Title:
AxBench: A Benchmark Suite for Approximate Computing Across the System Stack
AxBench: A Benchmark Suite for Approximate Computing Across the System Stack
| dc.contributor.author | Yazdanbakhsh, Amir | |
| dc.contributor.author | Mahajan, Divya | |
| dc.contributor.author | Lotfi-Kamran, Pejman | |
| dc.contributor.author | Esmaeilzadeh, Hadi | |
| dc.contributor.corporatename | Georgia Institute of Technology. College of Computing | en_US |
| dc.contributor.corporatename | Georgia Institute of Technology. School of Computer Science | en_US |
| dc.contributor.corporatename | Institute for Research in Fundamental Sciences. School of Computer Science | en_US |
| dc.date.accessioned | 2016-01-11T15:43:14Z | |
| dc.date.available | 2016-01-11T15:43:14Z | |
| dc.date.issued | 2016 | |
| dc.description | Research areas: Approximate computing, Computer architecture | en_US |
| dc.description.abstract | As the end of Dennard scaling looms, both the semiconductor industry and the research community are exploring for innovative solutions that allow energy efficiency and performance to continue to scale. Approximation computing has become one of the viable techniques to perpetuate the historical improvements in the computing landscape. As approximate computing attracts more attention in the community, having a general, diverse, and representative set of benchmarks to evaluate different approximation techniques becomes necessary. In this paper, we develop and introduce AxBench, a general, diverse and representative multi-framework set of benchmarks for CPUs, GPUs, and hardware design with the total number of 29 benchmarks. We judiciously select and develop each benchmark to cover a diverse set of domains such as machine learning, scientific computation, signal processing, image processing, robotics, and compression. AxBench comes with the necessary annotations to mark the approximable region of code and the application-specific quality metric to assess the output quality of each application. AxBenchwith these set of annotations facilitate the evaluation of different approximation techniques. To demonstrate its effectiveness, we evaluate three previously proposed approximation techniques using AxBench benchmarks: loop perforation [1] and neural processing units (NPUs) [2–4] on CPUs and GPUs, and Axilog [5] on dedicated hardware. We find that (1) NPUs offer higher performance and energy efficiency as compared to loop perforation on both CPUs and GPUs, (2) while NPUs provide considerable efficiency gains on CPUs, there still remains significant opportunity to be explored by other approximation techniques, (3) Unlike on CPUs, NPUs offer full benefits of approximate computations on GPUs, and (4) considerable opportunity remains to be explored by innovative approximate computation techniques at the hardware level after applying Axilog. | en_US |
| dc.embargo.terms | null | en_US |
| dc.identifier.uri | http://hdl.handle.net/1853/54485 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | Georgia Institute of Technology | en_US |
| dc.relation.ispartofseries | SCS Technical Report ; GT-CS-16-01 | en_US |
| dc.subject | Approximate computing | en_US |
| dc.subject | ASIC | en_US |
| dc.subject | Benchmarking | en_US |
| dc.subject | CPU | en_US |
| dc.subject | GPU | en_US |
| dc.subject | Performance evaluation | en_US |
| dc.title | AxBench: A Benchmark Suite for Approximate Computing Across the System Stack | en_US |
| dc.type | Text | |
| dc.type.genre | Technical Report | |
| dspace.entity.type | Publication | |
| local.contributor.corporatename | College of Computing | |
| local.contributor.corporatename | School of Computer Science | |
| local.relation.ispartofseries | College of Computing Technical Report Series | |
| local.relation.ispartofseries | School of Computer Science Technical Report Series | |
| relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 | |
| relation.isOrgUnitOfPublication | 6b42174a-e0e1-40e3-a581-47bed0470a1e | |
| relation.isSeriesOfPublication | 35c9e8fc-dd67-4201-b1d5-016381ef65b8 | |
| relation.isSeriesOfPublication | 26e8e5bc-dc81-469c-bd15-88e6f98f741d |