Search-based wordlength optimization for VLSI/DSP synthesis

Choi, Hyun-Jun; Burleson, Wayne

doi:10.1109/vlsisp.1994.574744

Cited by 41 publications

(43 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once vector s and matrix M are available, expression (22) can be used during the optimization process to assess the system quality. Many optimization techniques can be applied to the problem of finding the appropriate word-lengths.…”

Section: Compute Eqns (23-25) Using the Previously Collectedmentioning

confidence: 99%

“…Many optimization techniques can be applied to the problem of finding the appropriate word-lengths. Here, we present a gradient-descent optimization [22] that provides a trade-off between low complexity and optimality. Its behavior is described using pseudo-code in Algorithm 1.…”

Section: Compute Eqns (23-25) Using the Previously Collectedmentioning

confidence: 99%

“…Regarding the cost function, some authors use area [22,2,23,21], others the error itself [24] and others a linear combination of both [25]. The reader can extend the information on FPO techniques consulting [26,24,27, 28].…”

Section: Compute Eqns (23-25) Using the Previously Collectedmentioning

confidence: 99%

See 2 more Smart Citations

Fast Fixed-Point Optimization of DSP Algorithms

Caffarena

Carreras

López

et al. 2012

VLSI-SoC: Forward-Looking Trends in IC and Systems Design

View full text Add to dashboard Cite

Abstract. In this chapter, the fast fixed-point optimization of Digital Signal Processing (DSP) algorithms is addressed. A fast quantization noise estimator is presented. The estimator enables a significant reduction in the computation time required to perform complex fixed-point optimizations, while providing a high accuracy. Also, a methodology to perform fixed-point optimization is developed.Affine Arithmetic (AA) is used to provide a fast Signal-to-Quantization Noise-Ratio (SQNR) estimation that can be used during the fixed-point optimization stage. The fast estimator covers differentiable non-linear algorithms with and without feedbacks. The estimation is based on the parameterization of the statistical properties of the noise at the output of fixed-point algorithms. This parameterization allows relating the fixedpoint formats of the signals to the output noise distribution by means of fast matrix operations. Thus, a fast estimation is achieved and the computation time of the fixed-point optimization process is significantly reduced.The proposed estimator and the fixed-point optimization methodology are tested using a subset of non-linear algorithms, such as vector operations, IIR filter for mean power computation, adaptive filters -for both linear and non-linear system identification -and a channel equalizer. The computation time of fixed-point optimization is boosted by three orders of magnitude while keeping the average estimation error down to 6% in most cases.

show abstract

Section: Compute Eqns (23-25) Using the Previously Collectedmentioning

confidence: 99%

Section: Compute Eqns (23-25) Using the Previously Collectedmentioning

confidence: 99%

See 1 more Smart Citation

Fast Fixed-Point Optimization of DSP Algorithms

Caffarena

Carreras

López

et al. 2012

VLSI-SoC: Forward-Looking Trends in IC and Systems Design

View full text Add to dashboard Cite

show abstract

“…Sung & Kum [13], Han & al. [14], Choi and Burleson [15] and Fiore and Lee [16] proposed manual procedures and guidelines to optimize the FWL. These procedures and guidelines that use a search-based methodology are now examined.…”

Section: Related Workmentioning

confidence: 99%

An automatic word length determination method

Cantin

Savaria

Prodanos

et al.

ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196)

View full text Add to dashboard Cite

-Automatic word length determination of hardware data paths may require considering several error models, user specifications and hardware costs. A new automatic method for determining the word length of hardware data paths that consider these requirements is proposed and analyzed. The search-based method uses a C/C++ fixed-point simulation tool to model the impact of finite word lengths on overall accuracy. By computing dissimilarities between fixed-point and floating-point simulation results, a procedure searches for a combination of word lengths that meets accuracy criteria specified by the designer. This method is presented with four novel maximization procedures. These four automatic procedures are compared with other procedures given in the literature and adapted into the method. The comparison helps to select a procedure that finds a combination of word lengths that meet user specifications, in a small number of iterations. The procedures are characterized and compared using a dozen DSP algorithms.

show abstract

“…Finally, few are the works [GML04, LGC + 06, CCL03b, Con03, SR13] that measure the impact of quantization on latency and delay, and to the best of our knowledge only [CB94,CC10a] have used this metric as minimization objective.…”

Section: Optimization Objectivesmentioning

confidence: 99%

Automated wordlength optimization framework for multi-source statistical interval-based analysis of nonlinear systems with control-flow structures

Algarabel¹

View full text Add to dashboard Cite

Search-based wordlength optimization for VLSI/DSP synthesis

Cited by 41 publications

References 9 publications

Fast Fixed-Point Optimization of DSP Algorithms

Fast Fixed-Point Optimization of DSP Algorithms

An automatic word length determination method

Automated wordlength optimization framework for multi-source statistical interval-based analysis of nonlinear systems with control-flow structures

Contact Info

Product

Resources

About