Tandem mass spectrometry (MS/MS) is a critical tool for identifying molecular structures. By efficiently separating molecular fragments based on their mass-to-charge (m/z) ratios, it facilitates molecular generation and subsequent scientific discoveries. However, de novo molecular generation from MS/MS spectra remains fundamentally constrained by two paramount challenges: the vast chemical space requires effective structural constraints, and the absence of fine-grained substructural generation weakens the correspondences between spectral features and molecular structures. In this work, we propose MSAnchor, a novel two-stage framework for MS/MS-based molecular structure generation. We mitigate the search space challenge through the introduction of Anchor-Extended Molecular Scaffold (AEMS) representation that explicitly encodes side-chain anchoring points, thereby dramatically reducing combinatorial complexity. Leveraging the explicit attachment sites provided by AEMS, we develop anchor-specific priors that establish effective alignments between spectral features and molecular substructures. This fine-grained substructural correspondence is further enhanced by a modified Conditional Information Bottleneck (CIB) module that extracts the most informative spectral components in a structure-aware manner. These innovations enable MSAnchor to generate molecular structures that closely reflect spectral characteristics while constraining combinatorial complexity. Extensive experiments on the CANOPUS and MassSpecGym datasets demonstrate that MSAnchor achieves state-of-the-art performance in molecular structure prediction from MS/MS spectra, with performance improvements that are particularly more pronounced for molecules with higher complexity.

Multi-task learning (MTL) has gained widespread application for its ability to transfer knowledge across tasks, improving resource efficiency and generalization. However, gradient conflicts from different tasks remain a major challenge in MTL. Previous gradient-based and loss-based methods primarily focus on gradient optimization in shared parameters, often overlooking the potential of task-specific parameters. This work points out that task-specific parameters not only capture task-specific information but also influence the gradients propagated to shared parameters, which in turn affects gradient conflicts. Motivated by this insight, we propose ConsMTL, which models MTL as a bi-level optimization problem: in the upper-level optimization, we perform gradient aggregation on shared parameters to find a joint update vector that minimizes gradient conflicts; in the lower-level optimization, we introduce an additional loss for task-specific parameters guiding the k gradients of shared parameters to gradually converge towards the joint update vector. Our design enables the optimization of both shared and task-specific parameters to consistently mitigate gradient conflicts. Extensive experiments show that ConsMTL achieves state-of-the-art performance across various benchmarks with task numbers ranging from 2 to 40, demonstrating its superior performance.

Multi-task learning (MTL) can leverage shared knowledge across tasks to improve data efficiency and generalization performance, and has been applied in various scenarios. However, task imbalance remains a major challenge for existing MTL methods. While the prior works have attempted to mitigate inter-task unfairness through loss-based and gradient-based strategies, they still exhibit imbalanced performance across tasks on common benchmarks. This key observation motivates us to consider performance-level information as an explicit fairness indicator, which can precisely reflect the current optimization status of each task, and accordingly help to adjust the gradient aggregation process. Specifically, we utilize the performance variance among tasks as the fairness indicator and introduce a dynamic weighting strategy to gradually reduce the performance variance. Based on this, we propose PIVRG, a novel performance-informed variance reduction gradient aggregation approach. Extensive experiments show that PIVRG achieves SOTA performance across various benchmarks, spanning both supervised learning and reinforcement learning tasks with task numbers ranging from 2 to 40. Results from the ablation study also show that our approach can be integrated into existing methods, significantly enhancing their performance while reducing the performance variance among tasks, thus achieving fairer optimization.

Ultra-dense low earth orbit (LEO) satellite networks (UDLSNs) present a viable solution to deliver high-speed, lowlatency Internet services. Data transmission scheduling stands as a key technology for guaranteeing high-speed Internet services. Nonetheless, data transmission scheduling in UDLSNs encounters some critical challenges, predominantly related to the complexity of network scale, resource contention and the stringency of user demands. In this paper, we focus on the typical application scenario of satellite network, namely Airborne Internet, and delve into the data delivery scheduling problem in UDLSN. We aim to maximize the number of successfully scheduled flows by jointly optimizing satellite-to-aircraft downlink subchannel access, intersatellite link path planning, and flow scheduling based on timeexpanded graphs. Given the large-scale nature of the network, we decouple the proposed problem into a downlink subchannel access problem and a flow scheduling problem. We further design the matching-based subchannel allocation (MSA) algorithm and$A^{*}$-based path planning and flow scheduling (APPFS) algorithm to solve the two subproblems, respectively. We use authentic civil aviation flight trajectories and$\mathbf{1 1, 9 2 6}$LEO satellites in the entire Starlink phase as simulation data to evaluate the effectiveness of the proposed algorithm. Simulation results validate that the proposed algorithm can satisfy stringent user latency requirements and improve the number of successfully transmitted data.

