Chisel: Reliability- and Accuracy-Aware Optimization of Approximate Computational Kernels
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 p...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for Computing Machinery (ACM)
2014
|
| Online Access: | http://hdl.handle.net/1721.1/91290 https://orcid.org/0000-0001-8256-0965 https://orcid.org/0000-0001-5333-9161 https://orcid.org/0000-0003-0313-9270 https://orcid.org/0000-0001-8095-8523 |
| _version_ | 1826199848141979648 |
|---|---|
| author | Misailovic, Sasa Achour, Sara Qi, Zichao Rinard, Martin C. Carbin, Michael James |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Misailovic, Sasa Achour, Sara Qi, Zichao Rinard, Martin C. Carbin, Michael James |
| author_sort | Misailovic, Sasa |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T11:27:05Z |
| format | Article |
| id | mit-1721.1/91290 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:27:05Z |
| publishDate | 2014 |
| publisher | Association for Computing Machinery (ACM) |
| record_format | dspace |
| spelling | mit-1721.1/912902022-10-01T03:41:23Z Chisel: Reliability- and Accuracy-Aware Optimization of Approximate Computational Kernels Misailovic, Sasa Achour, Sara Qi, Zichao Rinard, Martin C. Carbin, Michael James Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Misailovic, Sasa Carbin, Michael James Achour, Sara Qi, Zichao Rinard, Martin C. 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) 2014-11-04T19:52:50Z 2014-11-04T19:52:50Z 2014-10 Article http://purl.org/eprint/type/ConferencePaper 9781450325851 http://hdl.handle.net/1721.1/91290 Sasa Misailovic, Michael Carbin, Sara Achour, Zichao Qi, and Martin C. Rinard. 2014. Chisel: reliability- and accuracy-aware optimization of approximate computational kernels. In Proceedings of the 2014 ACM International Conference on Object Oriented Programming Systems Languages & Applications (OOPSLA '14). ACM, New York, NY, USA, 309-328. https://orcid.org/0000-0001-8256-0965 https://orcid.org/0000-0001-5333-9161 https://orcid.org/0000-0003-0313-9270 https://orcid.org/0000-0001-8095-8523 en_US http://dx.doi.org/10.1145/2660193.2660231 Proceedings of the 2014 ACM International Conference on Object Oriented Programming Systems Languages & Applications (OOPSLA '14) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computing Machinery (ACM) MIT |
| spellingShingle | Misailovic, Sasa Achour, Sara Qi, Zichao Rinard, Martin C. Carbin, Michael James Chisel: Reliability- and Accuracy-Aware Optimization of Approximate Computational Kernels |
| title | Chisel: Reliability- and Accuracy-Aware Optimization of Approximate Computational Kernels |
| title_full | Chisel: Reliability- and Accuracy-Aware Optimization of Approximate Computational Kernels |
| title_fullStr | Chisel: Reliability- and Accuracy-Aware Optimization of Approximate Computational Kernels |
| title_full_unstemmed | Chisel: Reliability- and Accuracy-Aware Optimization of Approximate Computational Kernels |
| title_short | Chisel: Reliability- and Accuracy-Aware Optimization of Approximate Computational Kernels |
| title_sort | chisel reliability and accuracy aware optimization of approximate computational kernels |
| url | http://hdl.handle.net/1721.1/91290 https://orcid.org/0000-0001-8256-0965 https://orcid.org/0000-0001-5333-9161 https://orcid.org/0000-0003-0313-9270 https://orcid.org/0000-0001-8095-8523 |
| work_keys_str_mv | AT misailovicsasa chiselreliabilityandaccuracyawareoptimizationofapproximatecomputationalkernels AT achoursara chiselreliabilityandaccuracyawareoptimizationofapproximatecomputationalkernels AT qizichao chiselreliabilityandaccuracyawareoptimizationofapproximatecomputationalkernels AT rinardmartinc chiselreliabilityandaccuracyawareoptimizationofapproximatecomputationalkernels AT carbinmichaeljames chiselreliabilityandaccuracyawareoptimizationofapproximatecomputationalkernels |