Related papers: Towards QoS-Aware and Resource-Efficient GPU Micro…
Modern deep learning workloads often consist of many small tensor operations, especially in inference, attention, and micro-batched training. In these settings, kernel launch overhead can become a major bottleneck, sometimes exceeding the…
Currently, there are over 14 billion IoT devices [7], and with many devices come many protocols, the main ones being MQTT and CoAP. We are interested in connecting the many diverse IoT devices to the cloud. To do so, we use the middleware…
The latest trends in high-performance computing systems show an increasing demand on the use of a large scale multicore systems in a efficient way, so that high compute-intensive applications can be executed reasonably well. However, the…
Mobile edge computing (MEC) has recently emerged as a promising technology to release the tension between computation-intensive applications and resource-limited mobile terminals (MTs). In this paper, we study the delay-optimal computation…
The continuous growth of big data applications with high computational and scalability demands has resulted in increasing popularity of cloud computing. Optimizing the performance and power consumption of cloud resources is therefore…
We propose integrating the edge-computing paradigm into the multi-robot collaborative scheduling to maximize resource utilization for complex collaborative tasks, which many robots must perform together. Examples include collaborative…
While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches…
Cloud providers usually offer diverse types of hardware for their users. Customers exploit this option to deploy cloud instances featuring GPUs, FPGAs, architectures other than x86 (e.g., ARM, IBM Power8), or featuring certain specific…
We present an architecture of a hosting system consisting of a set of hosted Web Services subject to QoS constraints, and a certain number of servers used to run users demand. The traffic is session-based, while provider and users agree on…
It is commonly assumed that the end-to-end networking performance of edge offloading is purely dictated by that of the network connectivity between end devices and edge computing facilities, where ongoing innovation in 5G/6G networking can…
Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…
Integrating GPUs into serverless computing platforms is crucial for improving efficiency. However, existing solutions for GPU-enabled serverless computing platforms face two significant problems due to coarse-grained GPU management: long…
Quantum algorithms need to be compiled to respect the constraints imposed by quantum processors, which is known as the mapping problem. The mapping procedure will result in an increase of the number of gates and of the circuit latency,…
The limited HBM capacity has become the primary bottleneck for hosting an increasing number of larger-scale GPU tasks. While demand paging extends capacity via host DRAM, it incurs up to 78x slowdown due to the massive working sets and poor…
Nowadays IoT applications consist of a collection of loosely coupled modules, namely microservices, that can be managed and placed in a heterogeneous environment consisting of private and public resources. It follows that distributing the…
LLM inference powers latency-critical production services nowadays. The bursty nature of inference traffic results in over-provisioning, which in turn leads to resource underutilization. While online-offline colocation promises to utilize…
Centralized cloud computing with 100+ milliseconds network latencies cannot meet the tens of milliseconds to sub-millisecond response times required for emerging 5G applications like autonomous driving, smart manufacturing, tactile…
Distributed applications increasingly demand low end-to-end latency, especially in edge and cloud environments where co-located workloads contend for limited resources. Traditional load-balancing strategies are typically reactive and rely…
This paper explores resource allocation in serverless cloud computing platforms and proposes an optimization approach for autoscaling systems. Serverless computing relieves users from resource management tasks, enabling focus on application…
The problem of managing multi-service applications on top of Cloud-Edge networks in a QoS-aware manner has been thoroughly studied in recent years from a decision-making perspective. However, only a few studies addressed the problem of…