Paper Info
Title
CGPredict: Embedded GPU Performance Estimation from Single-Threaded Applications.
Abstract
Heterogeneous multiprocessor system-on-chip architectures are endowed with accelerators such as embedded GPUs and FPGAs capable of general-purpose computation. The application developers for such platforms need to carefully choose the accelerator with the maximum performance benefit. For a given application, usually, the reference code is specified in a high-level single-threaded programming language such as C. The performance of an application kernel on an accelerator is a complex interplay among the exposed parallelism, the compiler, and the accelerator architecture. Thus, determining the performance of a kernel requires its redevelopment into each accelerator-specific language, causing substantial wastage of time and effort. To aid the developer in this early design decision, we present an analytical framework CGPredict to predict the performance of a computational kernel on an embedded GPU architecture from un-optimized, single-threaded C code. The analytical approach provides insights on application characteristics which suggest further application-specific optimizations. The estimation error is as low as 2.66% (average 9%) compared to the performance of the same kernel written in native CUDA code running on NVIDIA Kepler embedded GPU. This low performance estimation error enables CGPredict to provide an early design recommendation of the accelerator starting from C code.
Year
DOI
Venue
2017
10.1145/3126546
ACM Trans. Embedded Comput. Syst.
Keywords
Field
DocType
GPGPU, Heterogenous platform, analytical model, cross-platform prediction, mobile platform, performance modeling
Kernel (linear algebra),Architecture,CUDA,Computer science,Parallel computing,Field-programmable gate array,Compiler,Multiprocessing,Real-time computing,General-purpose computing on graphics processing units,Computation
Journal
Volume
Issue
ISSN
16
5
1539-9087
Citations 
PageRank 
References 
0
0.34
14
Authors
3
Name
Order
Citations
PageRank
Siqi Wang1375.39
Guanwen Zhong2393.43
Tulika Mitra32714135.99