Believe it or Not! Multicore CPUs can Match GPUs for FLOP-intensive Applications

In this work, we evaluate performance of a real-world image processing application that uses a cross-correlation algorithm to compare a given image with a reference one. The algorithm processes individual images represented as 2-dimensional matrices of single-precision floating-point values using O(n4) operations involving dot-products and additions. We implement this algorithm on a nVidia GTX 285 GPU using CUDA, and also parallelize it for the Intel Xeon (Nehalem) and IBM Power7 processors, using both manual and automatic techniques. Pthreads and OpenMP with SSE and VSX vector intrinsics are used for the manually parallelized version, while a state-of-the-art optimization framework based on the polyhedral model is used for automatic compiler parallelization and optimization. The performance of this algorithm on the nVidia GPU suffers from: (1) a smaller shared memory, (2) unaligned device memory access patterns, (3) expensive atomic operations, and (4) weaker single-thread performance. On commodity multi-core processors, the application dataset is small enough to fit in caches, and when parallelized using a combination of task and short-vector data parallelism (via SSE/VSX) or through fully automatic optimization from the compiler, the application matches or beats the performance of the GPU version. The primary reasons for better multi-core performance include larger and faster caches, higher clock frequency, higher on-chip memory bandwidth, and better compiler optimization and support for parallelization. The best performing versions on the Power7, Nehalem, and GTX 285 run in 1.02s, 1.82s, and 1.75s, respectively. These results conclusively demonstrate that, under certain conditions, it is possible for a FLOP-intensive structured application running on a multi-core processor to match or even beat the performance of an equivalent GPU version.

Structure of the benzene center dot center dot center dot ICI complex: A UVPES and ab initio molecular orbital study

UVPES studies and ab initio and DFT computations have been done on the benzene...ICl complex; electron spectral data and computed orbital energies show that donor orbitals are stabilized and acceptor orbitals are destabilized due to complexation. Calculations predict an oblique structure for the complex in which the interacting site is a C=C bond center in the donor and iodine atom in the acceptor, in full agreement with earlier experimental reports. BSSE-corrected binding energies closely match the enthalpy of complexation reported, and the NBO analysis clearly reveals the involvement of the pi orbital of benzene and the sigma* orbital of ICl in the complex.

Axially Loaded Timoshenko Rotors From A Prestressed Continuum Approach

We consider an axially loaded Timoshenko rotor rotating at a constant speed and derive its governing equations from a continuum viewpoint. The primary aim of this paper is to understand the source and role of gyroscopic terms, when the rotor is viewed not as a Timoshenko beam but as a genuine 3D continuum. We offer the primary insight that macroscopically observed gyroscopic terms may also, quite equivalently, be viewed as external manifestations of internally existing spin-induced prestresses at the continuum level. To demonstrate this idea with an analytical example (the Timoshenko rotor), we have studied the reliable equations of Choi et al. (Journal of Vibration and Acoustics, 114, 1992, 249-259). Using a straightforward application of our insight in the framework of nonlinear elasticity, we obtain equations that exactly match Choi et al. for the case with no axial load. For the case of axial preload, our straightforward formulation leads to a slightly different set of equations that have negligible numerical consequence for solid rotors. However, we offer a macroscopic, intuitive, justification for modifying our formulation so as to obtain the exact equations of Choi et al. with the axial load included.

