An accurate and practical buffer allocation model for the buffer cache based on marginal gains

A new dynamic buffer allocation strategy based on the notion of marginal gains is presented for the buffer cache that is used by the operating system to store frequently accessed disk blocks in main memory, and the performance of the proposed strategy is compared with those of previous allocation strategies. In the proposed strategy, marginal gain values are predicted by exploiting functions that approximate the expected number of buffer hits per unit time. Experimental results from both trace-driven simulation and an actual implementation in the FreeBSD operating system show that the proposed strategy accurately predicts the marginal gain values for various workloads resulting in significantly improved buffer hit ratios.     

Foveation-Based Error Resilience and Unequal Error Protection over Mobile Networks

By exploiting new human-machine interface techniques, such as visual eyetrackers, it should be possible to develop more efficient visual multimedia services associated with low bandwidth, dynamic channel adaptation and robust visual data transmission. In this paper, we introduce foveation-based error resilience and unequal error protection techniques over highly error-prone mobile networks. Each frame is spatially divided into foveated and background layers according to perceptual importance. Perceptual importance is determined either through an eye tracker or by manually selecting a region of interest. We attempt to improve reconstructed visual quality by maintaining the high visual source throughput of the foveated layer using foveation-based error resilience and error correction using a combination of turbo codes and ARQ (automatic reQuest). In order to alleviate the degradation of visual quality, a foveation based bitstream partitioning is developed. In an effort to increase the source throughput of the foveated layer, we develop unequal delay-constrained ARQ (automatic reQuest) and rate compatible punctured turbo codes where the punctual pattern of RCPC (rate compatible punctured convolutional) codes in H.223 Annex C is used. In the simulation, the visual quality is significantly increased in the area of interest using foveation-based error resilience and unequal error protection; (as much as 3 dB FPSNR (foveal peak signal to noise ratio) improvement) at 40% packet error rate. Over real-fading statistics measured in the downtown area of Austin, Texas, the visual quality is increased up to 1.5 dB in PSNR and 1.8 dB in FPSNR at a channel SNR of 5 dB.     

X-ray-based measurement of composition during electron beam melting of AISI 316 stainless steel: Part II. Evaporative processes and simulation

An energy dispersive X-ray (EDX) detector mounted on a laboratory scale electron beam furnace (30 kW) was employed to assess the potential use of X-rays as a means of on-line composition monitoring during electron beam (E B) melting of alloys. The design and construction of the collimation and protection systems used for the EDX are described in Part I. In Part II, a mathematical simulation of the heat, mass, and momentum transfer was performed for comparison to the EDX and vapor deposition results. The predicted flow patterns and evaporation rates are used to explain the differences between the two experimental methods. For the EDX spectra measured, the X-rays generated were from the center of the hearth where fluid flow rising from the bulk of the pool is sufficient to maintain the bulk composition despite the high evaporative flux from the surface. The flow moves radially outward from the center of the pool, with the volatile species being depleted. The vapor deposition technique measures the entire region, giving an average surface composition, and it therefore differs from the EDX results, which gave a near bulk composition. This combined study using in-situ EDX measurements and numerical simulations both provided an insight into the phenomena controlling the evaporation in an EB-heated system and demonstrated the viability of using EDX to measure the bulk composition during EB melting processes.     

An efficient implementation of SELF, a dynamically-typed object-oriented language based on prototypes

We have developed and implemented techniques that double the performance of dynamically-typed object-oriented languages. Our SELF implementation runs twice as fast as the fastest Smalltalk implementation, despite SELF's lack of classes and explicit variables.To compensate for the absence of classes, our system uses implementation-levelmaps to transparently group objects cloned from the same prototype, providing data type information and eliminating the apparent space overhead for prototype-based systems. To compensate for dynamic typing, user-defined control structures, and the lack of explicit variables, our system dynamically compilesmultiple versions of a source method, eachcustomized according to its receiver's map. Within each version the type of the receiver is fixed, and thus the compiler can statically bind andinline all messages sent toself.Message splitting andtype prediction extract and preserve even more static type information, allowing the compiler to inline many other messages. Inlining dramatically improves performance and eliminates the need to hard-wire low-level methods such as+, ==, andifTrue:.Despite inlining and other optimizations, our system still supports interactive programming environments. The system traverses internal dependency lists to invalidate all compiled methods affected by a programming change. The debugger reconstructs inlined stack frames from compiler-generated debugging information, making inlining invisible to the SELF programmer.This work has been generously supported by National Science Foundation Presidential Young Investigator Grant #CCR-8657631, and by IBM, Texas Instruments, NCR, Tandem Computers, Apple Computer, and Sun Microsystems.This paper was originally published inOOPSLA '89 Conference Proceedings (SIGPLAN Notices, 25, 10 (1989) 49–70).     

Bandwidth and region division for broadband multi-cell networks

A cell planning technique termed BRD (bandwidth and region division) is presented for overcoming interference, maintaining QoS (quality of service) and improving channel capacity over OFDM (orthogonal frequency division multiplexing)-based broadband cellular networks. Through an optimal combination of sectorization and zero padding, bandwidth and region division is achieved that minimizes the outage probability for forward-link cell planning. In order to verify the effectiveness of the proposed algorithm, a Monte Carlo simulation is performed over multi-cell environments.     

A practical approach for statistical matching of output queueing

We study a practical approach to match the performance of an output-queued switch statistically. For this purpose, we propose a novel switching architecture called a multiple input/output-queued (MIOQ) switch that requires no speedup for providing sufficient switching bandwidth. To operate an MIOQ switch in a practical manner, we also propose a multitoken-based arbiter which schedules the switch at a high operation rate and a virtual first-in first-out queueing scheme which guarantees the departure order of cells belonging to the same traffic flow at output. Additionally, we show that the proposed switch can naturally provide asymmetric bandwidth for inputs and outputs, which may be important in dealing with the links with different bandwidth demands. Finally, we compare the performance of an MIOQ switch with that of an output-queued switch and discuss the design criteria to match the performance of an output-queued switch.     

Data retention characteristics of sub-100 nm NAND flash memory cells

In contrast to the conventional theories, we have revealed that the most distinguished mechanism in the data retention phenomenon after Fowler-Nordheim (FN) stress in sub-100 nm NAND Flash memory cells is the annihilation of interface states. Interface state generation rate increases rapidly as the channel width of NAND flash cell decreases. Comparison of interface states and stress-induced leakage current (SILC) component during retention mode shows that the annihilation of interface states strongly affects data retention characteristics of the programmed cells.     

建(构)筑物机械拆除方法综述

介绍了几种常用的建(构)筑物机械拆除方法,对其工作原理、特点、应用条件及局限性加以分析和说明。     

Orientation-based unique representation for planar curves and shapes

This paper presents an orientation-based representation for planar curves and shapes. The new representation can uniquely represent all types, of planar shapes, be it convex, nonconvex, polygonal, smoothly curved, or piecewise smooth shapes. It is based on a new parameterization, theabsolute integral orientation. This representation is invariant under translation and rotation. The absolute integral orientation is a parameter invariant under scaling. As a result, matching of similar shapes (i.e., determination of the relative orientation and the scaling factor) using the absolute integral orientation as the parameter is easier than using the arclength as the parameter. In addition, the new representation has the feature of adaptive sampling, making it more compact and efficient than arc-length-based representations.