Profile-Driven Component Placement for Cluster-Based Online Services

The growth of the Internet and of various intranets has spawned a wealth of online services, most of which are implemented on local-area clusters using remote invocation (for example, remote procedure call/remote method invocation) among manually placed application components. Component placement can be a significant challenge for large-scale services, particularly when application resource needs are workload dependent. Automatic component placement has the potential to maximize overall system throughput. The key idea is to construct (offline) a mapping between input workload and individual-component resource consumption. Such mappings, called component profiles, then support high-performance placement. Preliminary results on an online auction benchmark based on J2EE (Java 2 Platform, Enterprise Edition) suggest that profile-driven tools can identify placements that achieve near-optimal overall throughput.     

X-ray or UV adjustment of MOS threshold voltage: Analytical and numerical modeling

A model is formulated that describes how radiation-induced charge accumulates in the gate oxide of a MOS structure and how it decays through tunneling and thermal emission. The model is used in a numerical analysis of the x-ray or UV adjustment of threshold voltage in MOS-circuit manufacture. The limits of this process technique are evaluated.     

1/f noise in large-area Hg<Subscript>1−x</Subscript>Cd<Subscript>x</Subscript>Te photodiodes

The 1/f noise in photovoltaic (PV) molecular-beam epitaxy (MBE)-grown Hg_1−xCd_xTe double-layer planar heterostructure (DLPH) large-area detectors is a critical noise component with the potential to limit sensitivity of the cross-track infrared sounder (CrIS) instrument. Therefore, an understanding of the origins and mechanisms of noise currents in these PV detectors is of great importance. Excess low-frequency noise has been measured on a number of 1000-μm-diameter active-area detectors of varying “quality” (i.e., having a wide range of I-V characteristics at 78 K). The 1/f noise was measured as a function of cut-off wavelength under illuminated conditions. For short-wave infrared (SWIR) detectors at 98 K, minimal 1/f noise was measured when the total current was dominated by diffusion with white noise spectral density in the mid-10⁻¹⁵A/Hz^1/2 range. For SWIR detectors dominated by other than diffusion current, the ratio, α, of the noise current in unit bandwidth i_n(f = 1 Hz, V_d = −60 mV, and Δf = 1 Hz) to dark current I_d(V_d = −60 mV) was α_SW-d = i_n/I_d ∼ 1 × 10⁻³. The SWIR detectors measured at 0 mV under illuminated conditions had median α_SW-P = i_n/I_ph ∼ 7 × 10⁻⁶. For mid-wave infrared (MWIR) detectors, α_MW-d = i_n/I_d ∼ 2 × 10⁻⁴, due to tunneling current contributions to the 1/f noise. Measurements on forty-nine 1000-μm-diameter MWIR detectors under illuminated conditions at 98 K and −60 mV bias resulted in α_MW-P = i_n/I_ph = 4.16 ± 1.69 × 10⁻⁶. A significant point to note is that the photo-induced noise spectra are nearly identical at 0 mV and 100 mV reverse bias, with a noise-current-to-photocurrent ratio, α_MW-P, in the mid 10⁻⁶ range. For long-wave infrared (LWIR) detectors measured at 78 K, the ratio, α_LW-d = i_n/I_d ∼ 6 × 10⁻⁶, for the best performers. The majority of the LWIR detectors exhibited α_LW-d on the order of 2 × 10⁻⁵. The photo-induced 1/f noise had α_LW-P = i_n/I_ph ∼ 5 × 10⁻⁶. The value of the noise-current-to-dark-current ratio, α appears to increase with increasing bandgap. It is not clear if this is due to different current mechanisms impacting 1/f noise performance. Measurements on detectors of different bandgaps are needed at temperatures where diffusion current is the dominant current. Excess low-frequency noise measurements made as a function of detector reverse bias indicate 1/f noise may result primarily from the dominant current mechanism at each particular bias. The 1/f noise was not a direct function of the applied bias.     

Effect of Sb implantation on copper silicides formation and morphology after annealing of Cu/Si structures

In this work, the solid state reaction between a thin film of copper and silicon has been studied using Rutherford backscattering spectroscopy, X-ray diffraction, scanning electron microscopy and microprobe analysis. Cu films of 400 and 900 Å thicknesses are thermally evaporated on Si(1 1 1) substrates, part of them had previously been implanted with antimony ions of 5×10¹⁴ or 5×10¹⁵ at. cm⁻² doses. The samples are heat-treated in vacuum at temperatures in the range 200–700 °C for various times. The results show the growth and formation of Cu₃Si and Cu₄Si silicides under crystallites shape dispatched on the sample surface, independently of the implantation dose. On the other hand, it is established that the copper layer is less and less consumed as the antimony dose increases, resulting in the accumulation of Sb⁺ ions at silicide/Si interface and in the silicide layer close to surface. The exposure of samples to air at room temperature shows the stability of Cu₄Si phase whereas the Cu₃Si silicide disappears to the benefit of the silicon dioxide formation. The observed phenomena are discussed.     

