Function as a Service (FaaS) is a popular cloud computing service model that incorporates an auto-scaling mechanism, enabling applications to dynamically adjust computing resources, achieving rapid response to load changes and efficient resource utilization. However, the limited resource allocation mode for function containers can frequently cause function performance degradation before scaling is complete, so some FaaS platforms address this issue by default through a shared-resource mode. But existing constant target load-based autoscalers fail to perceive node-level load under this mode, leading to numerous scaling decisions to nodes that have already reached their load bottlenecks, without bringing actual resource or performance gains. This makes the system underutilized and even degrades its performance. To solve this issue, in this paper, we design a horizontal autoscaler, NDScaler, which efficiently scales functions in shared-resource mode by using the node load-aware scaling strategy, thereby eliminating invalid scaling behaviours and the resulting degradation of function performance. We implement this strategy through the proposed node load-aware and dynamic target load algorithm, which models the scale-up problem as a load transfer problem between nodes and functions and adopts a greedy search strategy to identify the optimal target functions for scale-up. Furthermore, it introduces a dynamic load target to assess the extent of load reduction for functions and accurately scales functions down. We have implemented NDScaler and evaluated it in detail on the OpenFaaS platform. Experimental results show that, compared with existing methods, NDScaler can ensure scaling effectiveness and achieve high-efficiency scaling in both simple single-function scenarios and complex multifunction scenarios, effectively improving function throughput while significantly reducing latency.

Semi-supervised 3D object detection has gained significant attention due to its potential to mitigate the heavy reliance on extensive annotations in traditional 3D object detection methodologies. Most existing approaches leverage the teacher’s predictions to guide and refine the student’s predictions while discarding low-confidence predictions using a fixed threshold. However, the presence of imbalanced variance in object scale poses challenges as different objects often exhibit varying levels of detection difficulty. Current methods relying on pseudo labels struggle to comprehensively capture information pertaining to objects across diverse scales. To address these challenges, we propose CSD3D, a cross-scale distillation approach via dual-consistency learning. CSD3D encompasses cross-scale distillation between the teacher and student as well as within the student itself, thereby enhancing the algorithm’s resilience to scale variance. Moreover, by adopting a dual-consistency learning paradigm that incorporates supervision at both feature and prediction levels, our approach provides comprehensive guidance to the student model. This integration of dual-consistency learning within cross-scale conditions is conducive to comprehending cross-scale object features and maintaining scale-consistent predictions. Rigorous experiments performed on the ScanNet and SUN RGB-D benchmarks reveal that CSD3D attains state-of-the-art performance. By utilizing a mere 10% of labeled data on ScanNet, we observe absolute improvements of 3.8 and 3.5 in [email protected] and [email protected], respectively.

New generation airborne embedded system has deployed Graphical Processing Units (GPUs) to raise processing capability to meet growing computational demands. Comparing with the cloud system, the airborne embedded system usually has a fixed application set, but strict real-time constraints. Unfortunately, the inherent GPU scheduler does not consider the application priority, which cannot provide the sufficient real-time capability to the airborne embedded system. To meet timeliness requirements, it is necessary to predict timing behaviors of those applications and design a real-time scheduling policy based on priority and deadline. We therefore propose WAMP2S, a workload-aware GPU performance model based pseudo-preemptive real-time scheduling algorithm for the airborne embedded system. The workload-aware GPU performance model can accurately predict the execution time of an application, which is running concurrently with other applications on GPU. The pseudo-preemptive real-time scheduling algorithm can provide the approximate preemption by dynamically adjusting GPU computing resources for active applications. Unlike previous work on GPU performance model and GPU real-time scheduling, WAMP2S considers the impact of co-executing workload on the execution time estimation and provides a software-only approach for preemption support. In addition, WAMP2S implements a prototype GPU scheduler without any source code analysis. We evaluate the proposed GPU performance model and real-time scheduling algorithm in both simulated and realistic application sets. Experimental results illustrate that WAMP2S can achieve low prediction error and high scheduling success ratio.

New generation airborne embedded system has deployed Graphical Processing Units (GPUs) to raise processing capability to meet growing computational demands. Applications in the airborne embedded system have strict real-time constraints. Therefore, it is necessary to accurately predict timing behaviors of those applications. Many previous work propose GPU performance models to estimate the execution time of applications. However, most of those models do not consider the impact of co-execution on the GPU performance. In this paper, we propose a workload-aware GPU performance model to predict the execution time of applications executed concurrently on a single GPU. Experimental results illustrate that the proposed model can achieve a 5.1%-11.6% prediction error in a real airborne embedded hardware platform.