最新刊期
卷 36 ， 期 2 ， 2008
- 摘要：With the progress of low-power research on embedded systems,the estimation and analysis of the energy consumption of operating system becomes a hot topic.This paper presents a quantitative approach to estimate and analyze the energy consumption of embedded operating system (EOS).In this approach,EOS and applications are executed on two cooperated simulators.Instruction execution energy is estimated using a cycle-accurate micro-architecture power model.We propose an OS energy consumption estimation model based on software functionality and structure.The approach can calculate the energy consumption for functions,routines,services and kernel execution paths in an EOS,and can identify the key modules and factors impacting the system energy consumption.Our experiments show that the proposed approach improves the accuracy and efficiency of energy estimation of EOS significantly.The estimation results can be used to quantitatively analyze and optimize the energy consumption of EOS and applications.关键词：embedded operating system;energy consumption estimation and analysis;quantitative approach2|1413|13更新时间：2025-07-16
- 摘要：This paper analyzes the limitations of current implementation technologies to Clark-Wilson integrity model,and presents an approach to enforcing Clark-Wilson model based on Type Enforcement.Firstly,the advantages of this approach are discussed.Secondly,the configuration rules and constraints that implement Clark-Wilson model based on TE are given.The triple (userid,TP,list of CDIs) of Clark-Wilson model is extended and replaced by the quarter-tuple (userid,role,TP,list of CDIs),which implement the separation of duty principle more practically.In addition,the protection of TP is covered by the TE,which ensures the correct functionality of TP,enhances the degree of confidence that TP function correctly,and releases the dependency on the certification procedure.关键词：Clark-Wilson model;integrity;Type Enforcement(TE);separation of duty2|943|1更新时间：2025-07-16
- 摘要：In Simultaneous Multithreading(SMT)processors,the instruction fetch policy determines the way of allocating shared resources among co-scheduled threads implicitly,and affects throughput and fairness consequently.However,prior work on fetch policies almost focuses on throughput optimization.The issue of fairness between threads in progress rates is studied rarely.In this paper,we purchase fairness as the main optimization goal and propose a novel fetch policy called FAIR.Results show that for all types of workloads,FAIR can achieve good fairness and RPRrange(a fairness metric defined in this paper)is less than 5%.Furthermore,FAIR does not sacrifice throughput severely.Compared to fetch policies orienting towards throughput maximization such as ICOUNT,degradation of FAIR in throughput is 3.8% on average.关键词：SMT;instruction fetch policy;throughput;fairness2|772|0更新时间：2025-07-16
- 摘要：A novel multilevel inverse-based ILU (MIB-ILU) preconditioning approach is applied to the hybrid finite-element/boundary-integral/multilevel fast multipole algorithm (FE/BI/MLFMA) for 3D scattering problems.Unlike the traditional ILU preconditioning technique,this MIB-ILU approach borrows the concept of the algebraic multi-grid method (AMG) to construct an algebraic multilevel recursive ILU preconditioning framework.Moreover,a new version of ILU factorization and an inverse-based dropping strategy are employed to improve the robust of the preconditioning approach.The numerical performance of the proposed MIB-ILU approach is studied.It is demonstrated that this approach exhibits high efficiency in memory and CPU time.Then,the proposed MIB-ILU approach is applied to the hybrid FE/BI/MLFMA method.A variety of numerical experiments are carried out,demonstrating that the proposed approach offers a good compromise between robustness and efficiency,and greatly improves the computing capability of the hybrid FE/BI/MLFMA.2|1219|0更新时间：2025-07-16
- 摘要：The equivalent circuits of a compact Quasi-Elliptic low-pass filter (QELPF) are derived from the Chebyshev prototype circuits by introducing an attenuation pole,which has excellent performance in selectivity and harmonic suppression. The inductances in series branch circuits of QELPF are realized by dumb-bell-shaped defected ground structures(DB-DGSs),the high external quality factor of LC parallel resonance circuits in series branch circuits are realized by spiral-shaped defected ground structures (SP-DGSs),and the shunt capacitances are realized by broadened microstrip lines. Since the design expressions are all analytical,this design process of QELPF is fast and accurate. Finally,a five-pole QELPF for 2.4GHz is developed. The simulated and measured results show that passband insert-loss is less than 0.5dB and the stopband width with 20dB attenuation is over 13GHz.Furthermore,its size in the lengthwise direction is only about 1/4 wavelength.关键词：low-pass filter;defected ground structure(DGS);equivalent circuit model2|904|4更新时间：2025-07-16
