Paper Info
Title
TBPoint: Reducing Simulation Time for Large-Scale GPGPU Kernels
Abstract
Architecture simulation for GPGPU kernels can take a significant amount of time, especially for large-scale GPGPU kernels. This paper presents TBPoint, an infrastructure based on profiling-based sampling for GPGPU kernels to reduce the cycle-level simulation time. Compared to existing approaches, TBPoint provides a flexible and architecture-independent way to take samples. For the evaluated 12 kernels, the geometric means of sampling errors of TBPoint, Ideal-Simpoint, and random sampling are 0.47%, 1.74%, and 7.95%, respectively, while the geometric means of the total sample size of TBPoint, Ideal-Simpoint, and random sampling are 2.6%, 5.4%, and 10%, respectively. TBPoint narrows the speed gap between hardware and GPGPU simulators, enabling more and more large-scale GPGPU kernels to be analyzed using detailed timing simulations.
Year
DOI
Venue
2014
10.1109/IPDPS.2014.53
IPDPS
Keywords
DocType
ISSN
large-scale gpgpu kernels,cycle-level simulation time reduction,architecture simulation,graphics processing units,tbpoint,multiprocessing systems,sampling errors,performance modeling,ideal-simpoint,sampling,simulation,gpgpu,random sampling,sampling methods,profiling-based sampling,computational modeling,markov processes,mathematical model,instruction sets,vectors,kernel,hardware
Conference
1530-2075
Citations 
PageRank 
References 
5
0.42
9
Authors
4
Name
Order
Citations
PageRank
Jen-Cheng Huang1222.54
Lifeng Nai2615.40
Hyesoon Kim3149381.05
Hsien-Hsin Sean Lee41657102.66