Improved interval-based characterization of fixed-point LTI systems with feedback loops

JA López, C Carreras… - IEEE Transactions on …, 2007‏ - ieeexplore.ieee.org
Traditional approaches for fixed-point characterization are based on long simulations or
additive noise models that do not show the nonlinear behavior of the quantization …

Fast and accurate computation of the round-off noise of linear time-invariant systems

JA López, G Caffarena, C Carreras… - IET Circuits, Devices & …, 2008‏ - IET
From its introduction in the last decade, affine arithmetic (AA) has shown beneficial
properties to speed up the time of computation procedures in a wide variety of areas. In the …

Optimization of imprecise circuits represented by Taylor series and real-valued polynomials

Y Pang, K Radecka, Z Zilic - IEEE Transactions on Computer …, 2010‏ - ieeexplore.ieee.org
Arithmetic circuits in general do not match specifications exactly, leading to different
implementations within allowed imprecision. We present a technique to search for the least …

Evaluation of static analysis techniques for fixed-point precision optimization

J Cong, K Gururaj, B Liu, C Liu, Z Zhang… - 2009 17th IEEE …, 2009‏ - ieeexplore.ieee.org
Precision analysis and optimization is very important when transforming a floating-point
algorithm into fixed-point hardware implementations. The core analysis techniques are …

[PDF][PDF] Fixed-point refinement of digital signal processing systems

D Menard, G Caffarena, JA Lopez, D Novo… - … Mixed Signal Systems, 2019‏ - inria.hal.science
For the digital signal processing (DSP) part of mixed-signal systems, fixed-point arithmetic is
favoured due to its high efficiency in terms of implementation cost, namely energy …

Automated range and precision bit-width allocation for iterative computations

AB Kinsman, N Nicolici - IEEE Transactions on Computer-Aided …, 2011‏ - ieeexplore.ieee.org
As scientific computing becomes more widespread in environments where form-factor
considerations necessitate hardware acceleration, the problem of selecting numerical data …

Symbolic noise analysis approach to computational hardware optimization

A Ahmadi, M Zwolinski - Proceedings of the 45th annual Design …, 2008‏ - dl.acm.org
This paper addresses the problem of computational error modeling and analysis. Choosing
different word-lengths for each functional unit in hardware implementations of numerical …

An Overflow/Underflow-Free Fixed-Point Bit-Width Optimization Method for OS-ELM Digital Circuit

M Tsukada, H Matsutani - IEICE Transactions on Fundamentals of …, 2022‏ - search.ieice.org
Currently there has been increasing demand for real-time training on resource-limited IoT
devices such as smart sensors, which realizes standalone online adaptation for streaming …

Finite-precision error modeling using affine arithmetic

S Vakili, JMP Langlois, G Bois - 2013 IEEE International …, 2013‏ - ieeexplore.ieee.org
This paper introduces a new approach for finite-precision error modeling based on affine
arithmetic. The paper demonstrates that there is a common hazard in affine arithmetic-based …

Automatic design space exploration for an error tolerant application

S Coward, T Drane, Y Harel - 2020 IEEE 27th Symposium on …, 2020‏ - ieeexplore.ieee.org
Creating optimized hardware for error tolerant applications presents significant challenges
as well as opportunities. Many algorithms in computer graphics & vision are error tolerant, as …