Hardware prefetching is a well-established technique for bridging the processor-memory performance gap. To improve cache miss coverage, modern processors often integrate multiple prefetchers. However, multi-prefetcher systems without proper management often suffer from suboptimal performance due to a surge of useless prefetches. Several techniques have been proposed to select appropriate prefetchers for issuing requests, but they all face limitations. Specifically, existing (1) static schemes lack feedback regulation mechanisms and suffer from inflexible prefetcher selections; (2) reinforcement learning (RL)based schemes incur high overhead and suffer from adjustment lag; and (3) performance-counter-based schemes rely on inefficient runtime metrics that fail to accurately and clearly reflect a prefetcher's true impact on performance. In this paper, we propose I-POP, a high-performance and lowoverhead prefetcher management scheme for multi-prefetcher systems. I-POP introduces a novel runtime metric, Prefetch Effectiveness (PE), which aggregates each prefetch request's beneficial and harmful effects to precisely quantify the impact of a prefetcher on performance, effectively overcoming the limitations of prior metrics. To compute and leverage this metric, I-POP incorporates two key components: the Metric Collector, which periodically calculates each prefetcher's PE, and the Control Engine, which dynamically manages all prefetchers based on their PE values. Specifically, I-POP ignites (enables) prefetchers with positive PE values, adaptively tuning their aggressiveness, and disables those with non-positive PE. We evaluated I-POP on numerous workloads, and the results show I-POP outperforms two state-of-the-art approaches, Bandit and Alecto, by$\mathbf{4. 2 \%}$and 3.5 % across three benchmark suites in a single-core system, and 6.6 % and 8.6 % in a 16 -core system, while incurring only 1.46 KB of storage overhead.

Mental manipulation on social media poses a covert yet serious threat to individuals' psychological well-being and the integrity of online interactions. Detecting such behavior is challenging due to the difficult-to-annotate training data, its highly covert and multi-turn nature, and the lack of real-world datasets. To address these challenges, we propose MentalMAD, a framework that enhances large language models for mental manipulation detection. Our approach consists of three key components: EvoSA, an annotation-free data augmentation method that combines evolutionary operations with speech-act-aware prompting; teacher-model-generated complementary-task supervision; and Complementary-Convergent Distillation, a phase-wise strategy for transferring manipulation-specific knowledge to student models. We then constructed the ReaMent dataset, comprising 5,000 real-world-sourced dialogues. Extensive experiments show that MentalMAD improves accuracy by 14.0%, macro-F1 by 27.3%, and weighted F1 by 15.1% over the strongest baseline. The code and the dataset are publicly available at https://github.com/Yuansheng-Gao/MentalMAD.

Estimating the frequency of items on the high-volume, fast data stream has been extensively studied in many areas, such as database and network measurement. Traditional sketches provide only coarse estimates under strict memory constraints. Although some learning-augmented methods have emerged recently, they typically rely on offline training with real frequencies or/and labels, which are often unavailable. Moreover, these methods suffer from slow update speeds, limiting their suitability for real-time processing despite offering only marginal accuracy improvements. To overcome these challenges, we propose UCL-sketch, a practical learning-based paradigm for per-key frequency estimation. Our design introduces two key innovations: (i) an online training mechanism based on equivalent learning that requires no ground truth (GT), and (ii) a highly scalable architecture leveraging logically structured estimation buckets to scale to real-world data stream. The UCL-sketch, which utilizes compressive sensing (CS), converges to an estimator that provably yields an error bound far lower than that of prior works, without sacrificing the speed of processing. Extensive experiments on both real-world and synthetic datasets demonstrate that our approach outperforms previously proposed approaches regarding per-key accuracy and distribution. Notably, under extremely tight memory budgets, its quality almost matches that of an (infeasible) omniscient oracle. Moreover, compared to the existing equation-based sketch, UCL-sketch achieves an average decoding speedup of nearly 500 times.

Zero-knowledge proof (ZKP) is a cryptographic primitive that enables one party to prove the validity of a statement to other parties without disclosing any secret information. With its widespread adoption in applications such as blockchain and verifiable machine learning, the demand for generating zero-knowledge proofs has increased dramatically. In recent years, considerable efforts have been directed toward developing GPU-accelerated systems for proof generation. However, these previous systems only explored efficiently generating a single proof by reducing latency rather than batch generation to provide high throughput.

