A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2012; you can also visit the original URL.
The file type is application/pdf.
Filters
Finite Field Arithmetic for Cryptography
2010
IEEE Circuits and Systems Magazine
Preserved Fulltext
We present different architectures, methods and techniques for fast execution of cryptographic operations as well as high utilization of resources in the realization of cryptographic algorithms. ...
as finite multiplicative groups, rings, and finite fields. ...
An efficient way to accelerate inversion operation is to apply a technique known as multibit shifting as described in both [16] and [45] . Algorithm D terminates when v 5 0 and u 5 1. ...
doi:10.1109/mcas.2010.936785
fatcat:y6ya7xmjk5doznqj5lxxrnodoe
A 4-GHz effective sample rate integrated test core for analog and mixed-signal circuits
2002
IEEE Journal of Solid-State Circuits
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2005; you can also visit the original URL.
The file type is application/pdf.
High-frequency narrow-band signals (extending into the gigahertz range) have been captured through subsampling and the use of a high-bandwidth front-end sampling network. ...
Similarly, circuit phenomena that are broadband in nature were measured by using a delayed-clock subsampling mechanism in which the digitizer sample clock is consistently delayed over multiple runs of ...
This is an important limitation of our technique, and it means that test time per device might be slightly compromised, but that there is potential for improving overall test throughput (for multiple devices ...
doi:10.1109/4.991388
fatcat:w4m55qus2vbz3hgmg4n3feidtm
Mitigating Silent Data Corruptions in Integer Matrix Products: Toward Reliable Multimedia Computing on Unreliable Hardware
2017
IEEE transactions on circuits and systems for video technology (Print)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
An experimental investigation of voltage-scaled integer GEMM computations for visual descriptor matching within state-of-theart image and video retrieval algorithms running on an Intel i7-4578U 3GHz processor ...
The generic matrix multiply (GEMM) routine comprises the compute and memory-intensive part of many information retrieval, machine learning and object recognition systems that process integer inputs. ...
be corrected without using triple modular redundancy (TMR) [23] . ...
doi:10.1109/tcsvt.2016.2589622
fatcat:bfv3k7l4uja3rjg6dtytfvi6f4
RNNFast: An Accelerator for Recurrent Neural Networks Using Domain Wall Memory
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The basic hardware primitive, the RNN processing element (PE) includes custom DWM-based multiplication, sigmoid and tanh units for high density and low-energy. ...
We show that DWM is very well suited for RNN acceleration due to its very high density and low read/write energy. ...
RNNFast offers a much more scalable design relative to a GPU due to its modular design and very high storage density of DWM. ...
arXiv:1812.07609v1
fatcat:2x2b3iqahrffrma5lc2ut2ivi4
Logic Synthesis
[chapter]
2017
Electronic Design Automation for IC Implementation, Circuit Design, and Process Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
So, designers have increased the use of dynamic power minimization techniques. ere has been signi cant development in industry and academia on register clumping and swapping of multibit ops to reduce the ...
Yim and C. M. Kyung, Data path layout optimization using genetic algorithm and simulated annealing, IEEE Proceedings of Computers and Digital Techniques, 145(2):135-141, 1998. 33. T. T. Ye and G. ...
doi:10.1201/9781315215112-13
fatcat:me52zpnxyfcczh3choo2p4zulm
Toward Scalable Systems for Big Data Analytics: A Technology Tutorial
2014
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
., health care and scientific sensors, user-generated data, Internet and financial companies, and supply chain systems) over the past two decades. ...
Because of the high expenditure of a single large capacity disk, disk arrays assemble a number of disks to achieve large capacity, high access throughput, and high availability at much lower costs. • Storage ...
In text clustering, documents can appear in multiple subtopics. Some clustering algorithms from the data mining community are commonly used to calculate similarity. ...
doi:10.1109/access.2014.2332453
fatcat:6unxlocbmnhs7mfctlvphdyqtu
In-Memory Acceleration for General Data Parallel Applications
2022
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
General purpose processors and accelerators including system-on-a-chip and graphics processing units are composed of three principal components: processor, memory, and interconnection of these two. ...
PIM moves compute logic near the memory, and thereby reduces data movement. ...
We use Bottom-Up Greedy (BUG) [59] as the baseline scheduling algorithm, and linear scan register allocation as the baseline resource allocation algorithm. ...
doi:10.7302/4538
fatcat:alevj7ibbfe6tivzjyai4uqjt4
System-Specialized and Hybrid Approaches to Network Packet Classification
[article]
2020
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Further important system traits are dynamic updateability and high expressiveness in terms of rule set semantics. ...
The contributions in the domain of classification algorithms are Jit Vector Search (JVS) and the SFL system. ...
Second, we show that existing algorithms which support high update rates fall short in terms of throughput. ...
doi:10.18452/21780
fatcat:dmd3vhhuvvb3lownkqil7dfwl4
2022 roadmap on neuromorphic computing and engineering
2022
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. ...
This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. ...
Acknowledgements The design and construction of the SpiNNaker machine was supported by EPSRC (the UK Engineering and Physical Sciences Research Council) under Grants EP/D07908X/1 and EP/G015740/1. ...
doi:10.3929/ethz-b-000529282
fatcat:x5s5lalqqbbn7fb6gmpqmbqkxu
2022 roadmap on neuromorphic computing and engineering
2022
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. ...
This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. ...
Acknowledgements The design and construction of the SpiNNaker machine was supported by EPSRC (the UK Engineering and Physical Sciences Research Council) under Grants EP/D07908X/1 and EP/G015740/1. ...
doi:10.5167/uzh-231198
fatcat:oiskfbnlhrf7zfh35knmjxj4ae