Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Ameya D. Patil"'
Publikováno v:
IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, Vol 5, Iss 1, Pp 10-18 (2019)
The energy and delay reductions from CMOS scaling have stagnated, motivating the search for a CMOS replacement. Spintronic devices are one of the promising beyond-CMOS alternatives. However, they exhibit high switching error rates of 1% or more when
Externí odkaz:
https://doaj.org/article/c080bf36177b4f93bd66c9e90fc72628
Publikováno v:
IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, Vol 5, Iss 1, Pp 34-42 (2019)
Computational scaling beyond silicon electronics based on Moore's law requires the adoption of alternate state variables such as electronic spin. Multiple research efforts are underway exploring both Boolean and non-Boolean design space using spin de
Externí odkaz:
https://doaj.org/article/9cea1abd162741b38021e92ba4cbb97b
Publikováno v:
IEEE Transactions on Circuits and Systems I: Regular Papers. 67:1627-1639
In-memory architectures, in particular, the deep in-memory architecture (DIMA) has emerged as an attractive alternative to the traditional von Neumann (digital) architecture for realizing energy and latency-efficient machine learning systems in silic
Publikováno v:
IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, Vol 5, Iss 1, Pp 10-18 (2019)
The energy and delay reductions from CMOS scaling have stagnated, motivating the search for a CMOS replacement. Spintronic devices are one of the promising beyond-CMOS alternatives. However, they exhibit high switching error rates of 1% or more when
Publikováno v:
IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, Vol 5, Iss 1, Pp 34-42 (2019)
Computational scaling beyond silicon electronics based on Moore’s law requires the adoption of alternate state variables such as electronic spin. Multiple research efforts are underway exploring both Boolean and non-Boolean design space using spin
Publikováno v:
ICCAD
Crossbar-based in-memory architectures have emerged as an attractive platform for energy-efficient realization of deep neural networks (DNNs). A key challenge in such architectures is achieving accurate and efficient writes due to the presence of bit
Publikováno v:
IEEE Journal of Solid-State Circuits. 53:642-655
A multi-functional in-memory inference processor integrated circuit (IC) in a 65-nm CMOS process is presented. The prototype employs a deep in-memory architecture (DIMA), which enhances both energy efficiency and throughput over conventional digital
Publikováno v:
ISCAS
This paper presents an MRAM-based deep in-memory architecture (MRAM-DIMA) to efficiently implement multi-bit matrix vector multiplication for deep neural networks using a standard MRAM bitcell array. The MRAM-DIMA achieves an 4.5 × and 70× lower en
Publikováno v:
ISCAS
With diminishing energy and delay benefits via CMOS scaling, there is much interest in exploring the use of alternative state variables such as electronic spin. Multiple research efforts are underway exploring both Boolean and non-Boolean design spac
Autor:
Lav R. Varshney, Jan M. Rabaey, Naresh R. Shanbhag, Ian A. Young, Larry Pileggi, Sasikanth Manipatruni, Eric Pop, Ameya D. Patil, Jeffrey A. Weldon, Dmitri E. Nikonov, Subhasish Mitra, H.-S. Philip Wong
Publikováno v:
DAC
Emerging applications require computing platforms to extract task-relevant information from increasingly large amounts of data. These requirements place stringent constraints on energy efficiency, throughput, latency, and for certain data types, secu