A comparative study of multiple attribute tree and inverted file structures for large bibliographic files

A variety of data structures such as inverted file, multi-lists, quad tree, k-d tree, range tree, polygon tree, quintary tree, multidimensional tries, segment tree, doubly chained tree, the grid file, d-fold tree. super B-tree, Multiple Attribute Tree (MAT), etc. have been studied for multidimensional searching and related problems. Physical data base organization, which is an important application of multidimensional searching, is traditionally and mostly handled by employing inverted file. This study proposes MAT data structure for bibliographic file systems, by illustrating the superiority of MAT data structure over inverted file. Both the methods are compared in terms of preprocessing, storage and query costs. Worst-case complexity analysis of both the methods, for a partial match query, is carried out in two cases: (a) when directory resides in main memory, (b) when directory resides in secondary memory. In both cases, MAT data structure is shown to be more efficient than the inverted file method. Arguments are given to illustrate the superiority of MAT data structure in an average case also. An efficient adaptation of MAT data structure, that exploits the special features of MAT structure and bibliographic files, is proposed for bibliographic file systems. In this adaptation, suitable techniques for fixing and ranking of the attributes for MAT data structure are proposed. Conclusions and proposals for future research are presented.

Composite field approximations for ion traps with apertures on electrodes

This paper presents two approximate analytical expressions for nonlinear electric fields in the principal direction in axially symmetric (3D) and two dimensional (2D) ion trap mass analysers with apertures (holes in case of 3D traps and slits in case of 2D traps) on the electrodes. Considered together (3D and 2D), we present composite approximations for the principal unidirectional nonlinear electric fields in these ion traps. The composite electric field E has the form E = E-noaperture + E-aperture. where E-noaperture is the field within an imagined trap which is identical to the practical trap except that the apertures are missing and E-aperture is the field contribution due to apertures on the two trap electrodes. The field along the principal axis, of the trap can in this way be well approximated for any aperture that is not too large. To derive E-aperture. classical results of electrostatics have been extended to electrodes with finite thickness and different aperture shapes.E-noaperture is a modified truncated multipole expansion for the imagined trap with no aperture. The first several terms in the multipole expansion are in principle exact(though numerically determined using the BEM), while the last term is chosen to match the field at the electrode. This expansion, once Computed, works with any aperture in the practical trap. The composite field approximation for axially symmetric (3D) traps is checked for three geometries: the Paul trap, the cylindrical ion trap (CIT) and an arbitrary other trap. The approximation for 2D traps is verified using two geometries: the linear ion trap (LIT) and the rectilinear ion trap (RIT). In each case, for two aperture sizes (10% and 50% of the trap dimension), highly satisfactory fits are obtained. These composite approximations may be used in more detailed nonlinear ion dynamics Studies than have been hitherto attempted. (C) 2009 Elsevier B.V. All rights reserved.

Justifying threshold voltage definition for undoped body transistors through ``crossover point'' concept

Two different definitions, one is potential based and the other is charge based, are used in the literatures to define the threshold voltage of undoped body symmetric double gate transistors. This paper, by introducing a novel concept of crossover point, proves that the charge based definition is more accurate than the potential based definition. It is shown that for a given channel length the potential based definition predicts anomalous change in threshold voltage with body thickness variation while the charge based definition results in monotonous change. The threshold voltage is then extracted from drain current versus gate voltage characteristics using linear extrapolation, transconductance and match-point methods. In all the three cases it is found that trend of threshold voltage variation support the charge based definition.

A fuzzy dynamic flood routing model for natural channels

A fuzzy dynamic flood routing model (FDFRM) for natural channels is presented, wherein the flood wave can be approximated to a monoclinal wave. This study is based on modification of an earlier published work by the same authors, where the nature of the wave was of gravity type. Momentum equation of the dynamic wave model is replaced by a fuzzy rule based model, while retaining the continuity equation in its complete form. Hence, the FDFRM gets rid of the assumptions associated with the momentum equation. Also, it overcomes the necessity of calculating friction slope (S-f) in flood routing and hence the associated uncertainties are eliminated. The fuzzy rule based model is developed on an equation for wave velocity, which is obtained in terms of discontinuities in the gradient of flow parameters. The channel reach is divided into a number of approximately uniform sub-reaches. Training set required for development of the fuzzy rule based model for each sub-reach is obtained from discharge-area relationship at its mean section. For highly heterogeneous sub-reaches, optimized fuzzy rule based models are obtained by means of a neuro-fuzzy algorithm. For demonstration, the FDFRM is applied to flood routing problems in a fictitious channel with single uniform reach, in a fictitious channel with two uniform sub-reaches and also in a natural channel with a number of approximately uniform sub-reaches. It is observed that in cases of the fictitious channels, the FDFRM outputs match well with those of an implicit numerical model (INM), which solves the dynamic wave equations using an implicit numerical scheme. For the natural channel, the FDFRM Outputs are comparable to those of the HEC-RAS model.

