Dynamic programming implementation on array processor architectures

Dynamic Programming (DP) applies to many signal and image processing applications including boundary following, the Viterbi algorithm, dynamic time warping, etc. This paper presents an array processor implementation of generic dynamic programming. Our architecture is a SIMD array attached to a host computer. The processing element of the architecture is based on an ASIC design opting for maximum speed-up. By adopting a torus interconnection network, a dual buffer structure, and a multilevel pipeline, the performance of the DP chip is expected to reach the order of several GOPS. The paper discusses both the dedicated hardware design and the data flow control of the DP chip and the total array.This work was supported in part by the NATO, Scientific and Environmental Affairs Division, Collaborative Research Grant SA.5-2-05(CRG.960201)424/96/JARC-501.     

An experimental study on the pumping performance of molecular drag pumps

The pumping performance of molecular drag pumps (MDP) has been investigated experimentally. The experimented MDPs are a disk-type drag pump (DTDP), helical-type drag pump (HTDP) and compound drag pump (CDP), respectively. In the case of the DTDP, spiral channels of a rotor are cut on both upper surface and lower surface of a rotating disk, and the corresponding stator is a planar disk. In the case of the HTDP, the rotor has six rectangular grooves. The CDP consists with the DTDP, at lower part, and with the HTDP, at upper part. The experiments are performed in the outlet pressure range of 0.2–533 Pa. The inlet pressure and compression ratio are measured under the various conditions of outlet pressure and throughputs, and nitrogen is used for the test gas. At the outlet pressure of 0.2 Pa, the ultimate pressure has been reached to 1.0 × 10⁻² Pa for the HTDP, 1.3 × 10⁻⁴ Pa for the DTDP, and 3.6 × 10⁻⁵ Pa for the CDP. The maximum compression ratio of the CDP is much higher than those of the DTDP or HTDP. Consequently, the ultimate pressure of the CDP is the lowest one.     

A precision on-line model for the prediction of roll force and roll power in hot-strip rolling

Investigated via a series of finite-element (FE) process simulations is the effect of diverse process variables on some selected nondimensional parameters characterizing the thermomechanical behavior of the strip in hot-strip rolling. Then, on the basis of these parameters an on-line model is derived for the precise prediction of roll force and roll power. The prediction accuracy of the proposed model is examined through comparison with predictions from a FE process model and also with measurements.     

Planar-shape prototype generation using a tree-based random greedy algorithm.

A prototype is representative of a set of similar objects. This paper proposes an approach that formulates the problem of prototype generation as finding the mean from a given set of objects, where the prototype solution must satisfy certain constraints. These constraints describe the important perceptual features of the sample shapes that the proposed prototype must retain. The contour prototype generated from a set of planar objects was used as an example of the approach, and the corners were used as the perceptual features to be preserved in the proposed prototype shape. However, finding a prototype solution for more than two contours is computationally intractable. A tree-based approach is therefore proposed in which an efficient greedy random algorithm is used to obtain a good approximation of the proposed prototype and analyze the expected complexity of the algorithm. The proposed prototype-generation process for hand-drawn patterns is described and discussed in this paper.     

Chemical vapor deposition of amorphous ruthenium-phosphorus alloy films

Chemical vapor deposition growth of amorphous ruthenium-phosphorus films on SiO₂ containing ∼ 15% phosphorus is reported. cis-Ruthenium(II)dihydridotetrakis-(trimethylphosphine), cis-RuH₂(PMe₃)₄ (Me = CH₃) was used at growth temperatures ranging from 525 to 575 K. Both Ru and P are zero-valent. The films are metastable, becoming increasingly more polycrystalline upon annealing to 775 and 975 K. Surface studies illustrate that demethylation is quite efficient near 560 K. Precursor adsorption at 135 K or 210 K and heating reveal the precursor undergoes a complex decomposition process in which the hydride and trimethylphosphine ligands are lost at temperatures as low at 280 K. Phosphorus and its manner of incorporation appear responsible for the amorphous-like character. Molecular dynamics simulations are presented to suggest the local structure in the films and the causes for phosphorus stabilizing the amorphous phase.     

