Zobrazeno 1 - 10
of 189
pro vyhledávání: '"Joel Emer"'
Publikováno v:
Scientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
Abstract As deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available compute power; however, efforts to continue to scale electronic p
Externí odkaz:
https://doaj.org/article/0d72cdbc9c1e4e1d9de42249a489e054
Publikováno v:
2022 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::89354c0eebf2c789f1ff457a7694b6eb
https://doi.org/10.1109/ispass55109.2022.00039
https://doi.org/10.1109/ispass55109.2022.00039
Publikováno v:
Synthesis Lectures on Computer Architecture. 15:1-341
This book provides a structured treatment of the key principles and techniques for enabling efficient processing of deep neural networks (DNNs). DNNs are currently widely used for many artificial intelligence (AI) applications, including computer vis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa2a7e8a812915256a4fcdff2b865f24
https://doi.org/10.2200/s01004ed1v01y202004cac050
https://doi.org/10.2200/s01004ed1v01y202004cac050
Autor:
Joel Emer, Matthew Fojtik, C. Thomas Gray, Ben Keller, Stephen G. Tell, Priyanka Raina, Stephen W. Keckler, Alicia Klinefelter, William J. Dally, Brucek Khailany, Brian Zimmer, Jason Clemons, Rangharajan Venkatesan, Nan Jiang, Yanqing Zhang, Nathaniel Pinckney, Yakun Sophia Shao
Publikováno v:
IEEE Journal of Solid-State Circuits. 55:920-932
Custom accelerators improve the energy efficiency, area efficiency, and performance of deep neural network (DNN) inference. This article presents a scalable DNN accelerator consisting of 36 chips connected in a mesh network on a multi-chip-module (MC
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ece7623ba975846ccab654fbbe909096
https://doi.org/10.1109/jssc.2019.2960488
https://doi.org/10.1109/jssc.2019.2960488
Autor:
Elba Garza, Gururaj Saileshwar, Udit Gupta, Tianyi Liu, Abdulrahman Mahmoud, Saugata Ghose, Joel Emer
Publikováno v:
2021 ACM/IEEE Workshop on Computer Architecture Education (WCAE).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::edfe3addc015a29b9986ea623dd8a255
https://doi.org/10.1109/wcae53984.2021.9707614
https://doi.org/10.1109/wcae53984.2021.9707614
Publikováno v:
ISCA
Irregular applications, such as graph analytics and sparse linear algebra, exhibit frequent indirect, data-dependent accesses to single or short sequences of elements that cause high main memory traffic and limit performance. Data compression is a pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fce6fe406efc6fe907b9098280f1616b
https://doi.org/10.1109/isca52012.2021.00087
https://doi.org/10.1109/isca52012.2021.00087
Publikováno v:
ASPLOS
Sparse matrix-sparse matrix multiplication (spMspM) is at the heart of a wide range of scientific and machine learning applications. spMspM is inefficient on general-purpose architectures, making accelerators attractive. However, prior spMspM acceler
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e19b0d511b63f4c73b09ee6f13b45e22
https://doi.org/10.1145/3445814.3446702
https://doi.org/10.1145/3445814.3446702
Autor:
Dirk Englund, Joel Emer, Liane Bernstein, Marin Soljacic, Alexander Sludds, Vivienne Sze, Ryan Hamerly
Publikováno v:
Physics and Simulation of Optoelectronic Devices XXIX.
Optical approaches to machine learning rely heavily on programmable linear photonic circuits. Since the performance and energy efficiency scale with size, a major challenge is overcoming scaling roadblocks to the photonic technology. Recently, we pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5dbe65a1a905cc94aca2a035ed1745f
https://doi.org/10.1117/12.2576990
https://doi.org/10.1117/12.2576990
Publikováno v:
ISPASS
This paper presents Sparseloop, the first infrastructure that implements an analytical design space exploration methodology for sparse tensor accelerators. Sparseloop comprehends a wide set of architecture specifications including various sparse opti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f893dd2f6f7dc7e3463f3ae84f61fca
https://doi.org/10.1109/ispass51385.2021.00043
https://doi.org/10.1109/ispass51385.2021.00043
Publikováno v:
ISPASS
Due to the data and computation intensive nature of many popular data processing applications, e.g., deep neural networks (DNNs), a variety of accelerators have been proposed to improve performance and energy efficiency. As a result, computing system
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::21b53bea8bd455a26065aaf7daebc436
https://doi.org/10.1109/ispass51385.2021.00042
https://doi.org/10.1109/ispass51385.2021.00042