Vibrations of a Beam in Variable Contact With a Flat Surface

We study small vibrations of cantilever beams contacting a rigid surface. We study two cases: the first is a beam that sags onto the ground due to gravity, and the second is a beam that sticks to the ground through reversible adhesion. In both cases, the noncontacting length varies dynamically. We first obtain the governing equations and boundary conditions, including a transversality condition involving an end moment, using Hamilton's principle. Rescaling the variable length to a constant value, we obtain partial differential equations with time varying coefficients, which, upon linearization, give the natural frequencies of vibration. The natural frequencies for the first case (gravity without adhesion) match that of a clamped-clamped beam of the same nominal length; frequencies for the second case, however, show no such match. We develop simple, if atypical, single degree of freedom approximations for the first modes of these two systems, which provide insights into the role of the static deflection profile, as well as the end moment condition, in determining the first natural frequencies of these systems. Finally, we consider small transverse sinusoidal forcing of the first case and find that the governing equation contains both parametric and external forcing terms. For forcing at resonance, w find that either the internal or the external forcing may dominate.

Texture dependent stress corrosion failure of commercial titanium sheets in bromine-methanol solution

The stress corrosion cracking (SCC) characteristics of agr-titanium sheets in a bromine-methanol solution have been studied in the annealed and cold-rolled conditions using longitudinal and transverse specimens. The times to failure for annealed longitudinal specimens were longer than those for similarly tested transverse specimens. The cold-rolled specimens developed resistance to SCC, but failed by cleavage when notched, unlike the intergranular separation in annealed titanium. The apparent activation energy was found to be texture dependent and was in the range 30 to 51 kJ mol–1 for annealed titanium, and 15kJ mol–1 for cold-rolled titanium. The dependence of SCC behaviour on the texture is related to the changes in the crack initiation times. These are caused by changes in the passivation and repassivation characteristics of the particular thickness plane. The thickness planes are identified with the help of X-ray pole figures obtained on annealed and cold-rolled material. On the basis of the activation energy and the electrochemical measurements, the mechanism of SCC in annealed titanium is identified to be the one involving stress-aided anodic dissolution. On the other hand, the results on the cold-rolled titanium are in support of the hydrogen embrittlement mechanism consisting of hydride precipitation. The cleavage planes identified from the texture data match with the reported habit planes for hydride formation.

Analysis And Design Of Two Layered Ultra Wide Band Filter

Design of an Ultra Wide Band (UWB) filter over 3.1 GHz to 10.6 GHz using broad side coupled and spur lines in microstrip medium suitable for UWB communications has been presented in this paper. Parameters of broad side coupled lines have been appropriately chosen to achieve ultra wide band response. Spur lines have been incorporated at the input and output feed lines of the filter to improve the stop band rejection characteristics of the filter. Filter has been analyzed based on circuit models and full wave simulations. Experimental results of the filter designed using the proposed structure has been verified against the results obtained from circuit models and full wave simulations. The results match satisfactorily. Stop band rejection of better than 20 dB was obtained over the frequencies of 13 GHz to 18.2 GHz. Overall size of the filter is 40 x 18 x 0.787 mm(3).