In Agile/Scrum software development, sprint planning and retrospective analysis are the key elements of project management. The aim of our work is to support software developers in these activities. In this paper, we present our prototype tool RetroAI++, based on emerging intelligent technologies. In our RetroAI++ prototype, we aim to automate and refine the practical application of Agile/Scrum processes within Sprint Planning and Retrospectives. Leveraging AI insights, our prototype aims to automate and refine the many processes involved in the Sprint Planning, Development and Retrospective stages of Agile/Scrum development projects, offering intelligent suggestions for sprint organisation as well as meaningful insights for retrospective refection.

Multi-Task Learning (MTL) enables a single model to learn multiple tasks simultaneously, leveraging knowledge transfer among tasks for enhanced generalization, and has been widely applied across various domains. However, task imbalance remains a major challenge in MTL. Although balancing the convergence speeds of different tasks is an effective approach to address this issue, it is highly challenging to accurately characterize the training dynamics and convergence speeds of multiple tasks within the complex MTL system. To this end, we attempt to analyze the training dynamics in MTL by leveraging Neural Tangent Kernel (NTK) theory and propose a new MTL method, NTKMTL. Specifically, we introduce an extended NTK matrix for MTL and adopt spectral analysis to balance the convergence speeds of multiple tasks, thereby mitigating task imbalance. Based on the approximation via shared representation, we further propose NTKMTL-SR, achieving training efficiency while maintaining competitive performance. Extensive experiments demonstrate that our methods achieve state-of-the-art performance across a wide range of benchmarks, including both multi-task supervised learning and multi-task reinforcement learning. Source code is available at https://github.com/jianke0604/NTKMTL.

Rate-splitting multiple access (RSMA) has recently gained attention in low earth orbit (LEO) satellite-terrestrial networks (LSTNs), due to its ability to provide high spectral efficiency in the context of constrained energy resources of LEO satellites. However, the impracticality of acquiring perfect real-time channel state information (CSI), due to high satellite mobility and long link delay, poses significant challenges to effective utilization of RSMA in LSTNs. To tackle this challenge, we propose a location-based robust RSMA scheme for downlink data transmission in LSTNs. First, we establish an optimization problem to minimize the power consumption of LEO satellites, while meeting user requirement on the real-time data rate violation probability. Subsequently, we transfer the probability constraints of rate violation probabilities into closed-form inequalities, by utilizing Markov inequality, Jensen’s inequality, and Cauchy-Schwarz inequality. The original problem is then transformed into a Markov decision process (MDP), and a Transformer encoder-based deep reinforcement learning (TDRL) algorithm is proposed to solve the complex problem based on the real-time locations of users and the LEO satellite. Additionally, a multi time-frame location-based training dataset generation method is proposed for the training of TDRL model, considering the mobility of LEO satellite. Simulation results demonstrate that the proposed scheme is effective in guaranteeing the rate violation probability requirement of each user, and RSMA significantly outperforms space division multiple access (SDMA) and non-orthogonal multiple access (NOMA), with TDRL achieving faster convergence than other baselines.

Ultradense low-Earth orbit (LEO) satellite-terrestrial network (ULSN) has evolved as a new paradigm to provide ubiquitous and high-capacity communications in next generation wireless networks. However, the direct LEO satellite broadband connectivity faces significant challenges in urban environments due to the masking effect, which limits the reliability and availability of communication links in ULSNs. To address this, reconfigurable intelligent surface (RIS) is emerging as a promising solution in ULSNs. In this article, we investigate RIS-aided downlink data transmission in urban environments of multiusers in ULSNs. We set up a mixed-integer programming (MIP) model for maximizing the sum rate of terrestrial users in ULSNs. To solve the complex MIP problem, we propose a two-phase joint optimization algorithm with a deep learning phase and an alternative optimization (AO) phase. In the deep learning phase, a deep neural network (DNN) algorithm is employed to obtain the optimal user association matrix based on the positions of terrestrial users and LEO satellites. Then in the AO phase, successive convex approximation is utilized to transform the nonconvex subproblems of beamforming and RIS phase design into convex formulations and iteratively solve them. Simulation results demonstrate that the proposed algorithm outperforms other baseline algorithms.

