Conference paper Open Access
Leon, Vasileios; Asimakopoulos, Konstantinos; Xydis, Sotirios; Soudris, Dimitrios; Pekmestzi, Kiamal
{ "files": [ { "links": { "self": "https://zenodo.org/api/files/7c1eb102-e455-4d2f-88e8-eddcf23e3abe/dac-Leon.pdf" }, "checksum": "md5:600061dcbbe96fcc3ffcada2124c1856", "bucket": "7c1eb102-e455-4d2f-88e8-eddcf23e3abe", "key": "dac-Leon.pdf", "type": "pdf", "size": 225005 } ], "owners": [ 43983 ], "doi": "10.1145/3316781.3317793", "stats": { "version_unique_downloads": 32.0, "unique_views": 60.0, "views": 71.0, "version_views": 71.0, "unique_downloads": 32.0, "version_unique_views": 60.0, "volume": 7425165.0, "version_downloads": 33.0, "downloads": 33.0, "version_volume": 7425165.0 }, "links": { "doi": "https://doi.org/10.1145/3316781.3317793", "latest_html": "https://zenodo.org/record/3472504", "bucket": "https://zenodo.org/api/files/7c1eb102-e455-4d2f-88e8-eddcf23e3abe", "badge": "https://zenodo.org/badge/doi/10.1145/3316781.3317793.svg", "html": "https://zenodo.org/record/3472504", "latest": "https://zenodo.org/api/records/3472504" }, "created": "2019-10-04T08:34:30.534047+00:00", "updated": "2020-01-20T16:49:14.340153+00:00", "conceptrecid": "3472503", "revision": 4, "id": 3472504, "metadata": { "access_right_category": "success", "embargo_date": "2020-01-01", "doi": "10.1145/3316781.3317793", "description": "<p>Approximate computing appears as an emerging and promising solution for energy-efficient system designs, exploiting the inherent error-tolerant nature of various applications. In this paper, targeting multiplication circuits, i.e., the energy-hungry counterpart of hardware accelerators, an extensive exploration of the error--energy trade-off, when combining arithmetic-level approximation techniques, is performed for the first time. Arithmetic-aware approximations deliver significant energy reductions, while allowing to control the error values with discipline by setting accordingly a configuration parameter. Inspired from the promising results of prior works with one configuration parameter, we propose 5 hybrid design families for approximate and energy-friendly hardware multipliers, consisting of two independent parameters to tune the approximation levels. Interestingly, the resolution of the state-of-the-art Pareto diagram is improved, giving the flexibility to achieve better energy gains for a specific error constraint imposed by the system. Moreover, we outperform prior works in the field of approximate multipliers by up to 60% energy reduction, and thus, we define the new Pareto front.</p>", "license": { "id": "CC-BY-4.0" }, "title": "Cooperative Arithmetic-Aware Approximation Techniques for Energy-Efficient Multipliers", "relations": { "version": [ { "count": 1, "index": 0, "parent": { "pid_type": "recid", "pid_value": "3472503" }, "is_last": true, "last_child": { "pid_type": "recid", "pid_value": "3472504" } } ] }, "grants": [ { "code": "780572", "links": { "self": "https://zenodo.org/api/grants/10.13039/501100000780::780572" }, "title": "Software Development toolKit for Energy optimization and technical Debt elimination", "acronym": "SDK4ED", "program": "H2020", "funder": { "doi": "10.13039/501100000780", "acronyms": [], "name": "European Commission", "links": { "self": "https://zenodo.org/api/funders/10.13039/501100000780" } } }, { "code": "801015", "links": { "self": "https://zenodo.org/api/grants/10.13039/501100000780::801015" }, "title": "Enhancing Programmability and boosting Performance Portability for Exascale Computing Systems", "acronym": "EXA2PRO", "program": "H2020", "funder": { "doi": "10.13039/501100000780", "acronyms": [], "name": "European Commission", "links": { "self": "https://zenodo.org/api/funders/10.13039/501100000780" } } } ], "publication_date": "2019-07-01", "creators": [ { "affiliation": "National Technical University of Athens, Greece", "name": "Leon, Vasileios" }, { "affiliation": "National Technical University of Athens, Greece", "name": "Asimakopoulos, Konstantinos" }, { "affiliation": "National Technical University of Athens, Greece", "name": "Xydis, Sotirios" }, { "affiliation": "National Technical University of Athens, Greece", "name": "Soudris, Dimitrios" }, { "affiliation": "National Technical University of Athens, Greece", "name": "Pekmestzi, Kiamal" } ], "access_right": "open", "resource_type": { "subtype": "conferencepaper", "type": "publication", "title": "Conference paper" } } }
Views | 71 |
Downloads | 33 |
Data volume | 7.4 MB |
Unique views | 60 |
Unique downloads | 32 |