Recent studies have shown that Contrastive Language-Image Pre-training (CLIP) models are threatened by targeted data poisoning and backdoor attacks due to massive training imagecaption pairs crawled from the Internet.Previous defense methods correct poisoned imagecaption pairs by matching a new caption for each image.However, the matching process relies solely on the global representations of images and captions, overlooking fine-grained features of visual and textual features.It may introduce incorrect image-caption pairs and harm the CLIP pre-training.To address their limitations, we propose an Optimal Transportbased framework to reconstruct image-caption pairs, named OTCCLIP.We propose a new optimal transport-based distance measure between fine-grained visual and textual feature sets and re-assign new captions based on the proposed optimal transport distance.Additionally, to further reduce the negative impact of mismatched pairs, we encourage the inter-and intra-modality fine-grained alignment by employing optimal transport-based objective functions.Our experiments demonstrate that OTC-CLIP can successfully decrease the attack success rates of poisoning attacks.Also, compared to previous methods, OTCCLIP significantly improves CLIP's zero-shot and linear probing performance trained on poisoned datasets.

With advancements in deep learning, speaker verification systems have significantly improved their performance in noisy environments. Researchers typically demonstrate the effectiveness of their improved models by comparing performance on specific datasets, such as the VoxCeleb benchmark. However, in diverse real-world noise conditions, the out-of-domain generalization ability is also a crucial factor in evaluating a model’s performance improvement. Research on stable learning indicates that eliminating the spurious correlation between training and testing data can enhance the generalization of the model. Building on this idea, we propose an improved speaker verification system with high generalization based on the extended U-Net (ExU-Net). It uses the sample reweighting method from stable learning to eliminate sample correlations and retains more effective speaker information through subpixel convolutions and coordinate attention mechanisms. We validate the effectiveness of this approach through extensive evaluations on VoxCeleb1, VOiCES, and other out-of-domain noise test sets, highlighting its generalization capability and model robustness.

Neural network models have markedly enhanced the field of Non-Intrusive Load Monitoring (NILM) compared to traditional approaches. However, two significant challenges persist. First, many studies overlook the design of model input paradigms and the role of feature interactions, leading to models with increasingly complex architectures and larger parameter counts, but with diminishing returns in performance. Second, existing models struggle with long-window input scenarios for load disaggregation, failing to balance the influences of local and global features effectively. This typically leads to a high rate of false positives and missed detections in identifying device energy usage events.To address the challenges associated with long-window disaggregation, this paper introduces a model named NILMixer. Constructed solely from linear and convolutional layers, NILMixer achieves an optimal balance between cost and performance through a layered approach to multi-scale feature interaction. Experimental results indicate that the proposed model not only outperforms several state-of-the-art methods but also effectively handles load disaggregation tasks across a spectrum from short to long window durations. Additionally, interpretability and ablation studies provide robust evidence and insights into the rational design of the model and the foundational role of its multi-scale features.

With the continuous development of smart sensing technology and energy internet, the growing demand for optimized energy resource management in power system operations side and the user side continues to grow and the indepth mining of power users’ electricity consumption behavior patterns can provide valuable insights for optimizing energy management and improving user-centric services. However, energy consumption behavior is highly complex, dynamic, and nonlinear. Traditional methods, relying on linear assumptions, fixed feature engineering, and labeled data, lack the adaptability needed to effectively capture such complex patterns. To address this problem, we propose an adaptive data augmentation method based on the attention mechanism for contrastive learning. Contrastive learning can automatically learn effective feature representations under unlabeled conditions, while the attention mechanism improves the expressiveness of the model by focusing on key features. Combining these two strategies for joint training helps the model better identify users’ electricity consumption behavior patterns in different time periods. Through comparative experiments with four data augmentation strategies and three models, the results show that the data augmentation method we proposed combined with the joint training strategy significantly improves the representation ability of the feature extractor, especially in the recognition and feature learning of complex electricity consumption behavior patterns.