- 摘要：A motion estimation algorithm based on gradient methods for low signal-to-noise (SNR) scenarios is presented by using statistical performance of the estimator.Firstly,the cost function of mean square error (MSE) is developed based on Cramer-Rao low bound by considering the influence of the noises on motion estimation.Secondly,the motion estimation MSE is minimized to find the gradient optimal filters.In combination with multi-scale pyramid approach,the estimator accuracy of such an algorithm can be further improved.Experimental simulations show that the estimator bias is less than 0.008 pixels for large motion estimation of low SNR scenarios.This represents a significant decrease in estimator accuracy compared to existing methods for motion estimation of low SNR situations.关键词：motion estimation;filters design;MSE;Cramer-Rao low bound;multi-scale2|1013|0更新时间：2025-07-16
- 摘要：In order to have a good performance for maneuvering target tracking,A fuzzy variable structure interacting multiple model (FVSIMM) algorithm based on H∞filter is proposed in this paper. It introducesH∞ filter as model-conditional filter,which keeps its robustness by constantly adjusting parameter,to improve the performance and the precision. Meanwhile,the algorithm takes model probabilities of the IMM algorithm as the input of fuzzy inference system. By the fuzzy logic inference to update model probabilities,it adjusts the number of models and parameters in real-time,reduces excessive competition,and realizes variable structure function. The simulation results indicate that,the algorithm has higher tracking accuracy than standard IMM algorithm.关键词：maneuvering target tracking;H∞ filter;interacting multiple model;fuzzy variable structure3|937|4更新时间：2025-07-16
- 摘要：Determination of transmission zeros is important in synthesis of cross-coupled filter.A novel method to determine the general Chebyshev filter degree and transmission zeros at the same time is proposed according to the extreme characteristic of the general Chebyshev function and the relationship between the filter degree and the number of transmission zeros.On the condition of the given filter specifications,the least filter degree and the optimum positions of transmission zeros are realized.Several simulation examples illustrate the procedure and the validity in the filter design of the proposed method.关键词：general Chebyshev function;cross-coupled filter;transmission zeros;extreme frequency2|1439|2更新时间：2025-07-16
- 摘要：The dynamics of ultrasonic transducer for thermosonic flip chip bonding is investigated.Velocities of mark points on transducer and bonding tool,which represent different modal vibrations,are sampled by a laser Doppler vibrometer.The results show the axial vibration is dominant while it is disturbed by other non-axial components.It means that the ultrasonic transducer system vibrates complicatedly,which couples the axial and non-axial components simultaneously.The effect of non-axial vibration influences significantly the bonding quality such as chip tilting and poor bonding strength.The multiple vibrations of ultrasonic transducer is analyzed by finite element model.It is found that ultrasonic transducer vibrates in coupling resultant of all allowable modes being excited.The origin and corresponding control method for multiple vibrations is brought forward.关键词：multiple modal vibrations;ultrasonic transducer;FEM analysis;thermosonic flip chip bonding2|1321|3更新时间：2025-07-16
- 摘要：The algorithm and implementation of the differential direct sequence spread spectrum multi-sign detector was studied in this paper.The differential direct sequence spread spectrum multi-sign detector algorithm was derived from the differential multi-sign detecting algorithm.The Barker code differential direct sequence spread spectrum multi-sign detector with the gain of 13 and the simultaneously detecting number of N=4 has been implemented by using the fusion design structure of SAW matching filter and fixed delay line.The de-spread spectrum and demodulation performances of the detector have been tested and analyzed as well.关键词：surface acoustic wave;differential direct sequence spread spectrum;multiple-symbol detection2|752|0更新时间：2025-07-16
- 摘要：A two-dimensional discrete-time map for pulse-width modulated second-order switched-capacitor DC-DC converter is derived.The stability at fixed point of the map is analyzed under nonlinear dynamics theory.The bifurcation diagram and largest Lyapunov exponent graph with the voltage feedback factor as parameter are obtained through numerical computation.Taking second-order switched-capacitor DC-DC converter as an example,we find a chaotic attractor in the converter by simulating the circuit with PSPICE program.The results from theoretical analysis,numerical computation and analog simulation coincide with each other well.关键词：switched-capacitor DC-DC converter;two-dimensional discrete-time map;bifurcation;chaos;Lyapunov exponent4|1186|9更新时间：2025-07-16
