M
Marc D. Riedel
Researcher at University of Minnesota
Publications - 100
Citations - 2674
Marc D. Riedel is an academic researcher from University of Minnesota. The author has contributed to research in topics: Stochastic computing & Combinational logic. The author has an hindex of 27, co-authored 95 publications receiving 2279 citations. Previous affiliations of Marc D. Riedel include Institut Français & François Rabelais University.
Papers
More filters
Journal ArticleDOI
An Architecture for Fault-Tolerant Computation with Stochastic Logic
TL;DR: The concept of stochastic logic is applied to a reconfigurable architecture that implements processing operations on a datapath and it is found to be much more tolerant of soft errors than conventional hardware implementations.
Journal ArticleDOI
Computation on Stochastic Bit Streams Digital Image Processing Case Studies
TL;DR: This paper introduces new SCEs based on finite-state machines based on FSMs for the task of digital image processing and compares the error tolerance, hardware area, and latency of stochastic implementations to those of conventional deterministic implementations using binary radix encoding.
Proceedings ArticleDOI
The synthesis of robust polynomial arithmetic with stochastic logic
Weikang Qian,Marc D. Riedel +1 more
TL;DR: This paper presents a general methodology for synthesizing stochastic logic for the computation of polynomial arithmetic functions, a category that is important for applications such as digital signal processing.
Proceedings ArticleDOI
A deterministic approach to stochastic computation
Devon Jenson,Marc D. Riedel +1 more
TL;DR: It is shown that randomness is not a requirement for this computational paradigm, and three deterministic methods are presented: relatively prime stream lengths, rotation, and clock division.
Journal ArticleDOI
Logical Computation on Stochastic Bit Streams with Linear Finite-State Machines
TL;DR: This paper provides a rigorous mathematical treatment of stochastic implementation of complex functions such as exponentiation and tanh implemented using linear FSMs, and presents two new functions, an absolute value function and exponentiation based on anabsolute value, motivated by specific applications.