As social media gains popularity, users frequently share personal photos without recognizing the risks of exposing their faces to advanced facial attribute detection technologies. These technologies can extract sensitive attributes such as age, race, sexual orientation, and potential health information from facial images, raising significant privacy concerns. Despite the availability of various anonymization techniques, our research reveals that current methods inadequately protect facial attribute privacy. They often fail to balance effectiveness and utility, underscoring the pressing need for more robust solutions in today’s pervasive photo-sharing culture. To remedy this gap, we introduce Invisible-Face, a tool designed to safeguard users’ facial attribute privacy using advanced adversarial perturbation techniques. Invisible-Face uses local, directional, and resilient perturbation generative strategies to obfuscate multiple facial attributes effectively, thus ensuring privacy while retaining the utility of the facial images. Our comprehensive evaluation across various datasets and model architectures shows that Invisible-Face significantly outperforms existing privacy-preserving methods in terms of effectiveness while maintaining high image naturalness. Furthermore, our extensive real-world evaluations on four popular MLaaS platforms—Baidu Brain, Tencent Cloud, Aliyun, and Face++—reveal that Invisible-Face achieves comparable privacy protection results while preserving the visual naturalness of images, outperforming existing methods. These findings boost public awareness about the importance of facial attribute privacy and urge online social platforms to improve their protection measures.

Visual retrieval aims to search for the most relevant visual items, e.g., images and videos, from a candidate gallery with a given query item. Accuracy and efficiency are two competing objectives in retrieval tasks. Instead of crafting a new method pursuing further improvement on accuracy, in this paper we propose a multi-teacher distillation framework Whiten-MTD, which is able to transfer knowledge from off-the-shelf pre-trained retrieval models to a lightweight student model for efficient visual retrieval. Furthermore, we discover that the similarities obtained by different retrieval models are diversified and incommensurable, which makes it challenging to jointly distill knowledge from multiple models. Therefore, we propose to whiten the output of teacher models before fusion, which enables effective multi-teacher distillation for retrieval models. Whiten-MTD is conceptually simple and practically effective. Extensive experiments on two landmark image retrieval datasets and one video retrieval dataset demonstrate the effectiveness of our proposed method, and its good balance of retrieval performance and efficiency. Our source code is released at https://github.com/Maryeon/whiten_mtd.

Hardware data prefetching is a well-studied technique to bridge the processor-memory performance gap. Bit-pattern-based prefetchers are one of the most promising spatial data prefetchers that achieve substantial performance gains. In bit-pattern-based prefetchers, the region size is a crucial parameter, which denotes the memory size that can be recorded by a pattern or prefetched by a prediction. However, existing bit-pattern-based prefetchers only support one fixed region size. Our experiment shows that the fixed region size cannot meet the requirements for numerous applications and leads to suboptimal performance and high hardware overhead. In this article, we propose PARS, a pattern-aware spatial data prefetcher supporting multiple region sizes. The key idea of PARS is that it supports multiple region sizes, enabling it to simultaneously enhance application performance while reducing the hardware overhead. Moreover, PARS supports dynamically switching appropriate region sizes for different patterns through an adaptive RS-switching mechanism. We evaluated PARS on numerous workloads and results show that PARS provides an average performance improvement of 40.6% over a baseline with no data prefetchers and outperforms the two state-of-the-art prefetchers Bingo by 2.1% (up to 24.4%) and Pythia by 3.9% (up to 111.2%) in the single-core system. In the four-core system, PARS outperforms Bingo by 5.0% (up to 66.0%) and Pythia by 5.4% (up to 177.9%).

In recent years, DeepFake technologies have seen widespread adoption in various domains, including entertainment and film production. However, they have also been maliciously employed for disseminating false information and engaging in video fraud. Existing detection methods often experience significant performance degradation when confronted with unknown forgeries or exhibit limitations when dealing with low-quality images. To address this challenge, we introduceDiff-ID, a novel approach designed to elucidate and quantify the identity loss induced by facial manipulations. When assessing the authenticity of an image,Diff-IDleverages a genuine image of the same individual as a reference and processes two images jointly. It aligns the reference image and the test image into the same identity-insensitive attribute feature space using a face-swapping generator. This alignment allows us to observe the identity disparities between the two images through the differences in the aligned generation pairs. Subsequently, we have developed a custom metric designed to quantify the identity loss relative to the reference image in the test image. This metric effectively distinguishes forgery images from the real ones. Extensive experiments have demonstrated the exceptional performance of our approach. It achieves a high level of detection accuracy on DeepFake images and showcases state-of-the-art generalization capabilities when confronted with previously unknown forgery methods. Moreover, it exhibits robustness even in the presence of image distortions.