The booming renaissance and rapid development of ultra-dense low earth orbit (LEO) satellite networks (UD-LSNs) are envisioned to realize a giant leap forward for the future sixth generation (6G) coverage expansion, bridging digital divide for remote areas and providing continuous services for user terminals worldwide. However, the inherent dual mobility, massive access scenarios and highly overlapped coverage may trigger frequent, vast and ping-pong handovers, especially with the existing limited and fixed deployment of terrestrial mobility functional entity. To this end, by exploiting the unique opportunity of UD-LSNs, we devise a medium Earth orbit (MEO) assisted distributed hierarchical mobility management architecture (HDMMA) with flexible function configuration to adapt the high dynamic and large scale network. Subsequently, the lightweight handover procedures (LHPs) are proposed for two scenarios under the HDMMA to ensure service continuity, that is on-orbit handover and off-orbit handover. Considering the user mobility attributes and satellite available resources, the on-orbit handover introduces user aggregate to share signaling overhead, while the off-orbit handover is further classified into intra-cluster, inter-cluster and inter-group handover based on the clustering and grouping. Furthermore, we conduct theoretical analysis model on the proposed LHP in terms of signaling overhead and handover latency. Simulation results verify the handover characteristics in UD-LSNs, illustrate the superiority of our HDMMA and demonstrate the handover performance improvement of the proposed LHP.

Supernet is a core component in many recent Neural Architecture Search (NAS) methods. It not only helps embody the search space but also provides a (relative) estimation of the final performance of candidate architectures. Thus, it is critical that the top architectures ranked by a supernet should be consistent with those ranked by true performance, which is known as the order-preserving ability. In this work, we analyze the order-preserving ability on the whole search space (global) and a sub-space of top architectures (local), and empirically show that the local order-preserving for current two-stage NAS methods still need to be improved. To rectify this, we propose a novel concept of Supernet Shifting, a refined search strategy combining architecture searching with supernet fine-tuning. Specifically, apart from evaluating, the training loss is also accumulated in searching and the supernet is updated every iteration. Since superior architectures are sampled more frequently in evolutionary searching, the supernet is encouraged to focus on top architectures, thus improving local order-preserving. Besides, a pre-trained supernet is often un-reusable for one-shot methods. We show that Supernet Shifting can fulfill transferring supernet to a new dataset. Specifically, the last classifier layer will be unset and trained through evolutionary searching. Comprehensive experiments show that our method has better order-preserving ability and can find a dominating architecture. Moreover, the pre-trained supernet can be easily transferred into a new dataset with no loss of performance.

The ultra-dense low earth orbit (UD-LEO) satellite network is being vigorously developed due to its great potential in providing global coverage and services. For the sake of improved network performance in resource-constrained satellite networks, multipath schemes are being explored. However, state-of-the-art multipath routing algorithms face the challenge when dealing with highly dynamic satellite network features (i.e., frequent traffic variation, link failures) and fail to exploit the simple grid topology to design fast yet efficient traffic engineering (TE) approaches. In this paper, we propose a novel distributed TE scheme called Flexible Satellite Traffic Engineering (FlexSATE), which leverages global path computation coupled with distributed local routing decisions to improve the overall load balancing performance for ultra-dense LEO satellite networks. By constructing a minimum-hop binary tree (MHBT), we propose an MHBT-based k-segment Routing algorithm, which is capable of promptly discovering routing paths with low latency, high diversity, and good load balancing. To further enhance network transmission performance, we employ supervised learning into dynamic rate adaption, where FlexSATE employs centralized offline learning to derive insights from the globally optimal routing strategy and utilizes distributed deployment to predict the optimal distribution of traffic in real time. Our simulation results on a real-world typical Walker-delta type LEO constellation with 720 satellites show that FlexSATE outperforms some existing approaches with superior robustness and flexibility.

Gradient estimation is critical in zeroth-order optimization methods, which aims to obtain the descent direction by sampling update directions and querying function evaluations. Extensive research has been conducted including smoothing and linear interpolation. The former methods smooth the objective function, causing a biased gradient estimation, while the latter often enjoys more accurate estimates, at the cost of large amounts of samples and queries at each iteration to update variables. This paper resorts to the linear interpolation strategy and proposes to reduce the complexity of gradient estimation by reusing queries in the prior iterations while maintaining the sample size unchanged. Specifically, we model the gradient estimation as a quadratically constrained linear program problem and manage to derive the analytical solution. It innovatively decouples the required sample size from the variable dimension without extra conditions required, making it able to leverage the queries in the prior iterations. Moreover, part of the intermediate variables that contribute to the gradient estimation can be directly indexed, significantly reducing the computation complexity. Experiments on both simulation functions and real scenarios (black-box adversarial attacks neural architecture search, and parameter-efficient fine-tuning for large language models), show its efficacy and efficiency. Our code is available at https://github.com/Thinklab-SJTU/ReLIZO.git.

