The N3XT approach to energy-efficient abundant-data computing
The world's appetite for analyzing massive amounts of structured and unstructured data has grown dramatically. The computational demands of these abundant-data applications, such as deep learning, far exceed the capabilities of today's computing systems and are unlikely to be met with isol...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/143253 |
| _version_ | 1826119308373131264 |
|---|---|
| author | Mohamed M. Sabry Aly Wu, Tony F. Bartolo, Andrew Malviya, Yash H. Hwang, William Hills, Gage Markov, Igor Wootters, Mary Shulaker, Max M. Wong, Philip H.-S. Mitra, Subhasish |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Mohamed M. Sabry Aly Wu, Tony F. Bartolo, Andrew Malviya, Yash H. Hwang, William Hills, Gage Markov, Igor Wootters, Mary Shulaker, Max M. Wong, Philip H.-S. Mitra, Subhasish |
| author_sort | Mohamed M. Sabry Aly |
| collection | NTU |
| description | The world's appetite for analyzing massive amounts of structured and unstructured data has grown dramatically. The computational demands of these abundant-data applications, such as deep learning, far exceed the capabilities of today's computing systems and are unlikely to be met with isolated improvements in transistor or memory technologies, or integrated circuit architectures alone. To achieve unprecedented functionality, speed, and energy efficiency, one must create transformative nanosystems whose architectures are based on the salient properties of the underlying nanotechnologies. Our Nano-Engineered Computing Systems Technology (N3XT) approach makes such nanosystems possible through new computing system architectures leveraging emerging device (logic and memory) nanotechnologies and their dense 3-D integration with fine-grained connectivity to immerse computing in memory and new logic devices (such as carbon nanotube field-effect transistors for implementing high-speed and low-energy logic circuits) as well as high-density nonvolatile memory (such as resistive memory), and amenable to ultradense (monolithic) 3-D integration of thin layers of logic and memory devices that are fabricated at low temperature. In addition, we explore the use of several device and integration technologies in the N3XT beyond the specific ones mentioned earlier that are also used in our main nanosystem prototypes. We also present an efficient resiliency technique to overcome endurance challenges in certain resistive memory technologies. N3XT hardware prototypes demonstrate the practicality of our architectures. We evaluate the benefits of the N3XT using a simulation framework calibrated using experimental measurements. System-level energy-delay product of common implementations of abundant-data workloads improves by three orders of magnitude in the N3XT compared with conventional architectures. These improvements impact a broad range of application workloads and architecture configurations, from embedded systems to the cloud. |
| first_indexed | 2024-10-01T04:57:47Z |
| format | Journal Article |
| id | ntu-10356/143253 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:57:47Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1432532020-08-17T04:13:52Z The N3XT approach to energy-efficient abundant-data computing Mohamed M. Sabry Aly Wu, Tony F. Bartolo, Andrew Malviya, Yash H. Hwang, William Hills, Gage Markov, Igor Wootters, Mary Shulaker, Max M. Wong, Philip H.-S. Mitra, Subhasish School of Computer Science and Engineering Engineering::Computer science and engineering CNTFETs Energy Efficiency The world's appetite for analyzing massive amounts of structured and unstructured data has grown dramatically. The computational demands of these abundant-data applications, such as deep learning, far exceed the capabilities of today's computing systems and are unlikely to be met with isolated improvements in transistor or memory technologies, or integrated circuit architectures alone. To achieve unprecedented functionality, speed, and energy efficiency, one must create transformative nanosystems whose architectures are based on the salient properties of the underlying nanotechnologies. Our Nano-Engineered Computing Systems Technology (N3XT) approach makes such nanosystems possible through new computing system architectures