Coarse-Grained Reconfigurable Arrays (CGRAs) play an important role in accelerating computation-intensive applications due to their flexibility and power efficiency. Most existing mapping works for CGRA assume that all the data of a loop kernel can be previously moved from DRAM to ScratchPad Memory (SPM) with one data transfer. However, when targeting low-power CGRAs, the SPM can hardly hold the entire data even for a small loop kernel, and it inevitably incurs multiple data transfers, leading to notable costs. In this case, where and how to perform data transfer considering the DRAM access behavior is crucial to the overall execution performance. To this end, this paper proposes a data transfer optimization method to simultaneously optimize loop pipelining and data transfer. Since there is an interplay between loop structure and data transfer, we establish an optimization problem considering both polyhedral transformation and transfer strategy exploration, offering opportunities to find the near-optimal data transfer strategy within the search space. The experimental results show that compared with existing methods, our method can achieve 1.36×–4.55× speedup for loop kernels with different on-chip buffer sizes, and only increase the compilation time by a small amount.

Widely adopted for their scalability and flexibility, modern microservice systems present unique failure diagnosis challenges due to their independent deployment and dynamic interactions. This complexity can lead to cascading failures that negatively impact operational efficiency and user experience. Recognizing the critical role of fault diagnosis in improving the stability and reliability of microservice systems, researchers have conducted extensive studies and achieved a number of significant results. This survey provides an exhaustive review of 98 scientific papers from 2003 to the present, including a thorough examination and elucidation of the fundamental concepts, system architecture, and problem statement. It also includes a qualitative analysis of the dimensions, providing an in-depth discussion of current best practices and future directions, aiming to further its development and application. In addition, this survey compiles publicly available datasets, toolkits, and evaluation metrics to facilitate the selection and validation of techniques for practitioners.

Multi-Agent Path Finding (MAPF), which focuses on finding collision-free paths for multiple robots, is crucial for applications ranging from aerial swarms to warehouse automation. Solving MAPF is NP-hard so learning-based approaches for MAPF have gained attention, particularly those leveraging deep neural networks. Nonetheless, despite the community’s continued efforts, all learning-based MAPF planners still rely on decentralized planning due to variability in the number of agents and map sizes. We have developed the first centralized learning-based policy for MAPF problem called RAILGUN. RAILGUN is not an agent-based policy but a map-based policy. By leveraging a CNN-based architecture, RAILGUN can generalize across different maps and handle any number of agents. We collect trajectories from rule-based methods to train our model in a supervised way. In experiments, RAILGUN outperforms most baseline methods and demonstrates great zero-shot generalization capabilities on various tasks, maps and agent numbers that were not seen in the training dataset.

Network failure diagnosis is challenging yet critical for high-performance computing (HPC) systems. Existing methods cannot be directly applied to HPC scenarios due to data heterogeneity and lack of accuracy. This paper proposes a novel framework, called ClusterRCA, to localize culprit nodes and determine failure types by leveraging multimodal data. ClusterRCA extracts features from topologically connected network interface controller (NIC) pairs to analyze the diverse, multimodal data in HPC systems. To accurately localize culprit nodes and determine failure types, ClusterRCA combines classifier-based and graph-based approaches. A failure graph is constructed based on the output of the state classifier, and then it performs a customized random walk on the graph to localize the root cause. Experiments on datasets collected by a top-tier global HPC device vendor show ClusterRCA achieves high accuracy in diagnosing network failure for HPC systems. ClusterRCA also maintains robust performance across different application scenarios.

Timely detection of performance regression issues is critical to ensuring the stability and user experience of software systems. Traditional methods often rely on high-quality annotated data or data distribution assumptions, which cannot effectively adapt to performance changes in dynamic workload environments. To solve this problem, we propose DynamicRegress, a performance regression detection method based on Siamese network and semi-supervised learning. DynamicRegress integrates multi-dimensional key performance indicators (KPIs) with workload context to accurately characterize system states and detect performance regressions in real time. By employing a dual weight-shared LSTM network, DynamicRegress reduces training complexity while retaining strong feature extraction capabilities. Data augmentation and a weighted loss function are incorporated to enhance the learning of minority regression cases, mitigating the class imbalance issue. Additionally, a semi-supervised learning strategy generates high-quality pseudo-labels to expand the training dataset, effectively addressing the challenge of limited labeled data. Experiments on production data from a top-tier global cloud service provider demonstrate that DynamicRegress achieves a superior F1 Score of 0.958 (outperforming the best baseline method by 0.282) while maintaining a low detection latency of 0.006 seconds per KPI pair. DynamicRegress provides a robust adaptive solution for performance regression detection in dynamic and complex software systems, and we have made the code publicly available to facilitate further research.