Ultra-dense low earth orbit (LEO) satellite terrestrial networks (ULSNs) are considered as a crucial component of future six generation (6G) networks, offering ubiquitous and massive services for various applications. However, for the development of advanced physical layer technologies for ULSNs, a comprehensive link-level simulation tool that integrates up-to-date satellite communication protocols becomes paramount and is urgently needed. In this paper, we develop a versatile simulator for the link-level performance analysis of ULSNs under the prevalent digital video broadcasting (DVB) standards. We first establish a complete satellite-terrestrial microwave channel model, taking practical factors such as rain attenuation, cloud attenuation, and Doppler frequency shift into consideration. Subsequently, the whole physical layer modules tailored for satellite-terrestrial microwave communication are implemented, including diverse physical layer modulation and coding schemes (MCSs). Furthermore, we realize adaptive coding and modulation (ACM) for adaptive channel performance simulation. Finally, comparative performance analysis using the established channel model is conducted to demonstrate the effectiveness of different MCSs of DVB standards. The complete link-level performance analysis based on our self-developed simulator can advance the field of satellite-terrestrial microwave communication and provide valuable insights for further exploration of ULSNs.

Nowadays, the ultra-dense low earth orbit (LEO) satellite network has become an attractive solution for providing global Internet coverage and services. With the ever-increasing demand for higher transmission performance, multipath also attracts much attention due to its great potential. In this paper, we consider the multipath cooperative routing in the ultra-dense LEO satellite network. To cope with the high dynamics of the network environment, a deep reinforcement learning (DRL) empowered intelligent routing algorithm is proposed, where each satellite only observes the local network state and independently makes the next-hop forwarding decision. Meanwhile, the perceived conditions of each path are recorded hop by hop in a format-specific packet. In this way, multiple available paths can be found for cooperative transmission. To balance multipath load, an adaptive traffic scheduling scheme is further developed on the sender to adjust traffic distribution according to the varying path conditions, so that multiple sub-flows can be efficiently maintained. Simulation results show the superiority and the effectiveness of the proposed multipath cooperative routing scheme compared with other baseline schemes.

Ultra-dense low earth orbit (LEO) satellite network (UD-LSN) is one of the most promising architectures in the sixth-generation (6G) systems, providing several types of services with different service level agreements (SLAs). Network slicing technology effectively meets these SLAs by building multiple logical networks isolated from each other on the physical network. In the UD-LSN, due to the spatiotemporal variations of users and available satellites, it poses a considerable challenge to make dynamic slicing decisions individually for each LEO satellite. This paper proposes a two-layer dynamic reconfigurable radio access network (RAN) slicing architecture for the UD-LSN. We consider the characteristics of enhanced mobile broadband (eMBB) and ultra-reliable and low-latency communications (uRLLC) services and formulate a stochastic optimization problem to maximize the long-term slicing utility, which consists of resource utilization, throughput, and reconfiguration cost. The original problem is transformed into a Markov Decision Process (MDP) and solved with the Branch Dueling Q-Network (BDQ)-based dynamic reconfigurable RAN slicing (DRRS) algorithm in a large slicing window and the priority-based user access algorithm in a small time slot. The simulation results validate the effectiveness of the proposed two-layer DRRS strategy, which has a better performance in the slicing utility, resource utilization, and throughput.

As one of the most promising architecture in the evolving sixth-generation (6G) systems, ultra-dense low Earth orbit (LEO) satellite network (UD-LSN) is drawing increasing attention due to its global coverage and ubiquitous access. To ensure service continuity, mobility management with provision of seamless handover is crucial in the process of satellite and user movement. However, massive service requests and overlapped satellite coverage will result in frequent handovers and diversified options in the UD-LSN. Meanwhile, existing mobility management methods based on the terrestrial networks are difficult to make timely and effective decisions due to the limited deployments of ground stations. In light of this, we propose a two-layer grouping and clustering based mobility management architecture (GCMMA) for the UD-LSN to reduce the management complexity with supporting the flexible function configurations. Under the GCMMA, we design lightweight handover procedures for different scenarios according to the established handover model, which considers user aggregation and combines with the regularity of satellite motion. Simulation results validate the effectiveness of the proposed mechanism, which has a better performance in handover delays and signaling overheads.

