Chisel: Reliability- and Accuracy-Aware Optimization of Approximate Computational Kernels

• Main Authors: Misailovic, Sasa (Contributor), Achour, Sara (Contributor), Qi, Zichao (Contributor), Rinard, Martin C. (Contributor), Carbin, Michael James (Contributor)
• Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
• Format: Article
• Language: English
• Published: Association for Computing Machinery (ACM), 2014-11-04T19:52:50Z.
• Subjects: Article
• Online Access: Get fulltext

The accuracy of an approximate computation is the distance between the result that the computation produces and the corresponding fully accurate result. The reliability of the computation is the probability that it will produce an acceptably accurate result. Emerging approximate hardware platforms provide approximate operations that, in return for reduced energy consumption and/or increased performance, exhibit reduced reliability and/or accuracy. We present Chisel, a system for reliability- and accuracy-aware optimization of approximate computational kernels that run on approximate hardware platforms. Given a combined reliability and/or accuracy specification, Chisel automatically selects approximate kernel operations to synthesize an approximate computation that minimizes energy consumption while satisfying its reliability and accuracy specification. We evaluate Chisel on five applications from the image processing, scientific computing, and financial analysis domains. The experimental results show that our implemented optimization algorithm enables Chisel to optimize our set of benchmark kernels to obtain energy savings from 8.7% to 19.8% compared to the fully reliable kernel implementations while preserving important reliability guarantees.
National Science Foundation (U.S.) (Grant CCF-1036241)
National Science Foundation (U.S.) (Grant CCF-1138967)
National Science Foundation (U.S.) (Grant IIS-0835652)
United States. Dept. of Energy (Grant DE-SC0008923)
United States. Defense Advanced Research Projects Agency (Grant FA8650-11-C-7192)
United States. Defense Advanced Research Projects Agency (Grant FA8750-12-2-0110)
United States. Defense Advanced Research Projects Agency (Grant FA-8750-14-2-0004)