A high‐performance sorting algorithm for multicore single‐instruction multiple‐data processors

Many sorting algorithms have been studied in the past, but there are only a few algorithms that can effectively exploit both single‐instruction multiple‐data (SIMD) instructions and thread‐level parallelism. In this paper, we propose a new high‐performance sorting algorithm, called aligned‐access sort (AA‐sort), that exploits both the SIMD instructions and thread‐level parallelism available on today's multicore processors. Our algorithm consists of two phases, an in‐core sorting phase and an out‐of‐core merging phase. The in‐core sorting phase uses our new sorting algorithm that extends combsort to exploit SIMD instructions. The out‐of‐core algorithm is based on mergesort with our novel vectorized merging algorithm. Both phases can take advantage of SIMD instructions. The key to high performance is eliminating unaligned memory accesses that would reduce the effectiveness of SIMD instructions in both phases. We implemented and evaluated the AA‐sort on PowerPC 970MP and Cell Broadband Engine platforms. In summary, a sequential version of the AA‐sort using SIMD instructions outperformed IBM's optimized sequential sorting library by 1.8 times and bitonic mergesort using SIMD instructions by 3.3 times on PowerPC 970MP when sorting 32 million random 32‐bit integers. Also, a parallel version of AA‐sort demonstrated better scalability with increasing numbers of cores than a parallel version of bitonic mergesort on both platforms. Copyright © 2011 John Wiley & Sons, Ltd.     

Fractional power approximation and its generation

For an analog simulating system, an approximating system is proposed. Its mathematical form is expressed by an algebraic equation:

$\text{? (x) ≈ α + β χ + γχ}{}^{\mathrm{k}}$

with four parameters given by real numbers. Their values can be determined so as to satisfy a best fit in a Chebyshev sense. Then, the accuracy is of the same order with that obtained by any kind of ordinary power series up to terms o f the third order. It is noticeable that a given function can be accurately approximated by this equation without destroying its uniform continuity.As its electronic system, it is possible to utilize forward current-voltage characteristics o f p-n diodes near their origins. Different functions can be produced by adjusting an amount o f ordinary resistances connected to diodes in series.     

Thermomechanical behavior of Ti-Ni shape memory alloy films deposited by DC magnetron sputtering

In this study, thermomechanical properties of titanium-nickel (Ti-Ni) shape memory alloy (SMA) films are investigated in order to derive constitutive relations. Ti-Ni SMA films, deposited by DC magnetron sputtering under controlled film composition, are characterized by uniaxial tensile tests. At room temperature (R.T.), Ti-Ni films having Ti contents less than 50 at% exhibit superelastic behavior, and those having Ti contents greater than 50 at% exhibit shape memory behavior. However, the Ni—53.2 at% Ti film fractured at a tensile strain of 0.8% because of an increase in brittleness with increasing Ti content. At elevated temperatures, Ti-Ni films having Ti contents of 50.2 to 52.6 at% undergo phase change from martensite to austenite. The Young's modulus of the Ti-Ni films depends on temperature at each phase, regardless of film composition. Film composition does, however, affect the measured material constants b_A, b_M, c_A, and c_M. Stress-strain curves calculated from the constructed constitutive equation closely agree with those obtained from tensile tests, for both the martensite and austenite phases. The constitutive equations are expected to find great utility in the design of Ti-Ni film-actuated microelectromechanical systems (MEMS).     

Optical pulse compression based on stationary rescaled pulse propagation in a comblike profiled fiber

In this paper, optical pulse compression using a comblike profiled fiber (CPF) is theoretically and experimentally studied, in which highly nonlinear fibers and single-mode fibers are alternately concatenated. Stationary rescaled pulse (SRP), is the main focus, which is a recently discovered nonlinear stationary pulse in CPF. The fundamental characteristics of SRP are investigated, and SRP propagation is applied to the design of the CPF pulse compressor. Using the proposed design method, the specifications of the CPF can easily be controlled, such as the compression ratio per step of the CPF or the pedestal of the output pulse. Two experimental results of pulse compression using the CPF based on the proposed design method are shown: 1) pulse compression with a large compression ratio per step of the CPF and 2) low-pedestal and wideband wavelength-tunable compression. A parametric noise-amplification phenomenon occurring in a compression process for an optical pulse sequence is also numerically analyzed.     

