Dimosthenis Masouros

The rapid evolution of Artificial Intelligence (AI) and Machine Learning (ML) has significantly heightened computational demands, particularly for inference-serving workloads. While traditional cloud-based deployments offer scalability, they face challenges such as network congestion, high energy consumption, and privacy concerns. In contrast, edge computing provides low-latency and sustainable alternatives but is constrained by limited computational resources. In this work, we introduce SynergAI , a novel framework designed for performance- and architecture-aware inference serving across heterogeneous edge-to-cloud infrastructures. Built upon a comprehensive performance characterization of modern inference engines, SynergAI integrates a combination of offline and online decision-making policies to deliver intelligent, lightweight, and architecture-aware scheduling. By dynamically allocating workloads across diverse hardware architectures, it effectively minimizes Quality of Service (QoS) violations. We implement SynergAI within a Kubernetes-based ecosystem and evaluate its efficiency. Our results demonstrate that architecture-driven inference serving enables optimized and architecture-aware deployments on emerging hardware platforms, achieving an average reduction of 2.4× in QoS violations compared to a State-of-the-Art (SotA) solution.

High-Level Synthesis (HLS) streamlines FPGA programming by abstracting low-level hardware complexities, facilitating rapid microarchitecture customization through the use of directives. However, identifying optimal directives remains a significant challenge, particularly for software developers without extensive hardware expertise. HLS-driven Design Space Exploration (DSE) addresses this challenge by automating the generation of directive configurations through a variety of techniques. The effectiveness of these methods heavily relies on the quality of the data on which they are built. Unfortunately, existing datasets are often constrained in scope, complexity, and device diversity. To address these limitations, we present GNΩSIS, ¹ the largest open-source HLS dataset, to the best of our knowledge, containing almost 219K design points generated from prominent benchmark suites and public repositories. The dataset covers two FPGAs with varying resource characteristics and three clock frequencies. Additionally, we introduce a versatile framework to automate design point generation. We evaluate the impact of frequency scaling, FPGA architecture, and optimization targets on Quality of Result (QoR) metrics, analyze HLS directive effectiveness across code constructs, and study design transferability across FPGAs and frequencies. These analyses provide practical insights into QoR and HLS behavior, offering guidance for designers with limited optimization experience. We believe GNΩSIS will enhance FPGA accessibility and act as an enabler for innovation in HLS-driven DSE research. The dataset is publicly accessible on Hugging Face, ² and the framework is available on GitHub. ³

Today, video analytics are becoming extremely popular due to the increasing need for extracting valuable information from videos available in public sharing services through camera-driven streams in IoT environments. To avoid data communication overheads, a common practice is to have computation close to the data source rather than Cloud offloading. Typically, video analytics are organized as separate tasks, each with different resource requirements (e.g., computational- vs. memory-intensive tasks). The serverless computing paradigm forms a promising approach for mapping such types of applications, enabling fine-grained deployment and management in a per-function, and per-device manner. However, there is a tradeoff between QoS adherence and resource efficiency. Performance variability due to function co-location and prevalent resource heterogeneity make maintaining QoS challenging. At the same time, resource efficiency is essential to avoid waste, such as unnecessary power consumption and CPU reservation. In this paper, we present Darly, a QoS-, interference- and heterogeneity-aware Deep Reinforcement Learning-based Scheduler for serverless video analytics deployments on top of distributed Edge nodes. The proposed framework incorporates a DRL agent that exploits performance counters to identify the levels of interference and the degree of heterogeneity in the underlying Edge infrastructure. It combines this information along with user-defined QoS requirements to improve resource allocations by deciding the placement, migration, or horizontal scaling of serverless functions. We evaluate Darly on a typical Edge cluster with a real-world workflow composed of commonly used serverless video analytics functions and show that our approach achieves efficient scheduling of the deployed functions by satisfying multiple QoS requirements for up to 91.6% (Profile-based) of the total requests under dynamic conditions.