- 摘要：With the increasing number of switched capacitor cells,the topology of n-stage step-up resonant switched capacitor converter (RSC) is more complex,so it is hard to observe sneak circuit paths in the converter. In this paper,a general method is proposed to analyze the sneak circuit paths in n-stage step-up RSC converters based on graphic theory. The theorem and steps to obtain sneak paths were explained in detail,and the 3-stage step-up RSC converter was taken as an example to describe how to find out the sneak circuit paths. The proposed sneak circuit analysis method,whose correctness is finally verified by simulation and experimental results,can be extended to other power electronics converters,and is useful for discovering,eliminating or utilizing sneak circuit paths.关键词：resonant switched capacitor converter;n-stage;step-up;sneak circuit;graphic theory2|1002|4更新时间：2025-07-16
- 摘要：In this paper,we propose the cluster-based power management mechanism,which uses register cluster as the power management granularity.Specifically,the cluster-oriented compiler makes the register numbers in loops as continuous as possible to offer more opportunities for run-time power management,and the cluster-based run-time power manager employs a register cluster buffer to filter accesses to the register file for dynamic power saving.The dynamic voltage scaling and gated precharge circuits are also well utilized to reduce the leakage of bitcells and bitlines.Averagely,the total register file power is reduced by 44.7%.Compared with traditional approaches,the hardware/software co-design approach proposed in this paper achieves better power,area and delay tradeoffs for register files in embedded processors.关键词：embedded processor;register file;register cluster;dynamic power;leakage power2|909|1更新时间：2025-07-16
- 摘要：To meet the future demands of earth observation satellites,this paper presents a novel architecture and describe the implementation of a prototype named Space Solid-State Recorder with several Memory Modules (MMs) connected by high-speed serial links.The MM utilizes an FPGA and DDR SDRAM to boost throughput,and adopts a featured SDDA (Single-Data-bus,Double-Address-bus) storage topology to manage and control these memory chips efficiently.Through high-speed serial transceivers embedded in the FPGA chip,several MMs interconnect with each other to form the Space Solid-State Recorder.To ensure the quality of serial links,a multilayer communication interface protocol stack that consists of a physical layer,link layer and message layer is proposed.As a result,the MM can provide storage capacity of 8GB,and its memory bandwidth approaches 3.2GBps.Furthermore,the physical bandwidth of the communication interface can reach up to 25Gbps.Moreover,the bit error rate (BER) of the interface in Space Solid-State Recorder system is below 10-11.关键词：solid-state recorder;high-speed serial links;memory module;field programmable gate array(FPGA);double data rate(DDR) SDRAM memory controller2|1001|2更新时间：2025-07-16
- 摘要：In this paper,a hierarchical BitTorrent-like file sharing system is proposed to improve the performance of file sharing.Peers in such system are grouped into clusters according to their proximity in the underlying overlay network.A fluid model is developed to compare the proposed hierarchical BitTorrent-like system with the original BitTorrent system.With this model,we find that the hierarchical BitTorrent-like system improves the performance of file sharing quite effectively.Finally,the simulation results further prove that the hierarchical BitTorrent-like system achieves better scalability and efficiency while retaining the robustness and incentives of the original BitTorrent paradigm.关键词：BitTorrent system;hierarchical architecture;super-peer2|741|3更新时间：2025-07-16
- 摘要：We present a new test data compression and decompression method based on statistic relativity of variable length data block,to resolve the storage and bandwidth problems faced by the automatic test equipment (ATE) in system-on-a-chip (SOC) during test.For each test vector,determine a data block with best relativity to be the referenced data block of it,then compress the vector by the relativity between its data blocks and the referenced data block.Besides,the length of referenced data blocks is independent from each other.Its decompression architecture requires only a finite state machine (FSM)、a five-bit storing device temporarily and a cyclical scan register (CSR) whose length is the same as the referenced data block,so the hardware cost in proposed scheme is small.Experimental results for ISCAS-89 benchmarks show that our new technique can provide a higher compression radios than other compression algorithms.关键词：relativity of data block;statistic;referenced data block;data compression2|1010|11更新时间：2025-07-16