With the rapid expansion of the scale of deployed low earth orbit (LEO) satellites, the ultra-dense LEO satellite-terrestrial integrated network (LTIN) is envisioned as a promising architecture in the sixth-generation (6G) system to implement seamless connectivity and high-speed data rate service. Especially for ultra-remote real-time services with long transmission distance and high delay requirements, the integrated network can guarantee its end-to-end service continuity. However, many challenges have been posed to the efficient resource orchestration for the service delivery, owing to the large scale, heterogeneity and high mobility of the integrated network. For each service, its data needs to go through a series of on-board processing, before being downloaded to the terrestrial network for further applications. To this end, service function chain (SFC), an ordered concatenation of network functions (NFs), is introduced to support service provision. By allocating the constituent NFs over the LTIN, we propose an efficient multiple service delivery scheme to minimize the overall delivery completion latency, while taking into account resource sharing and competition among multiple SFCs. First, we formulate the multiple SFC embedding problem as a noncooperative game that is further proved as the weighted potential game with at least one Nash equilibrium (NE). With the help of the proposed global coordination mechanism, we design two algorithms to obtain the NE. One is the best response (BR) algorithm with faster convergence, while the other is adaptive play (AP) algorithm with more capacity for best solutions. Then, the stochastic learning (SL) algorithm is proposed to adapt to network dynamics and reduce global information exchange. Finally, extensive simulations validate the convergence and effectiveness of the proposed algorithms.

Nowadays, the ultra-dense low earth orbit (LEO) satellite network has become a promising paradigm in the next generation mobile communication network. With the development of content centric communication, multicast technology also attracts much attention. In this paper, we consider the downlink multicast transmission in the ultra-dense LEO satellite network. Multiple LEO satellites provide multicast service for multiple ground user (GU) groups under their coverage, where each GU group requests the same content. To improve the multicast performance, we propose an optimal subchannel allocation and beamforming scheme to maximize the system max-min fair (MMF) capacity of GUs. By leveraging the many-to-many matching model, we obtain the optimal subchannel allocation solution, and we propose a successive convex approximation (SCA) based algorithm for the downlink beamforming in the matching process. The many-to-many matching algorithm is convergent to a stable solution after finite iterations. Simulation results show the superiority and the effectiveness of the proposed subchannel allocation and beamforming method compared with other baseline schemes.

Recently, the rapid-developed mega low earth orbit (LEO) satellite constellation has shown its great potential in cooperating with terrestrial networks to provide seamless global connectivity and high-speed data rate services. However, the heterogeneity of physical resources and diversity of service demands pose challenges for delivering service in an efficient way in the ultra-dense LEO satellite-terrestrial integrated networks (LTIN). When implementing service delivery, service data generally needs a series of on-board processing and then downloading to the terrestrial network for further applications. In this paper, we introduce service function chain (SFC), a sequence of network functions, to process the data on board and propose an efficient multiple service delivery scheme in the LTIN to minimize the total delivery completion time. Considering the heterogeneous resource sharing and competition among multiple SFCs, we formulate the problem as a noncooperative game, which is further proved as a weighted potential game. We design an improved response (IR) algorithm with fast convergence and an adaptive play (AP) algorithm to find the best Nash equilibrium (NE). Extensive simulation results validate the convergence and effectiveness of the proposed algorithms.

Lithium-ion batteries have been widely used as the energy storage systems in electric vehicles. State of Charge (SOC) is one of the most important characteristics of battery system. It is essential for efficient use of the battery and ensures the safety of the electric vehicle. In this paper, a nonlinear autoregressive with exogenous inputs neural network (NARXNN) architecture is designed to estimate the SOC. The proposed method requires no model or knowledge of battery's internal parameters, but rather uses the battery's voltage, charge/discharge currents in various ambient temperature to accurately estimate battery's SOC. An unscented Kalman filter is used to reduce the errors in the neural network-based SOC estimation. The adaptability, efficiency, and robustness of the model are evaluated using the FUDS, US06 and DST driving cycles at varying temperatures conditions. The results prove that the proposed NARXNN-UKF model achieves higher accuracy with less computational time under different temperature conditions and electric vehicle driving cycles.

