Related papers: WaSP: Warp Scheduling to Mimic Prefetching in Grap…
The main memory access latency has not much improved for more than two decades while the CPU performance had been exponentially increasing until recently. Approximate memory is a technique to reduce the DRAM access latency in return of…
High Speed computing meets ever increasing real-time computational demands through the leveraging of flexibility and parallelism. The flexibility is achieved when computing platform designed with heterogeneous resources to support…
In an overloaded FaaS cluster, individual worker nodes strain under lengthening queues of requests. Although the cluster might be eventually horizontally-scaled, adding a new node takes dozens of seconds. As serving applications are tuned…
We study the problem of scheduling VMs (Virtual Machines) in a distributed server platform, motivated by cloud computing applications. The VMs arrive dynamically over time to the system, and require a certain amount of resources (e.g.…
Real-time systems are intrinsic components of many pivotal applications, such as self-driving vehicles, aerospace and defense systems. The trend in these applications is to incorporate multiple tasks onto fewer, more powerful hardware…
High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems.The…
As inference workloads for large language models (LLMs) scale to meet growing user demand, pipeline parallelism (PP) has become a widely adopted strategy for multi-GPU deployment, particularly in cross-node setups, to improve key-value (KV)…
To train modern large DNN models, pipeline parallelism has recently emerged, which distributes the model across GPUs and enables different devices to process different microbatches in pipeline. Earlier pipeline designs allow multiple…
Pipeline Parallelism (PP) serves as a crucial technique for training Large Language Models (LLMs), owing to its capability to alleviate memory pressure from model states with relatively low communication overhead. However, in long-context…
Serverless Computing (FaaS) has become a popular paradigm for deep learning inference due to the ease of deployment and pay-per-use benefits. However, current serverless inference platforms encounter the coarse-grained and static GPU…
We study the general scheduling problem (GSP) which generalizes and unifies several well-studied preemptive single-machine scheduling problems, such as weighted flow time, weighted sum of completion time, and minimizing the total weight of…
Time Sensitive Networking (TSN) is fundamental for the reliable, low-latency networks that will enable the Industrial Internet of Things (IIoT). Wi-Fi has historically been considered unfit for TSN, as channel contention and collisions…
We consider the weighted completion time minimization problem for capacitated parallel machines, which is a fundamental problem in modern cloud computing environments. We study settings in which the processed jobs may have varying duration,…
Irregular applications comprise an increasingly important workload domain for many fields, including bioinformatics, chemistry, physics, social sciences and machine learning. Therefore, achieving high performance and energy efficiency in…
When executing a deep neural network (DNN), its model parameters are loaded into GPU memory before execution, incurring a significant GPU memory burden. There are studies that reduce GPU memory usage by exploiting CPU memory as a swap…
In wireless sensor networks (WSNs), implementing a high-precision time synchronization scheme on resource-constrained sensor nodes is a major challenge. Our investigation of the practical implementation on a real testbed of the…
Recent decades have witnessed the tremendous development of network science, which indeed brings a new and insightful language to model real systems of different domains. Betweenness, a widely employed centrality in network science, is a…
The high degree of parallelism and relatively complicated synchronization mechanisms in GPUs make writing correct kernels difficult. Data races pose one such concurrency correctness challenge, and therefore, effective methods of detecting…
Memory safety errors continue to pose a significant threat to current computing systems, and graphics processing units (GPUs) are no exception. A prominent class of memory safety algorithms is allocation-based solutions. The key idea is to…
We are given a set of jobs, each one specified by its release date, its deadline and its processing volume (work), and a single (or a set of) speed-scalable processor(s). We adopt the standard model in speed-scaling in which if a processor…