Existing lip synchronization (lip-sync) methods generate accurately synchronized mouths and faces in a generated video. However, they still confront the problem of artifacts in regions of non-interest (RONI), e.g. , background and other parts of a face, which decreases the overall visual quality. To solve these problems, we innovatively introduce diverse image inpainting to lip-sync generation. We propose Modulated Inpainting Lip-sync GAN (MILG), an audio-constraint inpainting network to predict synchronous mouths. MILG utilizes prior knowledge of RONI and audio sequences to predict lip shape instead of image generation , which can keep the RONI consistent. Specifically, we integrate modulated spatially probabilistic diversity normalization (MSPD Norm) in our inpainting network, which helps the network generate fine-grained diverse mouth movements guided by the continuous audio features. Furthermore, to lower the training overhead, we modify the contrastive loss in lip-sync to support small-batch-size and few-sample training. Extensive experiments demonstrate that our approach outperforms the existing state-of-the-art of image quality and authenticity while keeping lip-sync.

The advanced multi-core technology enables parallel computing to speed up Automatic Test Pattern Generation (ATPG). The main challenge is to solve an increasing number of hard-to-solve faults effectively. In this paper, we develop an efficient parallel computing system for the ATPG program, i.e., FPGNN-ATPG, which is consisted of two parts: graph-neural-networks-based (GNN-based) fault classification and fault-driven deterministic test pattern generator (DTPG). The end-to-end GNN-based classifier can predict fault types with superior accuracy compared with classical machine learning methods. And the fault-driven DTPG can solve different types of faults in parallel without runtime overhead. According to the experimental results on an 8-core machine, our FPGNN-ATPG framework obtains an average of 7.56X speedup while reducing 14.13% pattern count ratio with full 100% fault coverage for 10 industrial instances.

Automatic identification of function clones on cross-platform aims at determining whether two functions are identical or not without access to the source code, which is a fundamental challenge in vulnerability search, code plagiarism detection, and malware classification. With the rapid development of deep neural network in program analysis, the state-of-the-art neural network-based function clone identification methods propose to represent functions as embeddings by graph neural network (GNN). However, such a novel representation of functions brings in two challenges. (1) The feature engineering that accurately maps the raw data of binary code to machine learning features is complicated. (2) A highly accurate embedding of functions requires a customized GNN to focus on the most critical features to identify binary code. To the best of our knowledge, currently, a comprehensive work that can overcome the above challenges is still missing. In this paper, we propose a novel prototype named as Focus, which is designed to accurately and efficiently identify similar functions. Specifically, inspired by natural language processing techniques which effectively learns text semantic across natural languages, Focus can learn representative semantic features of functions by a customized learning model. To address the second challenge, a multi-head attention mechanism can be employed to capture the critical features of a function. Through extensive experiments, we demonstrate that Focus achieves high accuracy of function clone identification on a broad range of eight architectures. In particular, the identification performance (AUC value) of Focus is 97% and 99% for cross-platform and single-platform, respectively. Furthermore, the evaluation in real world applications shows that our Focus identifies 24 vulnerable functions among the top-30 candidates, which is one time higher than the baseline approaches.

One intriguing property of deep neural networks (DNNs) is their vulnerability to adversarial examples – those maliciously crafted inputs that deceive target DNNs. While a plethora of defenses have been proposed to mitigate the threats of adversarial examples, they are often penetrated or circumvented by even stronger attacks. To end the constant arms race between attackers and defenders, significant efforts have been devoted to providing certifiable robustness bounds for DNNs, which ensures that for a given input its vicinity does not admit any adversarial instances. Yet, most prior works focus on the case of symmetric vicinities (e.g., a hyperrectangle centered at a given input), while ignoring the inherent heterogeneity of perturbation direction (e.g., the input is more vulnerable along a particular perturbation direction). To bridge the gap, in this article, we propose the concept ofasymmetric robustnessto account for the inherent heterogeneity of perturbation directions, and presentAmoeba1, an efficient certification framework for asymmetric robustness. Through extensive empirical evaluation on state-of-the-art DNNs and benchmark datasets, we show that compared with its symmetric counterpart, the asymmetric robustness bound of a given input describes its local geometric properties in a more precise manner, which enables use cases including (i) modeling stronger adversarial threats, (ii) interpreting DNN predictions, and makes it a more practical definition of certifiable robustness for security-sensitive domains.