- 摘要：The performance of reduced reference (RR) image quality assessment depends on the feature extraction and sparse representation of the image.Wavelet-based contourlet transform(WBCT),a non-redundant sparse representation of image,can effectively reflect visual characteristics of the image,such that it is often used to capture the variation of visual perception to result from image distortion.Hereby,an objective image quality assessment metric is proposed by combining the WBCT with RR model.Experimental results illustrate that the proposed method has a good consistency with the subjective assessment of human beings,thus can be used to describe the visual perception of the image effectively.关键词：image quality assessment;reduced reference model;visual perception;wavelet-based contourlet transform2|1021|6更新时间：2025-07-16
- 摘要：We present a method of facial feature point extraction based on improved Active Shape Model (ASM) and Gabor wavelet.Facial feature points can be located robustly and precisely by using the method proposed in this paper.Firstly,light compensation is used on the detected facial region.Secondly,we locate the eyes and mouth to obtain a good initial shape of feature points.And then the improved ASM is used to get a robust rough shape.We improve local gray-level model of the traditional ASM by adding local skin similarity probability,and form local hybrid model.Finally,we search the precise location of a certain feature point by classifying the Gabor feature of points around the rough location.The Gabor feature can be trained and dimensionally reduced by Linear Discriminant Analysis (LDA),and classified by Nearest Neighborhood method.At the end of the paper,experimental results demonstrate the robustness and accuracy of this method.关键词：facial feature points extraction;skin similarity model;Gabor feature;feature point classification;linear discriminant analysis LDA;nearest neighbor classification2|1286|5更新时间：2025-07-16
- 摘要：Distributed storage use erasure coding and threshold scheme to provide security and reliability.We present threshold Byzantine quorum system (TBQS),which can be used to design reliable storage strategy where up to one fourth of the servers might exhibit Byzantine faults.TBQS can provide fault-tolerance and serviced without interruption together with erasure coding or threshold schemes.We discussed the existence of TBQS,and proposed two types of TBQS called threshold f-masking system and grid TBQS respectively.We also yield a read-write protocol base on TBQS that is both time-efficient and reliable.关键词：distributed storage;fault tolerance;quorum system;Byzantine fault2|970|3更新时间：2025-07-16
- 摘要：In view of that e-Prosecution system should effectively protect and encourage informants,this paper provides an anonymous e-prosecution scheme with reward support based on the technology of ring signature and ring signcryption.The scheme can effectively protect an informant for his/her identity is ambiguous;it can also guarantee the security of prosecution contents because all prosecutions are encrypted,non-transferable and can’t be forged.Furthermore,the scheme could provide effective reward support by informant’s ability of self-proof.Analysis shows that the scheme can effectively meet the requirement of such electronic prosecution system.关键词：prosecution system;identity ambiguous;self-proof;ring signcryption2|859|6更新时间：2025-07-16
- 摘要：From the syntactical point of view,the concept of the syntactic truth degree of formulas is proposed in two-valued propositional logic system.Two equivalent depiction theorems about syntactic truth degree are introduced.Examples of syntactic truth degree illustrate that the original truth degree from semantics is a special syntactic truth degree.It is pointed out that the similarity degree and pseudo-metric induced by syntactic truth degree possess respectively the basic properties of similarity degree and pseudo-metric from semantics.The concept of τ -consistent theory is given.Then the intrinsic relation between τ -consistent and consistent theory is pointed out.关键词：two-valued propositional logic;truth degree theory;syntactic truth degree;τ -consistent theory2|918|12更新时间：2025-07-16
- 摘要：RNA secondary structure prediction is one of the most important fields in computational molecular biology.The method to predict RNA secondary structure is introduced,including the mathematic models,main algorithms and softwares.Then seven main softwares are tested and compared detailedly with some groups of tRNA and RNase P.It showed that Pfold performed better than others when several homologous RNA sequences were predicted.At last some vital aspects that may be conducted in the future investigations are discussed.关键词：RNA secondary structure prediction;minimum free energy;comparative sequence analysis method;pseudoknot4|5992|14更新时间：2025-07-16
- 摘要：Capacitor mismatching is a main source of error for switched-capacitor analog-to-digital converter.A differential capacitor pairing technique is presented to reduce capacitor mismatch error.By comparing the capacitance of capacitors and then accordingly exchanging the position of capacitors,the gain error of the stage,which is proportional to the relative error between the sum of differential sampling capacitors and the sum of differential feedback capacitors,is obviously reduced.Probability analysis and Monte Carlo simulation indicate that the linearity of the analog-to-digital converter can be improved by 0.6 bit.Compared with other capacitor mismatch calibration techniques,the proposed technique has characteristics such as simple calibration circuits,unweakened conversion speed,and insensitive to the operation environment.关键词：capacitor mismatch calibration;pipelined A/D conversion;circuit techniques2|914|0更新时间：2025-07-16