Preparation of ferroelectric Ba(Ti/sub 0.85/Sn/sub 0.15/)O/sub 3/ thin films by metal-organic decomposition

Ferroelectric Ba(Ti/sub 0.85/Sn/sub 0.15/)O/sub 3/ (BTS/sub 15/) thin film is newly prepared on the Pt/Ti/SiO/sub 2//Si substrate by metal-organic decomposition. The firing condition is determined by thermogravimetric and differential thermal analysis. The BTS/sub 15/ thin film with a flat surface and uniform thickness is obtained by spin coating in N/sub 2/ atmosphere that avoids moisture. The BTS/sub 15/ film has a perovskite phase and a preferential [110] texture. It is also found that the crystalline structure is cubic at 24/spl deg/C with a lattice constant of 4.01 /spl Aring/, and a grain size of about 30 nm was estimated by Scherrer equation and SEM image. From P-E hysteresis loop at 20/spl deg/C, the polarization at E=0 and the electric field at P=0 are found to be 1.07 /spl mu/C/cm/sup 2/ and 24.0 kV/cm, respectively. It is observed that the dielectric constant decreases monotonously from about 830 to 630 with increasing temperature ranging from 20/spl deg/C to 50/spl deg/C. Finally, it is found that the BTS/sub 15/ thin film shows a sufficient ferroelectricity and is an attractive material for functional ferroelectric devices, such as thermal-type infrared sensors.     

Inside Front Cover: Fabrication of Ideally Ordered Nanoporous Alumina Films and Integrated Alumina Nanotubule Arrays by High‐Field Anodization (Adv. Mater. 17/2005)

A simple, low‐cost approach to fabricating large‐area highly ordered nanoporous alumina films in sulfuric acid solutions through a single‐step high‐field anodization, without the assistance of any additional process, is reported on p. 2115 by Chu and co‐workers. The critical high anodizing potential in the adopted electrolyte system increases with the ageing of solutions after a long period of anodization. Correspondingly, the applicable current density for stable anodization rises significantly, thus leading to high‐speed film growth. Uniform porous anodic alumina films in sulfuric acid solutions under a high electric field of 40–70 V and 1600–2000 A m^–2 are achieved.     

Charge behavior in flowing oil in oil/ pressboard insulation system by electro-optic field measurement

The electrical insulation structure of most power transformers is a combination of insulating oil and solid materials. One of the crucial problems we face in transformer operation is flow electrification, which occurs at a flowing oil/solid material interface. Thus, for the transformer insulation design, we need to clarify the now electrification phenomena. In this paper, we measured the electric field strength in an oil/pressboard composite insulation system using an electro-optic method of the Kerr effect. We obtained the time variation of electric field distribution in both flowing uncharged and charged oil. It is notable that we could quantitatively clarify the electric field distortion in flowing charged oil by flow electrification. Furthermore, we measured the leakage current from divided electrodes and derived a charge density distribution along the flow direction. Finally, we quantitatively discussed the electric field distribution and the charge behavior from the measurement results.     

High-efficiency photon-number detection for quantum information processing

The visible light photon counter (VLPC) features high quantum efficiency (QE) and low pulse height dispersion. These properties make it ideal for efficient photon-number state detection. The ability to perform efficient photon-number state detection is important in many quantum information processing applications, including recent proposals for performing quantum computation with linear optical elements. In this paper, we investigate the unique capabilities of the VLPC. The efficiency of the detector and cryogenic system is measured at 543 nm wavelengths to be 85%. A picosecond pulsed laser is then used to excite the detector with pulses having average photon numbers ranging from 3-5. The output of the VLPC is used to discriminate photon numbers in a pulse. The error probability for number state discrimination is an increasing function of the number of photons, due to buildup of multiplication noise. This puts an ultimate limit on the ability of the VLPC to do number state detection. For many applications, it is sufficient to discriminate between 1 and more than one detected photon. The VLPC can do this with 99% accuracy.     

Preparation and Property of Acrylic Acid Rare Earth Complex and Its Hydrosilylation

Acrylic acid rare earth complex was prepared. Its chemical composition was determined by chemical and elemental analysis, and its structure as well as properties was characterized using IR, Fluorescence and UV spectrum, and its solubility was also investigated. Meanwhile a kind of elastic functional polymer with rare earth units in the side chains was produced. It is confirmed by IR spectrum that the Si-H bonds really react with acrylic acid rare earth.