Towards making autotuning mainstream. (November 2013)

• Record Type: Journal Article
• Authors: Basu, Protonu; Hall, Mary; Khan, Malik; Maindola, Suchit; Muralidharan, Saurav; Ramalingam, Shreyas; Rivera, Axel; Shantharam, Manu; Venkat, Anand
• Is Part Of: International journal of high performance computing applications. Volume 27:Number 4(2013)
• Page Start: 379
• Page End: 393
• Publication Date: 2013-11
• Subjects: performance tuning -- compiler optimization -- parallel computing; High performance computing -- Periodicals; Supercomputers -- Periodicals; 004.1105
• DOI: 10.1177/1094342013493644
• Languages: English
• ISSNs: 1094-3420

Abstract

Autotuning systems employ empirical techniques to evaluate the suitability of a search space of possible implementations of a computation. Autotuning has emerged as a critical strategy for achieving high performance as architectural complexity grows. Present-day autotuning technology augments the capabilities of expert users or is hidden inside compilers, but to date has not been adopted as a mainstream technology. Based on our prior experience and the experience of others in developing autotuning technology and applying it to libraries and applications, this paper examines some of the barriers to adoption of the technology and future research areas to break down these barriers.