MoveMethod is a hallmark refactoring. Despite a plethora of research tools that recommend which methods to move and where, these recommendations do not align with how expert developers perform Movemethod. Given the extensive training of Large Language Models and their reliance upon naturalness of code, they should expertly recommend which methods are misplaced in a given class and which classes are better hosts. Our formative study of 2016 LLM recommendations revealed that LLMs give expert suggestions, yet they are unreliable: up to 80 % of the suggestions are hallucinations. We introduce the first LLM fully powered assistant for MoveMethod refactoring that automates its whole end-to-end lifecycle, from recommendation to execution. We designed novel solutions that automatically filter LLM hallucinations using static analysis from IDEs and a novel workflow that requires LLMs to be self-consistent, critique, and rank refactoring suggestions. As MoveMethod refactoring requires global, project-level reasoning, we solved the limited context size of LLMs by employing refactoring-aware retrieval augment generation (RAG). Our approach, MM-assist, synergistically combines the strengths of the LLM, IDE, static analysis, and semantic relevance. In our thorough, multi-methodology empirical evaluation, we compare MM-assist with the previous state-of-the-art approaches. MMASSIST significantly outperforms them: (i) on a benchmark widely used by other researchers, our Recall@1 and Recall@3 show a$1.7 x$improvement; (ii) on a corpus of 210 recent refactorings from Open-source software, our Recall rates improve by at least$\mathbf{2. 4 x}$. Lastly, we conducted a user study with$\mathbf{3 0}$experienced participants who used MM-ASSIST to refactor their own code for one week. They rated$\mathbf{8 2. 8 \%}$of MM-aSSIST recommendations positively. This shows that MM-ASSIST is both effective and useful.

In the context of open science, the management of metadata is essential for promoting research data utilization. Experimental scientists are required to manage a substantial volume of experimental data, including a significant proportion of failed data. This places a considerable burden on the experimental scientists. In this paper, we outline the development of a conceptual image for a data aggregation and management infrastructure for core facilities. The infrastructure enables an automatic assignment of unique identifier and metadata, optimizing research data management of experimental scientists.

Research must be reproducible to be verifiable. Provenance, which describes how data was produced, is one of the metadata that can improve reproducibility. In this paper, we propose a method to construct the provenance of research data produced in high-performance computing (HPC) systems. Our method can construct a high-level and user-perspective provenance by integrating information available in HPC systems, such as a workload manager, with low-level data about running programs' behavior captured in an operating system kernel. The method enables users of HPC systems to collect the provenance without modifying assets such as programs and scripts.

Spiking neural networks (SNNs) are expected to be energy efficient when implemented on dedicated hardware. However, fully exploiting SNN’s characteristics such as event-driven communications challenges on circuit designers and manufacturers. In this paper, inspired by the recent success of an artificial neural network (ANN) based system, known as charge-domain computing (CDC), we propose a novel framework for SNNs called “RC-Spike.” As CDC, RC-Spike uses a two-phase system: input spikes are received in the accumulation phase, and a neuron produces a spike in the spike generation phase. In RC-Spike, synaptic currents are accumulated with resistively coupled synapses, with which circuit implementation can be simplified compared with CDC circuits. Because of this resistive coupling effect, a neuron in RC-Spike does not compute an exact dot product. However, RC-Spike can be successfully trained in the framework of SNNs, and we show that the learning performance of RC-Spike is as high as ANNs on the MNIST and Fashion-MNIST datasets.

In 5G, the network is divided into slices to provide communications with different characteristics, such as low latency and reliable communications (URRLC), multiple connections (MTC), and high speed and high capacity communications (eMBB), for different applications. Although the selection of network slices is often static, in practice, dynamic slice selection is required depending on the application situation. However, there are issues such as the slice change itself changing the application situation and the delay associated with the slice change. In this paper, we realize dynamic slice selection by recognizing the rough situation and the mapping between the recognized situation and the slice. The Bayesian Attractor Model (BAM) is used for recognition to achieve consistent recognition and is extended to the Dirichlet Process Mixture Model (DPMM) to achieve automatic attractor construction. The mapping between situations and slices is also automatically learned by using feedback. As an application of dynamic slice selection, we also show slice selection based on the video streaming situation. Through numerical examples, we show that our method can keep the quality of video streaming high while reducing slice changes.