Software cache-coherent systems using programmable protocol processors provide a flexible infrastructure to expand the systems in size and function. However this flexibility comes at a cost in performance. First, the software implementation of protocols is inherently slower than a hardware implementation. Second, when multiple processors share a protocol processor, contention may result in a substantial increase in memory latency. In this paper, we study how the overhead of a software scheme can be reduced in the context of a shared- memory system consisting of SMP clusters. We study various design choices including hardware assists such as forwarding logic in the protocol processor and software hints through explicit communication primitives. We conduct our experiments via trace-driven simulation and compare the execution of three programs from the SPLASH-2 suite. We found that small cluster sizes (up to 4 processors/node) work well for both hardware and software implementations. When the forwarding logic is incorporated with the software scheme, the performance is competitive to that of the hardware scheme. When enhanced further by explicit communication primitives, the software scheme can perform even better than a pure hardware implementation. This is particularly noticeable when the network latency is high.

Recent developments in shared-memory multiprocessor systems advocate using off-the-shelf hardware to provide basic communication mechanisms and using software to implement cache coherence policies. The exposure of communication mechanisms to software opens many opportunities for enhancing application performance. In this paper we propose a set of communication primitives implemented on a communication co-processor that introduce a flavor of message passing and permit protocol optimization. To assess the overhead of the software implementation of the primitives and protocols, we compare a PRAM model, a hardware cache coherence scheme, a software scheme implementing only the basic cache coherence protocol, and an optimized software solution supporting the additional communication primitives and running with applications annotated with those primitives. With the parameters we chose for the communication processor, the overall memory system overhead of the basic software scheme is at least 50% higher than that of the hardware implementation. With the adequate insertion of the communication primitives, the optimized software solution has a performance comparable to that of the hardware scheme.

This paper investigates the performance of shared-memory cluster-based architectures where each cluster is a shared-bus multiprocessor augmented with a protocol processor maintaining cache coherence across clusters. For a given number of processors, sixteen in this study, we evaluate the performance of various cluster configurations. We also consider the impact of adding a remote shared cache in each cluster. We use Mean Value Analysis to estimate the cache miss latencies of various types and the overall execution time. The service demands of shared resources are characterized in detail by examining the sub-requests issued in resolving cache misses. In addition to the architectural system parameters and the service demands on resources, the analytical model needs parameters pertinent to applications. The latter, in particular cache miss profiles, are obtained by trace-driven simulation of three benchmarks.Our results show that without remote caches the performance of cluster-based architectures is mixed. In some configurations, the negative effects of the longer latency of inter-cluster misses and of the contention on the protocol processor are too large to counter-balance the lower contention on the data buses. For two out of the three applications best results are obtained when the system has clusters of size 2 or 4. The cluster-based architectures with remote caches consistently outperform the single bus system for all 3 applications. We also exercise the model with parameters reflecting the current trend in technology making the processor relatively faster than the bus and memory. Under these new conditions, our results show a clear performance advantage for the cluster-based architectures, with or without remote caches, over single bus systems.

The simulation of parallel architectures requires an enormous amount of CPU cycles and, in the case of trace-driven simulation, of disk storage. In this paper, we consider the evaluation of the memory hierarchy of multiprocessor systems via parallel trace-driven simulation. We refine Lin et al.[8] original algorithm, whose main characteristic is to insert the shared references from every trace in all other traces, by reducing the amount of communication between simulation processes. We have implemented our algorithm on a KSR-1. Results of our experiments on traces of four applications and three different cache coherence protocols show that parallel trace-driven simulation yields significant speedups over its sequential counter-part. The communication overhead is not substantial compared to the dominant overhead due to the processing of replicated inserted references. We also investigate filtering techniques and show how to filter in parallel private and shared references for various block sizes in one pass. Simulation of filtered traces is faster but with a lower speedup.

The efficiency of the basic operations of a NUMA (nonuniform memory access) multiprocessor determines the parallel processing performance on a NUMA multiprocessor. The authors present several analytical models for predicting and evaluating the overhead of interprocessor communication, process scheduling, process synchronization, and remote memory access, where network contention and memory contention are considered. Performance measurements to support the models and analyses through several numerical examples have been done on the BBN GP1000, a NUMA shared-memory multiprocessor. Analytical and experimental results give a comprehensive understanding of the various effects, which are important for the effective use of NUMA shared-memory multiprocessor. The results presented can be used to determine optimal strategies in developing an efficient programming environment for a NUMA system.>