Multi-Agent Path Finding (MAPF), which focuses on finding collision-free paths for multiple robots, is crucial for applications ranging from aerial swarms to warehouse automation. Solving MAPF is NP-hard so learning-based approaches for MAPF have gained attention, particularly those leveraging deep neural networks. Nonetheless, despite the community's continued efforts, all learning-based MAPF planners still rely on decentralized planning due to variability in the number of agents and map sizes. We have developed the first centralized learning-based policy for MAPF problem called RAILGUN. RAILGUN is not an agent-based policy but a map-based policy. By leveraging a CNN-based architecture, RAILGUN can generalize across different maps and handle any number of agents. We collect trajectories from rule-based methods to train our model in a supervised way. In experiments, RAILGUN outperforms most baseline methods and demonstrates great zero-shot generalization capabilities on various tasks, maps and agent numbers that were not seen in the training dataset.

Memory partitioning is a widely used technique to reduce access conflicts on multi-bank memory in high-level synthesis. Previous memory partitioning methods mainly focus on a given access pattern extracted from stencil applications. Restricted by the pattern shape, these methods are prone to sub-optimal bank numbers or large overhead on address generation. In this work, we propose a pattern-morphing-based memory partitioning method, PMP, that only requires reduced hyperplane families to achieve the minimal bank number. To reduce the side effect of extra data padding, an integer linear programming problem is formulated for pattern morphing. Compared to the previous hyperplane-based memory partitioning, the experimental results show that our approach could achieve the optimal partition factor while saving 22% in LUTs, 21% in FlipFlops, 10% in DSPs, and 40% in memory overhead, on average.

Chain of thought (CoT) is a reasoning framework that can enhance the performance of Large Language Models (LLMs) on complex inference tasks.In particular, among various studies related to CoT, multi-path inference stands out as a simple yet effective improvement.However, there is no optimal setting for the number of inference paths.Therefore, we have to increase the number of inference paths to obtain better results, which in turn increases the inference cost.To address this limitation, we can utilize question-related role templates to guide LLMs into relevant roles, thereby increasing the possibility of correct inferences for each path and further reducing dependence on the number of inference paths while improving reasoning accuracy.However, placing LLMs into specific roles may reduce their reasoning diversity and performance on a few tasks where role dependence is low.To alleviate the excessive immersion of the LLM into a specific role, we propose Nash CoT by constructing a competitive system on each path that balances the generation from role-specific LLMs' and the general LLMs' generation, thereby ensuring both effective role adoption and diversity in LLM generation further maintaining the performance of multi-path inference while reducing the requirement of the number of inference paths.We evaluate Nash CoT across various inference tasks, including Arabic Reasoning, Commonsense Question Answering, and Symbolic Inference, achieving results that are comparable to or better than those of multi-path CoT with the equal number of inference paths.

Compared with rigid robots, soft robots have the advantages of inherent compliance, high adaptability, and impact tolerance. Many researchers are very interested in the motion design of soft robot underwater. In this paper, inspired by the method of octopus propulsion, a jet propulsion unit with 80% soft materials driven by pressure is designed. It can change the volume of its cavity to absorb and eject the fluid medium to make the robot move. According to the working characteristics of the jet unit, corresponding experiments are designed to analyze its force output, deformation, ejection flow, and pressure response characteristics. In order to expand the motion space of the robot, a buoyancy unit is designed to control the depth of the robot in the water. Three jet units and a buoyancy element are combined into a tetrahedron robot - jet soft robot (JSR). The feasibility of its motion is verified by experiments. Compared with other similar jet robots, the biggest feature of this robot is that the drive unit can bend or twist roughly along the centerline, which can prevent accidental collision and damage.

