Paper Info
Title
Getting ready for approximate computing: trading parallelism for accuracy for DSS workloads.
Abstract
Processors have evolved dramatically in the last years and current multicore systems deliver very high performance. We areobserving a rapid increase in the number of cores per processor thus resulting in more dense and powerful systems. Nevertheless,this evolution will meet several challenges such as power consumption, and reliability. It is expected that, in order to improvethe efficiency, future processors will contain units that are able to operate at a very low power consumption with the drawbackof not guaranteeing the correctness of the produced results. This model is known as Approximate Computing. One interestingapproach to exploit Approximate Computing is to make applications aware of the errors and react accordingly. For this work wefocus on the Decision Support System Workloads and in particular the standard TPC-H set of queries. We first define a metricthat quantifies the correctness of a query result - Quality of Result (QoR). Using this metric we analyse the impact of relaxingthe correctness in the DBMS on the accuracy of the query results. In order to improve the accuracy of the results we propose adynamic adaptive technique that is implemented as a tool above the DBMS. Using heuristics, this tool spawns a number of replicaquery executions on different cores and combines the results as to improve the accuracy. We evaluated our technique using realTPC-H queries and data on PostgreSQL with a simple fault-injection to emulate the Approximate Computing model. The resultsshow that for the selected scenarios, the proposed technique is able to increase the QoR with a cost in parallel resources smallerthan any alternative static approach. The results are very encouraging since the QoR is within 7% of the best possible.
Year
DOI
Venue
2014
10.1109/ISPDC.2015.39
International Symposium on Parallel and Distributed Computing
Keywords
Field
DocType
simulator
Drawback,Replica,Computer science,Correctness,Decision support system,Parallel computing,Real-time computing,Exploit,Heuristics,Power consumption,Approximate computing,Distributed computing
Conference
ISSN
ISBN
Citations 
2379-5352
978-1-4673-7147-6
1
PageRank 
References 
Authors
0.35
18
1
Name
Order
Citations
PageRank
Pedro Trancoso137743.79