- 摘要：Conventional planar lowpass filters often suffer from the problem of spurious passbands.For spurious response suppression,integration of bandstop filters in a conventional open-stub lowpass filter is presented.By using equivalent T-shaped transmission lines to replace series connecting transmission lines of the conventional lowpass filter,the T-shaped lines work as bandstop filters at the spurious passbands.Furthermore,general design equations are given to transform arbitrary series connecting lines of the filter into the equivalent T-shaped lines.The proposed filter improves the out-of-band rejection over very wide operation band width and reduces the overall size with low insertion loss.Very good agreement has been observed between the experimental results and simulated data.The insertion loss is less than 0.5 dB from DC to 3GHz and the rejection is greater than 60 dB from 3.6GHz to 12GHz.关键词：lowpass filter;bandstop filter;T-shaped transmission line;broad-stopband4|1350|4更新时间：2025-07-16
- 摘要：The method of reducing triple-transition reflection signal with the same phase method is proposed in the paper.When the frequency of the signal equals the center frequency of iterdigital transducer (IDT),the phase of the main signal equals the phase of triple-transition reflection signal,so that the triple-transition reflection signal is reduced.And the parallel method of the double receiving IDTs is studied.The double receiving IDTs are absolutely symmetrical,otherwise the frequency characteristic curve of wavelet transform element of SAW type is not smooth.关键词：surface acoustic wave(SAW);wavelet transform element;triple-transition reflection signal;iterdigital transducer(IDT)2|737|1更新时间：2025-07-16
- 摘要：The performance analysis process of microprocessor has become more and more difficult with the rapid development of modern processor architecture.The traditional performance analysis approach based on macro benchmarks and simulator is complex and time-consuming.Moreover,it can not analyze the micro-architectural characteristics systematically.In this paper,a novel performance analysis approach based on micro-benchmark (Godson-Microbench) and ideal-bound computation formulas is proposed.This approach extends the bounds based performance analysis approach.Compared with the traditional approach,this approach can be used to analyze the pipeline efficiency and identify the performance bottleneck.With this approach,the micro-architecture of the Godson-2 processor and Alpha21264 processor are analyzed and compared.On the basis of this work,we improve the architecture of Godson-2,resulting a 13.8% increase in performance of the micro-benchmarks and 28.8% increase in IPC of the SPEC CPU2000.This performance analysis approach is a complement of the cycle-accurate simulation and plays an important role in the architectural optimization process of Godson-2.关键词：performance analysis;micro-benchmark;ideal bound;Godson-2 processor;Alpha21264 processor2|1488|0更新时间：2025-07-16
- 摘要：A new algorithm based on artificial neural network is presented as a software compensation to improve the non-linearity of pressure sensor and the output error characteristics caused by the variation of temperatures.It consists of the regulation for four weights,which stand for the coefficients of one and two powers of output signals and temperatures,respectively.An optimum output formula is obtained after a lot of iterations.This formula satisfies both sample values and other values among them and can check the correctness of the final iteration results of this artificial neural network computing.关键词：pressure sensor;artificial neural network;temperature compensation;software algorithm2|1903|21更新时间：2025-07-16
- 摘要：A new Switched Product Code Pyramid Vector Quantizer (SPCPVQ) used for quantizing the ISF (Immittance Spectral Frequencies) parameters of wideband speech is proposed in this paper.Based on switch vector quantization and product code pyramid vector quantization,in this quantizer,the ISF parameters vector to be quantized is first switched to one of the possible directions and then quantized using the corresponding product code pyramid vector quantizer.The characteristics of this Algorithm are low complexity and low memory for the codebook storage.Experimental results show that this quantization scheme achieves lower spectral distortion with transparent coding at 46bits/frame.关键词：speech coding;vector quantization;immittance spectral frequencies;pyramid VQ2|1048|3更新时间：2025-07-16
