DocumentCode :
2806493
Title :
Optimize or Wait? Using llc Fast-Prototyping Tool to Evaluate CUDA Optimizations
Author :
Reyes, Ruymán ; De Sande, Francisco
Author_Institution :
Dept. de EIO y Comput., Univ. de La Laguna, La Laguna, Spain
fYear :
2011
fDate :
9-11 Feb. 2011
Firstpage :
257
Lastpage :
261
Abstract :
Over the last few years, we have witnessed the proliferation of GPU devices on HPC environments. Manufacturers produce new versions of their devices every few years, though, posing a new problem for scientists and engineers using their technology: is it worth the time and effort spent optimizing the codes for the current version? Or it is better to wait until a new architecture appears? In this paper, we present a comparison of various CUDA versions, in order to compare their architectures, and optimize codes for each version. This work would require a tremendous coding effort if done manually. However, using fast prototyping tools, like llCoMP, this is an effortless process. Applying loop optimization techniques, we evaluate three different algorithms. With each one, we apply a set of optimization techniques, showing the performance benefit or penalty, in three CUDA architecture versions, including Fermi. The results of these techniques will guide developers on the right path towards efficient code optimization. Preliminary results show that some optimizations recommended for older CUDA architectures may not be useful in Fermi.
Keywords :
computer architecture; coprocessors; optimising compilers; program control structures; software prototyping; CUDA architecture; CUDA optimization; Fermi; GPU device; HPC environment; code optimization; llCoMP; llc fast-prototyping tool; loop optimization technique; Computational modeling; Computer architecture; Graphics processing unit; Instruction sets; Kernel; Optimization; Performance evaluation; CUDA; GPGPU; OpenMP; automatic parallelization; code performance; compiler; llc; productivity;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Parallel, Distributed and Network-Based Processing (PDP), 2011 19th Euromicro International Conference on
Conference_Location :
Ayia Napa
ISSN :
1066-6192
Print_ISBN :
978-1-4244-9682-2
Type :
conf
DOI :
10.1109/PDP.2011.12
Filename :
5738995
Link To Document :
بازگشت