Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Uri Weiser"'
Publikováno v:
IEEE Computer Architecture Letters. 22:49-52
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0e1ec2c2e8f88487a03d33ab75d57e9a
https://doi.org/10.1109/lca.2023.3275909
https://doi.org/10.1109/lca.2023.3275909
Publikováno v:
ACM Transactions on Architecture and Code Optimization. 16:1-27
Memory prefetchers are designed to identify and prefetch specific access patterns, including spatiotemporal locality (e.g., strides, streams), recurring patterns (e.g., varying strides, temporal correlation), and specific irregular patterns (e.g., po
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd59c9ac4a3387cebda19d7fd7e81aa4
https://doi.org/10.1145/3345000
https://doi.org/10.1145/3345000
Publikováno v:
IEEE Computer Architecture Letters. 18:99-102
Systolic arrays (SAs) are highly parallel pipelined structures capable of executing various tasks such as matrix multiplication and convolution. They comprise a grid of usually homogeneous processing units (PUs) that are responsible for the multiply-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::31251bcecac695e45dd546299374509c
https://doi.org/10.1109/lca.2019.2924007
https://doi.org/10.1109/lca.2019.2924007
Autor:
Uri Weiser, Gil Shomron
Publikováno v:
MICRO
Deep neural networks (DNNs) are known for their inability to utilize underlying hardware resources due to hardware susceptibility to sparse activations and weights. Even in finer granularities, many of the non-zero values hold a portion of zero-value
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::082bdb732349401bdb70f0a41ed22d58
http://arxiv.org/abs/2004.09309
http://arxiv.org/abs/2004.09309
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030586065
ECCV (10)
ECCV (10)
Convolutional neural networks (CNNs) introduce state-of-the-art results for various tasks with the price of high computational demands. Inspired by the observation that spatial correlation exists in CNN output feature maps (ofms), we propose a method
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3a832064b8de5fb6d2a1767eb596015c
https://doi.org/10.1007/978-3-030-58607-2_14
https://doi.org/10.1007/978-3-030-58607-2_14
Publikováno v:
IEEE Computer Architecture Letters. 16:141-144
Hardwired dynamic NAND address decoders are widely used in random access memories to decode parts of the address. Replacing wires by resistive elements allows storing and reprogramming the addresses and matching them to an input address. The resistiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::20f5c1c88de172e1ff677af49ddec6fb
https://doi.org/10.1109/lca.2017.2670539
https://doi.org/10.1109/lca.2017.2670539
Publikováno v:
IEEE Computer Architecture Letters. 16:68-71
Memory hierarchies in modern computing systems work well for workloads that exhibit temporal data locality. Data that is accessed frequently is brought closer to the computing cores, allowing faster access times, higher bandwidth, and reduced transmi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7a5606ce0e3e28c0be8e6e55a22b99d8
https://doi.org/10.1109/lca.2016.2520927
https://doi.org/10.1109/lca.2016.2520927
Publikováno v:
Computer. 49:47-55
By scheduling each workload according to its most advantageous core and managing voltage and frequency, the heterogeneous energy-aware race to halt (H-EARtH) algorithm optimizes CPU platform energy.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d5c95f1c6b01835d1d3e059761e72235
https://doi.org/10.1109/mc.2016.309
https://doi.org/10.1109/mc.2016.309
Publikováno v:
Journal of Parallel and Distributed Computing. 95:3-14
Additional transistors available in each process generation are used to increase the number of cores on chip. This trend results in high execution unit performance relative to other available resources, such as memory bandwidth, I/O bandwidth, and po
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d10bc4d21667210555f1619899dfa85
https://doi.org/10.1016/j.jpdc.2016.03.007
https://doi.org/10.1016/j.jpdc.2016.03.007
Autor:
Uri Weiser
Publikováno v:
IEEE Micro. 37:126-128
Uri Weiser, recipient of the 2016 ACM-IEEE Computer Society Eckert-Mauchly Award, shares insights from his career of nearly 40 years in the computer architecture field.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::37b3be9cca96418690114dac41bcbcdc
https://doi.org/10.1109/mm.2017.73
https://doi.org/10.1109/mm.2017.73