Dynamic Instabilities in Slender Space Launch Vehicles under Propulsive Thrust and Aerodynamic Forces

A mechanics based linear analysis of the problem of dynamic instabilities in slender space launch vehicles is undertaken. The flexible body dynamics of the moving vehicle is studied in an inertial frame of reference, including velocity induced curvature effects, which have not been considered so far in the published literature. Coupling among the rigid-body modes, the longitudinal vibrational modes and the transverse vibrational modes due to asymmetric lifting-body cross-section are considered. The model also incorporates the effects of aerodynamic forces and the propulsive thrust of the vehicle. The effects of the coupling between the combustion process (mass variation, developed thrust etc.) and the variables involved in the flexible body dynamics (displacements and velocities) are clearly brought out. The model is one-dimensional, and it can be employed to idealised slender vehicles with complex shapes. Computer simulations are carried out using a standard eigenvalue problem within h-p finite element modelling framework. Stability regimes for a vehicle subjected to propulsive thrust are validated by comparing the results from published literature. Numerical simulations are carried out for a representative vehicle to determine the instability regimes with vehicle speed and propulsive thrust as the parameters. The phenomena of static instability (divergence) and dynamic instability (flutter) are observed. The results at low Mach number match closely with the results obtained from previous models published in the literature.

Measurement of aerodynamic forces for missile shaped body in hypersonic shock tunnel using 6-component accelerometer based balance system

This paper reports the basic design of a new six component force balance system using miniature piezoelectric accelerometers to measure all aerodynamic forces and moments for a test model in hypersonic shock tunnel (HST2). Since the flow duration in a hypersonic shock tunnel is of the order of $1$ ms, the balance system [1] uses fast response accelerometers (PCB Piezotronics; frequency range of 1-10 kHz) for obtaining the aerodynamic data. The alance system has been used to measure the basic aerodynamic forces and moments on a missile shaped body at Mach $8$ in the IISc hypersonic shock tunnel. The experimentally measured values match well with theoretical predictions.

Design and characterization of in-plane MEMS yaw rate sensor

In this paper, we present the design and characterization of a vibratory yaw rate MEMS sensor that uses in-plane motion for both actuation and sensing. The design criterion for the rate sensor is based on a high sensitivity and low bandwidth. The required sensitivity of the yawrate sensor is attained by using the inplane motion in which the dominant damping mechanism is the fluid loss due to slide film damping i.e. two-three orders of magnitude less than the squeeze-film damping in other rate sensors with out-of-plane motion. The low bandwidth is achieved by matching the drive and the sense mode frequencies. Based on these factors, the yaw rate sensor is designed and finally realized using surface micromachining. The inplane motion of the sensor is experimentally characterized to determine the sense and the drive mode frequencies, and corresponding damping ratios. It is found that the experimental results match well with the numerical and the analytical models with less than 5% error in frequencies measurements. The measured quality factor of the sensor is approximately 467, which is two orders of magnitude higher than that for a similar rate sensor with out-of-plane sense direction.

Performance Analysis of MQAM-OFDM based WLAN in presence of Zigbee interference in AWGN and Rayleigh fading channel

In this paper we give the performance of MQAM OFDM based WLAN in presence of single and multiple channels Zigbee interference. An analytical model for getting symbol error rate (SER) in presence of single and multiple channel Zigbee interference in AWGN and Rayleigh fading channel for MQAM OFDM system is given. Simulation results are compared with analytical symbol error rate (SER) of the MQAM-OFDM system. For analysis we have modeled the Zigbee interference using the power spectral density (PSD) of OQPSK modulation and finding the average interference power for each sub-carrier of the OFDM system. Then we have averaged the SER over all WLAN sub-carriers. Simulations closely match with the analytical models. It is seen from simulation and analytical results that performance of WLAN is severely affected by Zigbee interference. Symbol error rate (SER) for 16QAM and 64QAM OFDM system is of order of 10(-2) for SIR (signal to interference ratio) of 20dB and 30dB respectively in presence of single Zigbee interferer inside the WLAN frequency band for Rayleigh fading channel. For SIR values more than 30dB and 40dB the SER approaches the SER without interference for 16QAM and 64QAM OFDM system respectively.