Web search queries reveal extensive sensitive information about users’ interests and preferences to the search engines and eavesdroppers. Obfuscation-based private web search solutions automatically generate dummy queries and send the obfuscated queries to the search engine to hide users’ search intentions. Despite many obfuscation methods and tools have been developed, there is no practical system for evaluating their utility performance and the vulnerability against modern privacy attacks. In this article, we propose and develop OB-WSPES, a uniform evaluation system for obfuscation-based web search privacy, which allows researchers to conduct fair analysis and evaluation of existing or newly developed web search privacy protection/attack techniques. Leveraging OB-WSPES, we model the obfuscation activities and systematically implement and evaluate five obfuscation schemes and 10 modern web search attacks on the public AOL dataset. Our results demonstrate that, counter-intuitively, adding more fake queries to a user’s real data does not necessarily yield better privacy. The query utility of obfuscated queries declines with the increasing amount of dummy queries, while the application utility does not. We discuss the experimental results and point out the four important factors that affect the web search privacy and utility. Further, we propose possible directions for future research.

Virtual desktop technology aims at accessing a remote desktop by endpoint hardware.Great attention has been increasingly paid to virtual desktop since it can increase the utilization of computing resources and provide more flexible accesses.However, researchers have not yet come up with a comprehensive set of rigorous standards of experimental design and implementation in this field.Therefore, it is difficult to conduct prudent experiments, which is correct, real, and transparent.In this paper, we assess the experimental evaluations of recently published papers on desktop virtualization.We observe that most works can be further improved, due to the unsuitable experimental environment and the lack of descriptions of experimental settings.In this paper, in order to help researchers, reviewers, and readers, we propose several guidelines for designing correct, real, and transparent desktop virtualization experiment.

Virtual machine placement (VMP) problem has been a key issue in IaaS/PaaS cloud infrastructures. Many recent works on VMP prove that inter-VM relations such as memory share, traffic dependency and resource competition should be seriously considered to save energy, increase the performance of infrastructure, reduce service level agreement violation rates and provide better administrative capabilities to the cloud provider. However, most existing works consider the inter-VM relations without taking the heterogeneity of cloud data centers into account. In practice, heterogeneous physical machines (PM) in a heterogeneous data center are often partitioned into logical groups for load balancing and specific services, cloud users always assigned their VMs with specific PM requirements, which make the inter-VM relations far more complex. In this paper, we propose an efficient solution for VMP with inter-VM relation constraints in a heterogeneous data center. The experimental results prove that our solution can efficiently solve the complex problem with an acceptable runtime.

Summary Hybrid storage systems that consist of flash‐based solid state drives (SSDs) and traditional disks are now widely used. In hybrid storage systems, there exists a two‐level cache hierarchy that regard dynamic random access memory (DRAM) as the first level cache and SSD as the second level cache for disk storage. However, this two‐level cache hierarchy typically uses independent cache replacement policies for each level, which makes cache resource management inefficient and reduces system performance. In this paper, we propose a novel adaptive multi‐level cache (AMC) replacement algorithm in hybrid storage systems. The AMC algorithm adaptively adjusts cache blocks between DRAM and SSD cache levels using an integrated solution. AMC uses combined selective promote and demote operations to dynamically determine the level in which the blocks are to be cached. In this manner, the AMC algorithm achieves multi‐level cache exclusiveness and makes cache resource management more efficient. By using real‐life storage traces, our evaluation shows the proposed algorithm improves hybrid multi‐level cache performance and also increases the SSD lifetime compared with traditional multi‐level cache replacement algorithms. Copyright © 2015 John Wiley & Sons, Ltd.

With the rapid development of multi-core and multi-threading technologies, the performance gap between CPU and storage system is widening year by year, causing the storage system to be the bottleneck of the whole system performance. To alleviate this situation, flash memory has been used as the caching device of HDDs. On the other hand, cloud computing is becoming more and more popular and mature in industry field. As the key building block of it, virtualization technology allows several virtual machines (VMs) running on one single physical machine simultaneously, most of which usually run the same or similar operating systems and applications. In this scenario, flash cache will be occupied by many duplicate data blocks. However, existing flash cache architectures and replacement policies don't take this observation into consideration, which greatly limits the efficient use of the flash cache. In this paper, we propose a new duplication-aware flash cache architecture (DASH). In this architecture, flash cache is organized to cache only one copy of the duplicate data blocks, which can notably expand the effective cache capacity, making more I/O requests hit in the cache. Moreover, this architecture can reduce the amount of data written to flash cache, and thus the life span of flash device can be significantly prolonged. Experiments based on realistic applications show that, in some situations, our cache architecture can improve the cache hit ratio by 5 times, reduce the average I/O latency by 63% and eliminate flash cache writes by 81%.

