
2

Relationship

0
10

Authors

Journals

citations
Cited by 80 publications
(44 citation statements)
references
References 48 publications
0
44
0
Order By: Relevance
“…We incorporate the changes suggested by Xi et al [22] to improve the accuracy of the models. The hardware structures of the DMU are modeled using CACTI 6.0 [23], adding the appropriate counters in gem5 to measure the extra power introduced by the DMU.…”
Section: Experimental Framework a Full-system Simulation Infrastmentioning
confidence: 99%
“…We incorporate the changes suggested by Xi et al [22] to improve the accuracy of the models. The hardware structures of the DMU are modeled using CACTI 6.0 [23], adding the appropriate counters in gem5 to measure the extra power introduced by the DMU.…”
Section: Experimental Framework a Full-system Simulation Infrastmentioning
confidence: 99%
“…Power consumption is evaluated with McPAT [23] using a process technology of 22 nm, voltage of 0.6V and the default clock gating scheme. We add the changes suggested by Xi et al [24] to improve the accuracy of the models. The hardware structures of RaCCD are modeled using CACTI 6.0 [25].…”
Section: A Full-system Simulation Infrastructurementioning
confidence: 99%
“…Estimating power with this tool is slow as they require use of a cycle-accurate simulator such as GEM5 [2] to acquire the data needed by the power model. Recently, Xi et al [19] found that McPAT's estimations might have a significant error due to some of their power models being incomplete, or too highlevel, or assume implementations of structures that differ from that of the real hardware. The Functional-Level Power Analysis (FLPA) technique proposed by Rethinagiri et al [14][13] [15] was efficiently utilized in developing power models for various hardware components (processing core, clock unit, memory system, Input/Output peripheral units, etc.)…”
Section: Related Workmentioning
confidence: 99%