Efficient design space exploration of GPGPU architectures

Authors:
Ali Jooya;Amirali Baniasadi;Nikitas J. Dimopoulos
Affiliations:
Department of Electrical and Computer Engineering, University of Victoria, Victoria, B.C., Canada;Department of Electrical and Computer Engineering, University of Victoria, Victoria, B.C., Canada;Department of Electrical and Computer Engineering, University of Victoria, Victoria, B.C., Canada
Venue:
Euro-Par'12 Proceedings of the 18th international conference on Parallel processing workshops
Year:
2012

Citing 8
Cited 0

Knapsack problems: algorithms and computer implementations

Knapsack problems: algorithms and computer implementations
Improving Computer Architecture Simulation Methodology by Adding Statistical Rigor

IEEE Transactions on Computers
Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow

Proceedings of the 40th Annual IEEE/ACM International Symposium on Microarchitecture
Rodinia: A benchmark suite for heterogeneous computing

IISWC '09 Proceedings of the 2009 IEEE International Symposium on Workload Characterization (IISWC)
ReSPIR: a response surface-based Pareto iterative refinement for application-specific design space exploration

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
The GPU Computing Era

IEEE Micro
A New Heuristic for Solving the Multichoice Multidimensional Knapsack Problem

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Stargazer: Automated regression-based GPU design space exploration

ISPASS '12 Proceedings of the 2012 IEEE International Symposium on Performance Analysis of Systems & Software

Quantified Score

Hi-index	0.00

Visualization

Abstract

The goal of this work is to revisit GPU design and introduce a fast, low-cost and effective approach to optimize resource allocation in future GPUs. We have achieved this goal by using the Plackett-Burman methodology to explore the design space efficiently. We further formulate the design exploration problem as that of a constraint optimization. Our approach produces the optimum configuration in 84% of the cases, and in case that it does not, it produces the second optimal case with a performance penalty of less than 3.5%. Also, our method reduces the number of explorations one needs to perform by as much as 78%.