A Regular VLSI Array for an Irregular Algorithm
نویسندگان
چکیده
We present an application specific, asynchronous VLSI processor array for the dynamic programming algorithm for the 0/1 knapsack problem. The array is derived systematically, using correctnesspreserving transformations, in two steps: the standard (dense) algorithm is first transformed into an irregular (sparse) functional program which has better efficiency. This program is then implemented as a modular VLSI architecture with nearest neighbor connections. Proving bounds on buffer sizes yields a linear array of identical asynchronous processors, each with simple computational logic and a pair of fixed size FIFOs. A modular solution can be obtained by additional load-time control, enabling the processors to pool their buffers.
منابع مشابه
AREA AND ENERGY EFFICIENT VLSI ARCHITECTURES FOR LOW-DENSITY PARITY-CHECK DECODERS USING AN ON-THE-FLY COMPUTATION A Dissertation by KIRAN
Area and Energy Efficient VLSI Architectures for Low -Density Parity-Check Decoders Using an On-the-Fly Computation. (December 2006) Kiran Kumar Gunnam, M.S., Texas A&M University Co-Chairs of Advisory Committee: Dr. Gwan Choi Dr. Scott Miller The VLSI implementation complexity of a low density parity check (LDPC) decoder is largely influenced by the interconnect and the storage requirements. T...
متن کاملA New Vlsi Architecture for 2-d Dst Transform of Prime Length
Using a recently proposed VLSI algorithm for 2-D discrete sine transform (DST) an efficient VLSI architecture is proposed. This VLSI architecture has a modular and regular hardware structure and can compute in parallel thus resulting in high speed performances. The proposed architecture has been obtained by mapping the VLSI algorithm into two linear systolic arrays and combining them into a sin...
متن کاملA Vlsi Algorithm for the Hardware Implementation of 1-d Discrete Sine Transform Based on a Pseudo-band Correlation Structure
Abstract. Using a novel input restructuring sequence and appropriate index-mapping techniques a new VLSI algorithm for a prime-length DST is presented. The proposed algorithm uses a modular and regular computational structure, called pseudo-band correlation structure, well adapted to the VLSI implementation of 1-D DST, thus resulting an efficient VLSI implementation. The proposed algorithm can ...
متن کاملAn Irregular Lattice Pore Network Model Construction Algorithm
Pore network modeling uses a network of pores connected by throats to model the void space of a porous medium and tries to predict its various characteristics during multiphase flow of various fluids. In most cases, a non-realistic regular lattice of pores is used to model the characteristics of a porous medium. Although some methodologies for extracting geologically realistic irregular net...
متن کاملVLSI Array Architectures for Pyramid Vector QuantizationBongjin
We present parallel algorithms and array architectures for pyramid vector quantization (PVQ) 3] for use in image coding in low-power wireless systems. Both encoding and decoding algorithms have data-dependent iteration bounds and data-dependent dependencies which prevent eecient parallelization of the algorithms. We perform an algorithmic transformation 4] to convert data-dependent regular algo...
متن کامل