Proactive failure detection of instances is vitally essential to microservice systems because an instance failure can propagate to the whole system and degrade the system's performance. Over the years, many single-modal (i.e., metrics, logs, or traces) databased anomaly detection methods have been proposed. However, they tend to miss a large number of failures and generate numerous false alarms because they ignore the correlation of multimodal data. In this work, we propose AnoFusion, an unsupervised failure detection approach, to proactively detect instance failures through multimodal data for microservice systems. It applies a Graph Transformer Network (GTN) to learn the correlation of the heterogeneous multimodal data and integrates a Graph Attention Network (GAT) with Gated Recurrent Unit (GRU) to address the challenges introduced by dynamically changing multimodal data. We evaluate the performance of AnoFusion through two datasets, demonstrating that it achieves the F1-score of 0.857 and 0.922, respectively, outperforming the state-of-the-art failure detection approaches.

To ensure the performance of large-scale datacenters, operators need to monitor up to tens of millions of various-type KPIs, e.g., CPU utilization, memory utilization. For each KPI, it is crucial but challenging to detect outliers that deviate from its historical patterns or the patterns of other KPIs in the same period. In this work, we proposeOutSpot, an unsupervised outlier detection framework that integrates hierarchical agglomerative clustering (HAC) with conditional variational autoencoder (CVAE), which significantly improves computational efficiency and comprehensively learns the above two patterns. Additionally, two simple yet effective techniques, soft threshold and median filter, are applied to precisely determine outlier KPIs. Using two real-world datasets collected from the datacenters owned by a top-tier global short video service provider and a top-tier domestic operator,respectively. It demonstrates thatOutSpotachieves the best F1 score of 0.95 and 0.91, AUC of 0.99 and 0.99 on the two datasets, significantly outperforming seven baseline outlier detection methods.

The Moderate Resolution Imaging Spectroradiometer (MODIS) is one of the primary instruments in the National Aeronautics and Space Administration Earth observing system. The first MODIS instrument was launched in December, 1999 onboard the Terra spacecraft. MODIS has 36 bands, covering a wavelength range 0.4-14.4 μm. MODIS band 27 (6.72 μm) is a water vapor band, which is designed to be insensitive to Earth surface features. In recent Earth view images of Terra band 27, surface feature contamination is clearly seen with pronounced striping. In this paper, it is shown that these band-27 issues are caused by electronic crosstalk from bands 28-30. An algorithm using a linear approximation is developed to correct the crosstalk effect. The crosstalk coefficients are derived from Terra MODIS lunar observations. They show that the crosstalk is strongly detector-dependent and the crosstalk pattern has changed in a noticeable fashion since launch. The crosstalk contributions were positive to the instrument response of band 27 early in the mission but became negative and much larger in magnitude at later stages of the mission for most detectors of the band. The algorithms are applied to both the black body (BB) calibration and the MODIS L1B calibrated products. With the crosstalk effect significantly removed, the calibration coefficients of Terra MODIS band 27 derived from the BB show that the detector differences become smaller. With the algorithms applied to MODIS L1B products, the Earth surface features are significantly removed, thereby restoring the radiometric balance of the band and substantially reducing the striping features in the image.

In this work, we present SlideType, an intuitive text-entry system on touchscreen devices with touch and gestural inputs as well as visual and auditory output to be used by as many people as possible, including those have vision, dexterity and cognition impairments. 9 participants were tested using SlideType to input a name such as "John Smith" without training. Overall, participants were able to complete the task of typing and editing. We reported some usability study results.

Current accessible voting machines require many voters with visual, cognitive and dexterity limitations to vote with assistance, if they can vote at all. To address accessibility problems, we developed the EZ Ballot. The linear layout of the EZ ballot structure fundamentally re-conceptualizes ballot design to provide the same simple and intuitive voting experience for all voters, regardless of ability or input/output (I/O) device used. Further, multimodal I/O interfaces were seamlessly integrated with the ballot structure to provide flexibility in accommodating voters with different abilities.