VLSI architectural design tradeoffs for sliding-window log-MAP decoders

Turbo codes have received tremendous attention and have commenced their practical applications due to their excellent error-correcting capability. Investigation of efficient iterative decoder realizations is of particular interest because the underlying soft-input soft-output decoding algorithms usually lead to highly complicated implementation. This paper describes the architectural design and analysis of sliding-window (SW) Log-MAP decoders in terms of a set of predetermined parameters. The derived mathematical representations can be applied to construct a variety of VLSI architectures for different applications. Based on our development, a SW-Log-MAP decoder complying with the specification of third-generation mobile radio systems is realized to demonstrate the performance tradeoffs among latency, average decoding rate, area/computation complexity, and memory power consumption. This paper thus provides useful and general information on practical implementation of SW-Log-MAP decoders.     

Study of warpage due to P-V-T-C relation of EMC in IC packaging

There were many studies about the prediction of warpage due to thermal mismatch , . However, cure induced warpage is usually ignored and the results can be inaccurate. To minimize this problem, a thorough understanding of epoxy molding compound (EMC) with pressure-volume-temperature-cure (P-V-T-C) relation is necessary. This paper used the P-V-T-C relation of an encapsulation material to formulate the stress-strain relationship. With the help of finite element method (FEM) and mold flow analysis, warpage predictions combined with P-V-T-C relation were performed and the results show that this approach is practical. For a given P-V-T-C relation, the shrinkage direction is pointing toward the gate and maximum warpage usually occurs at the boundary of an integrated circuit (IC) package. Variation of specific volume difference along the flow direction is larger than that perpendicular to the flow direction. When temperature difference is small in thickness direction, specific volume difference in thickness direction varies only slightly.     

Plastic deformation in a multifunctional Ti-Nb-Ta-Zr-O alloy

Mechanisms for plastic deformation in the newly developed Ti-24 at. pct (Ta + Nb + V)-(Zr,Hf)-O alloys (Gum Metal) were investigated in relation to their unique properties. Transmission electron microscopy revealed that the microstructure after deformation was characterized by highly distorted crystal images, which are accompanied by numerous “giant faults.” Such plastic behavior implies that a large amount of elastic stain energy was stored discretely and hierarchically during cold working. Calculated elastic constants of the Ti-X (Nb,Ta,Mo,V) binary systems predicted that Young’s modulus in 〈001〉 and shear moduli along some directions including slip systems in a bcc crystal were extraordinary small. The low modulus not only well explains the highly distorted microstructure observed in the cold-worked specimens, but also signifies that ideal shear strength of the developed alloys is a very small value, which is close to the practical strength required for plastic deformation in the alloy. This implies that the giant faults observed in the deformed specimen were formed without the aid of dislocation glide.     

On Striping Traffic over Multiple IEEE 802.11(b) Wireless Channels

Due to interference, path loss, multipath fading, background noise, and many other factors, wireless communication normally cannot provide a wireless link with both a high data rate and a long transmission range. To address this problem, striping network traffic in parallel over multiple lower-data-rate but longer-transmission-range wireless channels may be used. In this paper, we propose a new striping method and evaluate its performances over multiple IEEE 802.11(b) channels under various conditions. Our extensive simulation results show that this method is quite effective for such an application. S.Y. Wang is an Associate Professor of the Department of Computer Science and Information Engineering at National Chiao Tung University, Taiwan. He received his Master and Ph.D. degree in computer science from Harvard University in 1997 and 1999, respectively. His research interests include wireless networks, Internet technologies, network simulations, and operating systems. He is the author of the NCTUns 2.0 network simulator and emulator, which is being widely used by network and communication researchers. More information about the tool is available at http://NSL.csie.nctu.edu.tw/nctuns.html. C.H. Hwang received his master degree in computer science from NCTU in 2002 and currently is working for a network company. C.L. Chou currently is a third-year Ph.D. student at the Department of Computer Science and Information Engineering, National Chiao TungUniversity (NCTU), Taiwan. He received his master degree in computer science from NCTU in 2002.