Zobrazeno 1 - 10
of 219
pro vyhledávání: '"Milos D. Ercegovac"'
Autor:
Tooba Arifeen, Saeid Gorgin, Mohammad Hosein Gholamrezaei, Abdus Sami Hassan, Milos̆ D. Ercegovac, Jeong-A Lee
Publikováno v:
Journal of Signal Processing Systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::061b6ec5d744627516f35963541e21af
https://doi.org/10.1007/s11265-023-01866-8
https://doi.org/10.1007/s11265-023-01866-8
Autor:
Miloš D. Ercegovac, Tomás Lang
Digital arithmetic plays an important role in the design of general-purpose digital processors and of embedded systems for signal processing, graphics, and communications. In spite of a mature body of knowledge in digital arithmetic, each new generat
Publikováno v:
2021 55th Asilomar Conference on Signals, Systems, and Computers.
We present a pipelined multiplier with reduced activities and minimized interconnect based on online digit-serial arithmetic. The working precision has been truncated such that $p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::169c41a41a27a04c3aceb3a660cb3118
https://doi.org/10.1109/ieeeconf53345.2021.9723215
https://doi.org/10.1109/ieeeconf53345.2021.9723215
Publikováno v:
2021 55th Asilomar Conference on Signals, Systems, and Computers.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::412e7849a4cf7f2f76b0db3b67830d90
https://doi.org/10.1109/ieeeconf53345.2021.9723236
https://doi.org/10.1109/ieeeconf53345.2021.9723236
Autor:
Milos D. Ercegovac
Publikováno v:
ACSSC
Online and left-to-right arithmetic process operands and results digit-serially, most significant digit first. An online operation needs only a small number of input digits to begin producing the result digits. This property allows overlap between su
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a0a04adee16e6ede600aacce8660fc74
https://doi.org/10.1109/ieeeconf51394.2020.9443576
https://doi.org/10.1109/ieeeconf51394.2020.9443576
Publikováno v:
ACSSC
This paper shows the details of an implementation of variable radix floating-point complex division based on previous implementations of the algorithm. This implementation takes advantage of the easier prescaling offered by low-radix division and rec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eafd1f13263ab8c7658fbeb90f2d6dba
https://doi.org/10.1109/ieeeconf51394.2020.9443498
https://doi.org/10.1109/ieeeconf51394.2020.9443498
Autor:
Milos D. Ercegovac, Wen Yan
Publikováno v:
2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP).
An energy efficient truncated inner product unit is proposed in this paper. The proposed unit is pipelined and processes the $m$ pairs of n-bit operands in serial, so that only one unit is required and it can be reused in each recurrence. Truncated i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::be4b6956bf993468f12d33616df9dd79
https://doi.org/10.1109/icsidp47821.2019.9173061
https://doi.org/10.1109/icsidp47821.2019.9173061
Autor:
James E. Stine, Milos D. Ercegovac
Publikováno v:
ACSSC
This paper discusses digit-recurrence division with operand scaling focusing on its implementation for energy and delay. The implementations with are compared with implementations without scaling and with multiplicative division methods. Results demo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d3e97d2b2508d3befb72938bacf7b25
https://doi.org/10.1109/ieeeconf44664.2019.9049049
https://doi.org/10.1109/ieeeconf44664.2019.9049049
Publikováno v:
IEEE Transactions on Computers. 63:2948-2960
This paper presents a new scheme for evaluating complex reciprocal and exponential functions in hardware. The proposed method utilizes a two-dimensional convolution algorithm to interpolate bivariate functions from tabulated function values in the co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::00d50cb38ac9df880b2e57cf1f42f611
https://doi.org/10.1109/tc.2013.181
https://doi.org/10.1109/tc.2013.181
Publikováno v:
IEEE Transactions on Circuits and Systems II: Express Briefs. 61:711-715
Linear (order-1) function evaluation schemes, such as bipartite and multipartite tables, are usually effective for low- precision approximations. For high-output precision, the lookup table size is often too large for practical use. This brief invest
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9a866cd6a8fda2ddc1fb4d306d3120a6
https://doi.org/10.1109/tcsii.2014.2331094
https://doi.org/10.1109/tcsii.2014.2331094