- 摘要：This paper addresses a problem of continuous batch scheduling arising in the heating-process of blooms in steel industry.Each heating furnace is modeled as continuous batch processing machine,which can handle more than one job simultaneously.The processing time of a batch depends on its size,the longest processing time of jobs in the batch and the capacity of the batching machine.In this paper we consider the problem for minimizing total completion time.The theoretic analysis of optimal solution properties are given,and the optimal policy of batching and the method of sequencing the batches are provided.A dynamic programming algorithm with a polynomial running time is represented based on the properties of batching and scheduling.关键词：steel industry;heating-furnace scheduling;continuous batch;dynamic programming algorithm2|788|2更新时间：2025-07-16
- 摘要：A heat transfer model is given for thermistor mount in power measurement procedure.A relational expression of effective efficiency with thermal capacitance and thermal conductance is derived from the model.A microwave power measurement error,which is from heat exchange difference,is defined as thermal equivalence error.The thermal equivalent error is analyzed in detail and its analytic expression is derived.Methods are suggested to eliminate this error at last.关键词：metrology;power measurement;power standard;microcalorimeter2|954|3更新时间：2025-07-16
- 摘要：As a new tool of signal analysis,wavelet transform has been successfully used in image processing.One of the most important fields of image processing is denoising.Since image contains plenty of edges,the wavelet basis used in image denoising should have the nice properties of edge-preserving and noise-smoothing.However,it is difficult to find such a wavelet basis.In this paper,based on the theory of multi-phase representation of signal,a 3-channel orthogonal perfect reconstruction filter bank is designed and the corresponding soft thresholding algorithm used in image denoising is deduced too.Examples show that the proposed filter bank is effective in image denoising.关键词：image processing;wavelet transform;multi-channel filter bank;denoising2|736|0更新时间：2025-07-16
- 摘要：The major drawback of recent image filtering algorithms for removing impulse noise is lack of the ability of preserving the image details and edges which are smaller than the size of filtering windows.To alleviate this limitation,a new image filtering algorithm using a double noise detector and edge-preserving regularization function is proposed in this paper.The proposed filter has a two-stage scheme:detecting noise and removing noise.In order to improve accurate rate of noise detection,noise candidates identified with the noise detection algorithm of the adaptive median filter are judged again by local fuzzy membership function,and then a convex objective function composed of 1 data-fidelity term and edge-preserving regularization function is employed to deal with noise candidates.The input of edge-preserving regularization function is adaptively selected to take full advantage of local features of the image.The image corrupted by noise is restored successfully as the convex objective function gets its minimum.Experimental results show the superiority of the proposed filter in terms of the ability of removing noise and preserving the details and edges of the image in comparison with some recent methods,it is also shown that even at a very high noise level (＞70%) details and edges of the original image are preserved very well with our method.关键词：double noise detector;edge-preserving regularization function;Salt-and-Pepper noise2|885|3更新时间：2025-07-16
- 摘要：In conventional motion compensated temporal filtering based wavelet coding scheme,where the size of group of picture and low-pass frames’ positions are fixed,and the motion activities in video sequences are not considered.In this paper,we propose a haar-like motion compensated temporal filtering based wavelet video coding scheme,which can adaptively select the size of group of picture and the low-pass frames based on mutual information technology.Then,the temporal decomposition level is determined using the selected size of group of picture and the low-pass frames' position.We compare the PSNR performance of the proposed scheme with the conventional scheme by carrying out a large amount of experimental work.When the video sequence has high motion activity,the proposed low-pass frame selection can improve the compression quality by about 0.3~0.5 dB compared with the conventional scheme;And,the proposed adaptive approach for selecting the size of group of picture is more suitable for situations with un-even variation of motion activities,e.g.with frequent shot cuts.关键词：key-frame;mutual information;group of picture;Motion Compensated Temporal Filtering(MCTF)2|968|2更新时间：2025-07-16
