The algorithm-based fault tolerance (ABFT) provides low-cost error protection for VLSI processor arrays used in real-time digital signalprocessing. Several ABFT techniques (weighted check-sum) have be proposed to des...
详细信息
ISBN:
(纸本)081940943X
The algorithm-based fault tolerance (ABFT) provides low-cost error protection for VLSI processor arrays used in real-time digital signalprocessing. Several ABFT techniques (weighted check-sum) have be proposed to design fault-tolerant LU decomposition, QR decomposition, and matrix inversion. In these schemes, encoding/decoding uses either multiplication or division so that overhead is high. In this paper, we propose new encoding/decoding methods for designing fault-tolerant matrix operations. Since the new encoding/decoding methods use only additions and subtractions, the overhead of a fault-tolerant processor array can be drastically reduced.
A new derivation of the QR-based fast recursive least squares algorithms for Toeplitz matrices is presented. algorithms for computing Q and R in the QR decomposition of the data matrix are proposed. These algorithms c...
详细信息
ISBN:
(纸本)0819406945
A new derivation of the QR-based fast recursive least squares algorithms for Toeplitz matrices is presented. algorithms for computing Q and R in the QR decomposition of the data matrix are proposed. These algorithms can be efficiently incorporated with the fast recursive least squares algorithm and can be performed only when they are needed.
Central to `multimedia' image processing is the desire to encode computer graphics data into a standard television signal, complete with line, field, and color subcarrier synchronizing information. The numerous in...
详细信息
ISBN:
(纸本)081940943X
Central to `multimedia' image processing is the desire to encode computer graphics data into a standard television signal, complete with line, field, and color subcarrier synchronizing information. The numerous incompatibilities between television and computer display standards render this operation far less trivial than it sounds to anyone who hasn't worked with both types of signals. To simplify the task of encoding computer graphics signals into standard NTSC (North America and Japan) or PAL (most of Europe) television format for display, broadcast, or recording, TRW LSI Products Inc. has introduced the two newest members of it multimedia integrated circuit family, the TMC22090 and TMC22190 digital video encoders.
We formulate in a simple fashion the concept of invariance for a linear system. We show that one must define what we call an "associated Hermitian operator"' which commutes with the system function. We s...
详细信息
ISBN:
(纸本)9780819468451
We formulate in a simple fashion the concept of invariance for a linear system. We show that one must define what we call an "associated Hermitian operator"' which commutes with the system function. We show that it is this Hermitian operator that defines the invariance and also determines the appropriate transform and other connections between input and output relations.
The NRL FLEX processor architecture is designed for real-time radar signalprocessing and was described at last year's conference in the context of its original application, the Point Defense Demonstration Radar p...
详细信息
ISBN:
(纸本)081940943X
The NRL FLEX processor architecture is designed for real-time radar signalprocessing and was described at last year's conference in the context of its original application, the Point Defense Demonstration Radar project at NRL. This paper describes the current status of the processor and the application of the same architecture to a new problem which requires a different board configuration to satisfy a different set of latency and data flow requirements.
We calculate the instantaneous frequency at a fixed position of a propagating pulse in the asymptotic regime. We also discuss the multimode case and relate it to the concept of instantaneous bandwidth.
ISBN:
(纸本)0819425842
We calculate the instantaneous frequency at a fixed position of a propagating pulse in the asymptotic regime. We also discuss the multimode case and relate it to the concept of instantaneous bandwidth.
A robust focusing matrix, called unitary constrained array manifold focusing, is proposed for the coherent signal-subspace method which is a novel approach for direction finding of broad- band sources. The proposed fo...
详细信息
ISBN:
(纸本)081940943X
A robust focusing matrix, called unitary constrained array manifold focusing, is proposed for the coherent signal-subspace method which is a novel approach for direction finding of broad- band sources. The proposed focusing matrix has robustness against size variations of focusing sectors obtained by preliminary group angle estimates. To quantify information loss due to source focusing, a new measure, relative efficiency index, is introduced. This index is useful in assessing statistical sufficiency of a data-reduced statistic formed by source focusing. The sensitivity issue as well as estimation performance comparisons for various focusing schemes, based on simulations and relative efficiency index, are also presented.
Serra-Capizzano recently introduced anti-reflecting boundary conditions (AR-BC) for blurring models: the idea seems promising both from the computational and approximation viewpoint. The key point is that, under certa...
详细信息
ISBN:
(纸本)0819450782
Serra-Capizzano recently introduced anti-reflecting boundary conditions (AR-BC) for blurring models: the idea seems promising both from the computational and approximation viewpoint. The key point is that, under certain symmetry conditions, the AR-BC matrices can be essentially simultaneously diagonalized by the (fast) sine transform DST I and, moreover, a C-1 continuity at the border is guaranteed in the ID case. Here we give more details for the 2D case and we perform extensive numerical simulations which illustrate that the AR-BC, periodic and reflective BCs in certain applications. can be superior to Dirichlet.
This paper presents, Index Mapping, a technique to efficiently map a widely used class of digital signalprocessingalgorithms onto a space/time paradigm with immediate representation as the partitioning and schedulin...
详细信息
ISBN:
(纸本)0819425842
This paper presents, Index Mapping, a technique to efficiently map a widely used class of digital signalprocessingalgorithms onto a space/time paradigm with immediate representation as the partitioning and scheduling map of a small, I/O efficient, hardware array. When applied to reconfigurable FPGA based hardware architectures with downstream Sea-of-Gates optimization methods, the resulting systems form a dynamic signalprocessing environment with the best mix of performance and flexibility for wireless applications. Herein, Index Mapping is demonstrated with a mapping of the Fast Fourier Transform (FFT) onto an FPGA computing machine, the ReConfigurable Processor (RCP).
Implementing Jacobi algorithms in parallel VLSI processor arrays is a non-trivial task, in particular when the algorithms are parametrized with respect to size and the architectures are parametrized with respect to sp...
详细信息
ISBN:
(纸本)0819412767
Implementing Jacobi algorithms in parallel VLSI processor arrays is a non-trivial task, in particular when the algorithms are parametrized with respect to size and the architectures are parametrized with respect to space-time trade-offs. The paper is concerned with an approach to implement several time-adaptive Jacobi-type algorithms on a parallel processor array, using only Cordic arithmetic and asynchronous communications, such that any degree of parallelism, ranging from single-processor up to full-size array implementation, is supported by a `universal' processing unit. This result is attributed to a gracious interplay between algorithmic and architectural engineering.
暂无评论