leveraging emerging device (logic and memory) nanotechnologies and their dense 3-D integration with fine-grained connectivity to immerse computing in memory and new logic devices (such as carbon nanotube field-effect transistors for implementing high-speed and low-energy logic circuits) as well as high-density nonvolatile memory (such as resistive memory), and amenable to ultradense (monolithic) 3-D integration of thin layers of logic and memory devices that are fabricated at low temperature. In addition, we explore the use of several device and integration technologies in the N3XT beyond the specific ones mentioned earlier that are also used in our main nanosystem prototypes. We also present an efficient resiliency technique to overcome endurance challenges in certain resistive memory technologies. N3XT hardware prototypes demonstrate the practicality of our architectures. We evaluate the benefits of the N3XT using a simulation framework calibrated using experimental measurements. System-level energy-delay product of common implementations of abundant-data workloads improves by three orders of magnitude in the N3XT compared with conventional architectures. These improvements impact a broad range of application workloads and architecture configurations, from embedded systems to the cloud. Accepted version 2020-08-17T04:13:52Z 2020-08-17T04:13:52Z 2018 Journal Article Mohamed M. Sabry Aly, Wu, T. F., Bartolo, A., Malviya, Y. H., Hwang, W., Hills, G., ... Mitra, S. (2019). The N3XT approach to energy-efficient abundant-data computing. Proceedings of the IEEE, 107(1), 19-48. doi:10.1109/jproc.2018.2882603 0018-9219 https://hdl.handle.net/10356/143253 10.1109/JPROC.2018.2882603 2-s2.0-85059575205 1 107 19 48 en Proceedings of the IEEE © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/JPROC.2018.2882603. application/pdf |
| spellingShingle | Engineering::Computer science and engineering CNTFETs Energy Efficiency Mohamed M. Sabry Aly Wu, Tony F. Bartolo, Andrew Malviya, Yash H. Hwang, William Hills, Gage Markov, Igor Wootters, Mary Shulaker, Max M. Wong, Philip H.-S. Mitra, Subhasish The N3XT approach to energy-efficient abundant-data computing |
| title | The N3XT approach to energy-efficient abundant-data computing |
| title_full | The N3XT approach to energy-efficient abundant-data computing |
| title_fullStr | The N3XT approach to energy-efficient abundant-data computing |
| title_full_unstemmed | The N3XT approach to energy-efficient abundant-data computing |
| title_short | The N3XT approach to energy-efficient abundant-data computing |
| title_sort | n3xt approach to energy efficient abundant data computing |
| topic | Engineering::Computer science and engineering CNTFETs Energy Efficiency |
| url | https://hdl.handle.net/10356/143253 |
| work_keys_str_mv | AT mohamedmsabryaly then3xtapproachtoenergyefficientabundantdatacomputing AT wutonyf then3xtapproachtoenergyefficientabundantdatacomputing AT bartoloandrew then3xtapproachtoenergyefficientabundantdatacomputing AT malviyayashh then3xtapproachtoenergyefficientabundantdatacomputing AT hwangwilliam then3xtapproachtoenergyefficientabundantdatacomputing AT hillsgage then3xtapproachtoenergyefficientabundantdatacomputing AT markovigor then3xtapproachtoenergyefficientabundantdatacomputing AT woottersmary then3xtapproachtoenergyefficientabundantdatacomputing AT shulakermaxm then3xtapproachtoenergyefficientabundantdatacomputing AT wongphiliphs then3xtapproachtoenergyefficientabundantdatacomputing AT mitrasubhasish then3xtapproachtoenergyefficientabundantdatacomputing AT mohamedmsabryaly n3xtapproachtoenergyefficientabundantdatacomputing AT wutonyf n3xtapproachtoenergyefficientabundantdatacomputing AT bartoloandrew n3xtapproachtoenergyefficientabundantdatacomputing AT malviyayashh n3xtapproachtoenergyefficientabundantdatacomputing AT hwangwilliam n3xtapproachtoenergyefficientabundantdatacomputing AT hillsgage n3xtapproachtoenergyefficientabundantdatacomputing AT markovigor n3xtapproachtoenergyefficientabundantdatacomputing AT woottersmary n3xtapproachtoenergyefficientabundantdatacomputing AT shulakermaxm n3xtapproachtoenergyefficientabundantdatacomputing AT wongphiliphs n3xtapproachtoenergyefficientabundantdatacomputing AT mitrasubhasish n3xtapproachtoenergyefficientabundantdatacomputing |