Springer Science and Business Media LLC

This research is to design an effective prefetching method required for hybrid main memory systems consisting of dynamic random-access memory (DRAM) and phase-change memory (PCM) components, which can be especially used for big data applications and massive-scale computing environment. Conventional prefetchers perform adequately for regular memory access patterns. However, graph processing applications show extremely irregular memory access characteristics, causing some difficulty in predicting accurate prefetching operation. Therefore, an effective dynamical prefetching algorithm based on the regression method is proposed in this study. We have designed an intelligent prefetch engine that can identify any dynamic accessing characteristics in memory accessing sequences. Specifically, it can select regular, linear, or polynomial regression predictive analysis based on the memory access sequence characteristics, and also dynamically determine the number of pages required for any selected prefetching. We also present a DRAM-PCM hybrid memory structure that can reduce the energy consumption and resolve the thermal issue that hampers conventional DRAM memory systems. Experimental results indicate that the performance can increase by around 40%, compared to that of conventional DRAM memory structures.

Process scheduling techniques consider the current load situation to allocate computing resources. Those techniques make approximations such as the average of communication, processing, and memory access to improve the process scheduling, although processes may present different behaviors during their whole execution. They may start with high communication requirements and later just processing. By discovering how processes behave over time, we believe it is possible to improve the resource allocation. This has motivated this paper which adopts chaos theory concepts and nonlinear prediction techniques in order to model and predict process behavior. Results confirm the radial basis function technique which presents good predictions and also low processing demands show what is essential in a real distributed environment.

Because in-house debugging and test are difficult to discover all potential data races in multicore programs, it is necessary and significant to tolerate the potential data races in the production-run phase to secure the correct execution. However, the existing tolerating methods are limited to some kinds of data races. This paper proposes a new data-race tolerating approach, which can detect and adjust the data races whether it is in the protection of critical section or lack of protection to improve the correctness of multicore programs. It uses sliding windows to accommodate the memory instructions in critical section or recent memory instructions lack of protection and detects the potential data races which are more likely to cause errors. Then, by delaying the critical reversion points, data races are adjusted to reduce the probability of software failure. To implement the tolerating approach, the current multicore processor need not change its original cache coherence protocol and just adds very little hardware. Simulation results show that it brings low hardware, low bandwidth overhead, and negligible slowdown.

Blendshape technique is an effective tool in the computer facial animation. Every character requires its own unique blendshapes to cover numerous facial expressions in the Visual Effects industry. Despite outstanding advances in this area, existing techniques still need a professional artist’s intuition and complex hardware. In this paper, we propose a framework for customizing blendshapes to capture facial details. The suggested method primarily consists of two stages: Blendshape generation and Blendshape augmentation. In the first stage, localized blendshapes are automatically generated from real-time captured faces with two methods: linear regression and an autoencoder Han (in: IEEE International Conference on Big Data and Smart Computing (BigComp) 2021) (2021). In our experiment, face construction with the former outperforms that of the later method. However, generated blendshapes are slightly missing the source features, especially mouth movements. To overcome this, in the last stage, we extend Han (in: IEEE International Conference on Big Data and Smart Computing (BigComp) 2021), (2021) by adding a blendshape incrementally to minimize erroneous expression transfer.

Một cách tiếp cận tự động hóa tế bào (CA) được đề xuất để mô phỏng dòng chảy chất lỏng qua các vật liệu xốp với các kênh quanh co ở mức độ lỗ chân lông. Cách tiếp cận này nhằm kết hợp các phương pháp CA để xây dựng đại diện máy tính của hình thái vật liệu xốp và để mô phỏng dòng chảy chất lỏng qua nó. Đại diện hình thái được thu được bằng cách sử dụng CA, sự tiến hóa của nó thể hiện sự tự tổ chức và dẫn đến cấu hình ổn định. Cấu hình này sau đó được sử dụng cho ứng dụng Lattice Gas CA để mô phỏng dòng chảy chất lỏng qua mẫu vật liệu xốp và tính toán các đặc tính thấm của nó. Các điều kiện biên đặc biệt được giới thiệu cho phép sự khác biệt về độ nhẵn của bề mặt tường lỗ rỗng rắn. Mô hình đã được thử nghiệm trên một mảnh 2D nhỏ trong máy tính cá nhân và sau đó được triển khai để nghiên cứu một điện cực carbon xốp của pin nhiên liệu hydro trên 128 bộ xử lý của một cụm đa xử lý.

Using attribute graphs for node embedding to detect community structure has become a popular research topic. However, most of the existing algorithms mainly focus on the network structure and node features, which ignore the higher-order relationships between nodes. In addition, only adopting the original graph structure will suffer from sparsity problems, and will also result in suboptimal node clustering performance. In this paper, we propose a hypergraph network embedding (HGNE) for community detection to solve the above problems. Firstly, we construct potential connections based on the shared feature information of the nodes. By fusing the original topology with feature-based potential connections, both the explicit and implicit relationships are encoded into the node representations, thus alleviating the sparsity problem. Secondly, for integrating the higher-order relationship, we adopt hypergraph convolution to encode the higher-order correlations. To constrain the quality of the node embedding, the spectral hypergraph embedding loss is utilized. Furthermore, we design a dual-contrast mechanism, which draws similar nodes closer by comparing the representations of different views. This mechanism can efficiently prevent multi-node classes from distorting less-node classes. Finally, the dual-contrast mechanism is jointly optimized with self-training clustering to obtain more robust node representations, thus improving the clustering results. Extensive experiments on five datasets indicate the superiority and effectiveness of HGNE.

The majority of today's Internet applications relies on point-to-point communication. In recent years, however, multipoint communication support has become the foundation for such applications as multiparty video conferencing, distributed interactive simulations, and collaborative systems. We describe a novel protocol to coordinate multipoint groupwork within the IP-multicast framework. The protocol supports Internet-wide coordination for large and highly-interactive groupwork, relying on the dissemination of coordination directives among group members across a shared end-to-end multicast tree. We also describe how addressing extensions to IP multicast can be used for our multisite coordination mechanism.