New Logic-In-Memory Paradigms: An Architectural and Technological Perspective
Processing systems are in continuous evolution thanks to the constant technological advancement and architectural progress. Over the years, computing systems have become more and more powerful, providing support for applications, such as Machine Learning, that require high computational power. Howev...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/10/6/368 |
| _version_ | 1818993908513767424 |
|---|---|
| author | Giulia Santoro Giovanna Turvani Mariagrazia Graziano |
| author_facet | Giulia Santoro Giovanna Turvani Mariagrazia Graziano |
| author_sort | Giulia Santoro |
| collection | DOAJ |
| description | Processing systems are in continuous evolution thanks to the constant technological advancement and architectural progress. Over the years, computing systems have become more and more powerful, providing support for applications, such as Machine Learning, that require high computational power. However, the growing complexity of modern computing units and applications has had a strong impact on power consumption. In addition, the memory plays a key role on the overall power consumption of the system, especially when considering data-intensive applications. These applications, in fact, require a lot of data movement between the memory and the computing unit. The consequence is twofold: Memory accesses are expensive in terms of energy and a lot of time is wasted in accessing the memory, rather than processing, because of the performance gap that exists between memories and processing units. This gap is known as the memory wall or the von Neumann bottleneck and is due to the different rate of progress between complementary metal−oxide semiconductor (CMOS) technology and memories. However, CMOS scaling is also reaching a limit where it would not be possible to make further progress. This work addresses all these problems from an architectural and technological point of view by: (1) Proposing a novel Configurable Logic-in-Memory Architecture that exploits the in-memory computing paradigm to reduce the memory wall problem while also providing high performance thanks to its flexibility and parallelism; (2) exploring a non-CMOS technology as possible candidate technology for the Logic-in-Memory paradigm. |
| first_indexed | 2024-12-20T20:49:32Z |
| format | Article |
| id | doaj.art-b373f02968b84a76b70ab90c71f92a3c |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-12-20T20:49:32Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-b373f02968b84a76b70ab90c71f92a3c2022-12-21T19:26:57ZengMDPI AGMicromachines2072-666X2019-05-0110636810.3390/mi10060368mi10060368New Logic-In-Memory Paradigms: An Architectural and Technological PerspectiveGiulia Santoro0Giovanna Turvani1Mariagrazia Graziano2Dipartimento di Elettronica e Telecomunicazioni, Politecnico di Torino; Corso Castelfidardo 39, 10129 Torino, ItalyDipartimento di Elettronica e Telecomunicazioni, Politecnico di Torino; Corso Castelfidardo 39, 10129 Torino, ItalyDipartimento di Elettronica e Telecomunicazioni, Politecnico di Torino; Corso Castelfidardo 39, 10129 Torino, ItalyProcessing systems are in continuous evolution thanks to the constant technological advancement and architectural progress. Over the years, computing systems have become more and more powerful, providing support for applications, such as Machine Learning, that require high computational power. However, the growing complexity of modern computing units and applications has had a strong impact on power consumption. In addition, the memory plays a key role on the overall power consumption of the system, especially when considering data-intensive applications. These applications, in fact, require a lot of data movement between the memory and the computing unit. The consequence is twofold: Memory accesses are expensive in terms of energy and a lot of time is wasted in accessing the memory, rather than processing, because of the performance gap that exists between memories and processing units. This gap is known as the memory wall or the von Neumann bottleneck and is due to the different rate of progress between complementary metal−oxide semiconductor (CMOS) technology and memories. However, CMOS scaling is also reaching a limit where it would not be possible to make further progress. This work addresses all these problems from an architectural and technological point of view by: (1) Proposing a novel Configurable Logic-in-Memory Architecture that exploits the in-memory computing paradigm to reduce the memory wall problem while also providing high performance thanks to its flexibility and parallelism; (2) exploring a non-CMOS technology as possible candidate technology for the Logic-in-Memory paradigm.https://www.mdpi.com/2072-666X/10/6/368in-memory computinglogic-in-memorynon-von Neumann architectureconfigurable logic-in-memory architecturememory wallconvolutional neural networksemerging technologiesperpendicular Nano Magnetic Logic (pNML) |
| spellingShingle | Giulia Santoro Giovanna Turvani Mariagrazia Graziano New Logic-In-Memory Paradigms: An Architectural and Technological Perspective Micromachines in-memory computing logic-in-memory non-von Neumann architecture configurable logic-in-memory architecture memory wall convolutional neural networks emerging technologies perpendicular Nano Magnetic Logic (pNML) |
| title | New Logic-In-Memory Paradigms: An Architectural and Technological Perspective |
| title_full | New Logic-In-Memory Paradigms: An Architectural and Technological Perspective |
| title_fullStr | New Logic-In-Memory Paradigms: An Architectural and Technological Perspective |
| title_full_unstemmed | New Logic-In-Memory Paradigms: An Architectural and Technological Perspective |
| title_short | New Logic-In-Memory Paradigms: An Architectural and Technological Perspective |
| title_sort | new logic in memory paradigms an architectural and technological perspective |
| topic | in-memory computing logic-in-memory non-von Neumann architecture configurable logic-in-memory architecture memory wall convolutional neural networks emerging technologies perpendicular Nano Magnetic Logic (pNML) |
| url | https://www.mdpi.com/2072-666X/10/6/368 |
| work_keys_str_mv | AT giuliasantoro newlogicinmemoryparadigmsanarchitecturalandtechnologicalperspective AT giovannaturvani newlogicinmemoryparadigmsanarchitecturalandtechnologicalperspective AT mariagraziagraziano newlogicinmemoryparadigmsanarchitecturalandtechnologicalperspective |