On trading wavelengths with fibers: a cost-performance based study

We consider the effect of multiple fibers on wavelength division multiplexing networks without wavelength conversion. We study networks with dynamic wavelength routing and develop accurate analytical models to compare various possible options using single- and multiple-fiber networks. We use results of an analytical model and simulation-based studies to evaluate the blocking performance and cost of multifiber networks. The number of fibers required providing high performance in multifiber networks and their costs are compared. A case is made for using multiple fibers in each link with fewer wavelengths instead of using a single fiber with many wavelengths. In particular, we show that a network with four fibers per link and with four wavelengths on each fiber without any wavelength conversion on any node yields similar same performance as the networks with one fiber per link and 16 wavelengths per fiber on each link and with full wavelength conversion capability on all nodes. In addition, the multifiber network may also offer the cost advantage depending on the relative cost of components. We develop a parametric cost model to show that multiple fibers in each link are an attractive option. Finally, such multifiber networks also has fault tolerance, with respect to a single fiber failure, already built into the system.     

QR factoring to compute the GCD of univariate approximate polynomials

We present a stable and practical algorithm that uses QR factors of the Sylvester matrix to compute the greatest common divisor (GCD) of univariate approximate polynomials over /spl Ropf/[x] or /spl Copf/[x]. An approximate polynomial is a polynomial with coefficients that are not known with certainty. The algorithm of this paper improves over previously published algorithms by handling the case when common roots are near to or outside the unit circle, by splitting and reversal if necessary. The algorithm has been tested on thousands of examples, including pairs of polynomials of up to degree 1000, and is now distributed as the program QRGCD in the SNAP package of Maple 9.     

Influence of device engineering on the analog and RF performances of SOI MOSFETs

This work presents a systematic comparative study of the influence of various process options on the analog and RF properties of fully depleted (FD) silicon-on-insulator (SOI), partially depleted (PD) SOI, and bulk MOSFET's with gate lengths down to 0.08 /spl mu/m. We introduce the transconductance-over-drain current ratio and Early voltage as key figures of merits for the analog MOS performance and the gain and the transition and maximum frequencies for RF performances and link them to device engineering. Specifically, we investigate the effects of HALO implantation in FD, PD, and bulk devices, of film thickness in FD, of substrate doping in SOI, and of nonstandard channel engineering (i.e., asymmetric Graded-channel MOSFETs and gate-body contacted DTMOS).     

High-gain hybrid amplifier consisting of cascaded fluoride-based TDFA and silica-based EDFA in 1458-1540 nm wavelength region

A hybrid optical fibre amplifier is described that consists of a fluoride-based thulium-doped fibre amplifier and a silica-based erbium-doped fibre amplifier connected in a cascade. The amplifier has a gain of more than 25 dB and a noise figure of less than 9 dB over a wide wavelength region of 1458-1540 nm.     

Static energy reduction techniques for microprocessor caches

Microprocessor performance has been improved by increasing the capacity of on-chip caches. However, the performance gain comes at the price of static energy consumption due to subthreshold leakage current in cache memory arrays. This paper compares three techniques for reducing static energy consumption in on-chip level-1 and level-2 caches. One technique employs low-leakage transistors in the memory cell. Another technique, power supply switching, can be used to turn off memory cells and discard their contents. A third alternative is dynamic threshold modulation, which places memory cells in a standby state that preserves cell contents. In our experiments, we explore the energy and performance tradeoffs of these techniques. We also investigate the sensitivity of microprocessor performance and energy consumption to additional cache latency caused by leakage-reduction techniques.     

An improved statistical analysis of the least mean fourth (LMF) adaptive algorithm

The paper presents an improved statistical analysis of the least mean fourth (LMF) adaptive algorithm behavior for a stationary Gaussian input. The analysis improves previous results in that higher order moments of the weight error vector are not neglected and that it is not restricted to a specific noise distribution. The analysis is based on the independence theory and assumes reasonably slow learning and a large number of adaptive filter coefficients. A new analytical model is derived, which is able to predict the algorithm behavior accurately, both during transient and in steady-state, for small step sizes and long impulse responses. The new model is valid for any zero-mean symmetric noise density function and for any signal-to-noise ratio (SNR). Computer simulations illustrate the accuracy of the new model in predicting the algorithm behavior in several different situations.