- 摘要：Register file design is very important in high performance processor design. Register Stack and Register Stack Engine are effective ways to improve performance. Compiler optimizations are often driven by specific assumptions about the underlying architecture and implementation of the target machine. In this paper,we present our efforts to design and implement register file management mechanism——MTRM (Mapping Table-based Register Management) on EDSMT,which is a kind of SMT architecture based on IA-64. MTRM assigns a Mapping Table for each thread to mapping their logic registers to physic registers,which adds a middle level into Itanium's original rename mechanism. MTRM focused on supporting the effective sharing of registers in an EDSMT processor,using register renaming to permit multiple threads to share a single global register file. Existing hardware is effective at allocating physical registers;it has only limited ability to identify register deallocation points. Compile optimization is considered to deallocate dead registers,while Special Bit and Special Instruction are used as two effective ways. Simulation results indicate that these mechanisms can reduce register deallocation ineffciencies;in particular,on small register files,the best of the schemes attains speedups of up to 2.2 for some applications,and 1.8 on average.关键词：register file;simultaneous multithreading(SMT);explicitly parallel instruction computing(EPIC);parallel;compile optimization2|1054|0更新时间：2025-07-16
- 摘要：Authenticated key agreement protocol is designed to provide pair of parties communicating over an insecure network with a secure session key.However,most of the existing authenticated key agreement protocols are not designed for protecting privacy.We emphasize user’s privacy properties in network services,in particular we stress anonymity and deniability.We specify the desired security properties of privacy-enhancing authentication key agreement protocols,i.e.mutual authentication,key control,key confirmation,session-key confidentiality,known-key security,forward secrecy,anonymity of user,forward anonymity of user,unlinkability,deniability.Based on elliptic curve cryptosystem we also propose a protocol which satisfies all the desired security properties.关键词：anonymity;deniability;authentication key agreement;elliptic curve2|1016|4更新时间：2025-07-16
- 摘要：A model of MPI synchronization communication programs is presented and its three basic simplified models are also defined.A series of theorems and methods for deciding whether deadlocks will occur among the three models are given and proved strictly.These theories and methods for simple models’ deadlock detection are the necessary base for real MPI program deadlock detection.The methods are based on a static analysis through programs and with runtime detection in necessary cases and they are able to determine before compiling whether it will be deadlocked for two of the three basic models.For another model,some deadlock cases can be found before compiling and others at runtime.Our theorems can be used to prove the correctness of currently popular MPI program deadlock detection algorithms.Our methods may decrease codes that those algorithms need to change to MPI source or profiling interface and may detects deadlocks ahead of program execution,thus the overheads can be reduced greatly.关键词：message passing interface(MPI);deadlock;synchronization communication2|863|4更新时间：2025-07-16
- 摘要：Filter conflicts resolving is an important issue for packet classification and network management.On the one hand,to reduce the time spent on packet classification,a certain algorithm for resolving filter conflicts should be applied to eliminate all filter conflicts during the preprocessing phase.On the other hand,because of the complexity of firewall filters,when firewall administrators add a filter,the newly added filter may conflict with existing ones.This not only makes filter databases difficult to manage,but also may lead to security vulnerabilities.Thus a certain algorithm for resolving filter conflicts should also be applied to eliminate all filter conflicts.Several algorithms for resolving filter conflicts have already been proposed but most of them cannot eliminate filter conflicts completely and set restrictions on filters.This paper analyses filter conflicts from the perspective of computational geometry and presents a filter conflicts resolving algorithm based on cutting mapping.The algorithm resolves filter conflicts according to the classification of conflicts.It treats two filters as the basic processed object and sequentially cuts every dimension of the filters that have lower priority.This paper proves the algorithm and experiments verify its good performance.关键词：filter conflicts;resolving conflicts;cutting mapping;computational geometry;classification of conflicts2|820|4更新时间：2025-07-16
- 摘要：How to effectively locate resources is a very important factor affecting the performance of Grid and P2P environment.Some resource discovery methods have been already proposed,which utilizes Small World phenomena.In this paper,on the base of Kleinberg Small World model,this paper proposes an efficient decentralized construction approach SSWCP(Scalable Small World Construction Protocol),which uses partial view instead of global knowledge of network.Through analysis and simulations,we show that SSWCP is scalable to very large network sizes and large numbers of resources.关键词：grid;P2P;small world;distributed2|1259|1更新时间：2025-07-16
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
0