Network virtualization is expected to handle various forms of network traffic induced by Internet of Things applications and other Internet-based services. Because traffic patterns change with time, virtual networks should be dynamically reconstructed to accommodate increasing traffic and to free unused resources. However, collecting all traffic information is difficult when applications are deployed on a wide-area network. It is therefore necessary to consider uncertainty of information due to data incompleteness or traffic dynamics. Our research group has proposed a virtual network reconstruction method based on a Bayesian attractor model that deals with uncertain information in decision-making. However, this method requires advance knowledge of the assumed environment as an attractor. When the environment changes, attractors must also be changed. In this study, we use control feedback to automatically update attractors when the environment changes. Simulation-based evaluations demonstrate that the proposed method deals with unknown situations while maintaining noise tolerance.

We propose a multi-plane isomorphic network that increases network throughput and reduces network latency by effectively configuring multi-plane networks. In the proposed network, each plane adopts the same graph topology but different switch-to-switch connections. We evaluate the dual-plane isomorphic hypercube network by graph analysis and cycle level simulation. Results of the graph analysis show that the dual-plane isomorphic 8-hypercube reduces the average shortest path length by 22% and improves throughput by 28% compared with the dual-plane hypercube. Similar improvements are confirmed from the results of the cycle level simulation. We also examine the dual-plane isomorphic folded-hypercube network. Finally, we discuss the effect of longer cable length caused by the isomorphic network on the network cost and latency.

Network Function Visualization (NFV) is becoming a new networking architecture for telecom carriers. NFV achieves network functions with software and commercial off the shelf (COTS) servers instead of dedicated hardware. While the software-based approach is expected to reduce costs, it could cause performance issues. CPU-FPGA tightly coupled architectures may be available in COTS servers in the near future. This paper proposes accelerating NFV application leveraging such a CPU-FPGA architecture. The proposed method of acceleration uses a data plane development kit (DPDK) ring queue, which is often used in network software, as the communication interface between the FPGA and CPU. We propose two optimizations for ring operation and table lookup operation to efficiently use the bus between FPGA and CPU. We evaluated the proposed method with an actual CPU+FPGA based platform, and an NFV application, i.e., vCPE. The results revealed that the evaluation system could accommodate 2 × 40-GbE Internet traffic, and could increase capacity as a vCPE server by x1.33.

Technology trends are not only transforming the hardware landscape of end-user devices but are also dramatically changing the types of software applications that are deployed on these devices. With the maturity of cloud computing during the past few years, users increasingly rely on networked applications that are deployed in the cloud. In particular, new applications will emerge where user interactions will be based on real-time continuous media streams instead of the traditional request-response types of interfaces. Furthermore, many of these applications will be multi-user streaming media based interactions instead of a single user interaction with an application. In this paper, we propose a geographic location-aware, hybrid, scalable cloud assisted peer-to-peer (P2P) architecture to support such applications that targets low administration cost, reduced bandwidth consumption, low latency, low initial investment cost and optimized resource usage. The main objective is to develop an efficient media delivery system that leverages locality. We propose a 3-layer novel architecture that uses at the core the cloud for application management, 2-tier edge cloud for supporting geo-dispersed user groups, and at the lowest level peer-to-peer dynamic overlays for locally clustered user groups. The proposed architecture manages multiple streaming sessions simultaneously and each streaming session is an independent entity. Our experiments on PlanetLab show that the dynamic construction and maintenance of delivering streams at both the user-level P2P overlay and edge cloud are indeed feasible and effective.

A parallel computer Cenju-4 is a cache-coherent non-uniform memory access (ccNUMA) multiprocessor and designed to be scalable up to 1024 nodes. For scalability, Cenju-4 adopts a bit-pattern directory. This scheme enables more precise representation than other imprecise schemes, such as a coarse vector scheme. Cenju-4 utilizes multicast and gathering functions of the network for delivering invalidation request messages and for collecting replies. This enables store access latency to be scalable, even when the block is shared among all nodes. Cenju-4 also prevents starvation and deadlock by queuing certain types of messages in the main memory. This enables a full solution to the starvation problem with centralized directory scheme, and to the deadlock problem with one physical or virtual network. The buffer sizes required for queuing messages at each node are only 32K bytes and two 64K bytes on a 2024-node system. In this paper, we present the design of the DSM architecture and some performance results.