ABSTRACT Most of existing traffic simulation efforts focus on urban regions with a coarse two‐dimensional representation; relatively few studies have been conducted to simulate realistic three‐dimensional traffic flows on a large, complex road web in rural scenes. In this paper, we present a novel agent‐based approach called accident‐avoidance full velocity difference model (abbreviated as AA‐FVDM) to simulate realistic street‐level rural traffics, on top of the existing FVDM. The main distinction between FVDM and AA‐FVDM is that FVDM cannot handle a critical real‐world traffic problem while AA‐FVDM settles this problem and retains the essence of FVDM. We also design a novel scheme to animate the lane‐changing maneuvering process (in particular, the execution course). Through numerous simulations, we demonstrate that besides addressing a previously unaddressed real‐world traffic problem, our AA‐FVDM method efficiently (in real time) simulates large‐scale traffic flows (tens of thousands of vehicles) with realistic, smooth effects. Furthermore, we validate our method using real‐world traffic data, and the validation results show that our method measurably outperforms state‐of‐the‐art traffic simulation methods.Copyright © 2013 John Wiley & Sons, Ltd.

ABSTRACT How to automatically generate realistic and heterogeneous traffic behaviors has been a much needed yet challenging problem for numerous traffic simulation and urban planning applications. In this paper, we propose a novel approach to model heterogeneous traffic behaviors by adapting a well‐established personality trait model (i.e., Eysenck's PEN (psychoticism, extraversion and neuroticism) model) into widely used traffic simulation approaches. First, we collected a large amount of user feedback while users watch a variety of computer‐generated traffic simulation video clips. Then, we trained regression models to bridge low‐level traffic simulation parameters and high‐level perceived traffic behaviors (i.e., adjectives according to the PEN model and the three PEN traits). We also conducted an additional user study to validate the effectiveness and usefulness of our approach, in particular, high correlation coefficients and the Pearson values between users’ feedback and our model predictions prove the effectiveness of our approach. Furthermore, our approach can also produce interesting emergent traffic patterns including faster‐is‐slower effect and sticking‐in‐a‐pin‐wherever‐there‐is‐room effect. Copyright © 2014 John Wiley & Sons, Ltd.

Trajectories obtained from Global Position System (GPS)-enabled taxis grant us an opportunity not only to extract meaningful statistics, dynamics, and behaviors about certain urban road users but also to monitor adverse and/or malicious events. In this paper, we focus on the problem of detecting anomalous routes by comparing the latter against time-dependent historically “normal” routes. We propose an online method that is able to detect anomalous trajectories “on-the-fly” and to identify which parts of the trajectory are responsible for its anomalousness. Furthermore, we perform an in-depth analysis on around 43 800 anomalous trajectories that are detected out from the trajectories of 7600 taxis for a month, revealing that most of the anomalous trips are the result of conscious decisions of greedy taxi drivers to commit fraud. We evaluate our proposed isolation-based online anomalous trajectory (iBOAT) through extensive experiments on large-scale taxi data, and it shows that iBOAT achieves state-of-the-art performance, with a remarkable performance of the area under a curve (AUC)$\geq$0.99.

There are two problems in the existing rendering platforms that support HLA-based simulation applications. One is the fact that the management of simulation entity objects and the management of rendering scene objects are separate, which leads to inefficiency in simulation and rendering. Another one is absence of rendering interface, especially for parallel rendering for users. In order to solve the above problems, we present a unified object model supporting HLA-based simulation and parallel rendering, which consists of heterogenous scene graph tree, action list and universal access interface. The Unified object model establishes an efficient data exchange bridge between HLA simulation and parallel rendering. Therefore massive complex scene and large quantity of simulation entities can be organized and managed in a unified form. An experimental demo is given at the end of this paper.

Distributed simulation and parallel rendering based on PC cluster have seen great success in recent years. To improve the overall performance, there is a trend to integrate modeling, simulation and visualization into a common distributed environment. In this paper, we propose a unified framework of building high performance distributed virtual reality (DVR) applications. The core components of this framework include the High Level Architecture (HLA), scene graphs and parallel rendering. The HLA supports interactive distributed simulation. Scene graphs are efficient to organize and manipulate scene data. And parallel rendering provides powerful rendering ability. This paper presents the in-depth architectural analysis of each components and derives a design that integrates them into a unified framework. Two DVR applications, including a remote navigation of massive virtual scenes and a multi-player video game, have been developed to evaluate the framework performance.