Related papers: Optimized Memoryless Fair-Share HPC Resources Sche…
We consider a setting in which a group of agents share resources that must be allocated among them in each discrete time period. Agents have time-varying demands and derive constant marginal utility from each unit of resource received up to…
Runtime scheduling and workflow systems are an increasingly popular algorithmic component in HPC because they allow full system utilization with relaxed synchronization requirements. There are so many special-purpose tools for task…
Many task-parallel applications can benefit from attempting to execute tasks in a specific order, as for instance indicated by priorities associated with the tasks. We present three lock-free data structures for priority scheduling with…
Using correct design metrics and understanding the limitations of the underlying technology is critical to developing effective scheduling algorithms. Unfortunately, existing scheduling techniques used \emph{incorrect} metrics and had…
As multimodal and AI-driven services exchange hundreds of megabytes per request, existing IPC runtimes spend a growing share of CPU cycles on memory copies. Although both hardware and software mechanisms are exploring memory offloading,…
Modern distributed machine learning (ML) training workloads benefit significantly from leveraging GPUs. However, significant contention ensues when multiple such workloads are run atop a shared cluster of GPUs. A key question is how to…
We optimize the throughput of a single cell multiuser orthogonal frequency division multiplexing system with proportional data rate fairness among the users. The concept is to support mobile users with different levels of service. The…
In this work, we investigate a multi-source multi-cast network with the aid of an arbitrary number of relays, where it is assumed that no direct link is available at each S-D pair. The aim is to find the fundamental limit on the maximal…
The fairness of machine learning-based decisions has become an increasingly important focus in the design of supervised machine learning methods. Most fairness approaches optimize a specified trade-off between performance measure(s) (e.g.,…
High-Performance Computing (HPC) job scheduling involves balancing conflicting objectives such as minimizing makespan, reducing wait times, optimizing resource use, and ensuring fairness. Traditional methods, including heuristic-based,…
We present a number of novel algorithms, based on mathematical optimization formulations, in order to solve a homogeneous multiprocessor scheduling problem, while minimizing the total energy consumption. In particular, for a system with a…
Optimizing resource utilization in high-performance computing (HPC) clusters is essential for maximizing both system efficiency and user satisfaction. However, traditional rigid job scheduling often results in underutilized resources and…
We consider fair resource allocation in sequential decision-making environments modeled as weakly coupled Markov decision processes, where resource constraints couple the action spaces of $N$ sub-Markov decision processes (sub-MDPs) that…
In this paper, we consider a two-hop relay-assisted cognitive downlink OFDMA system (named as secondary system) dynamically accessing a spectrum licensed to a primary network, thereby improving the efficiency of spectrum usage. A…
We consider energy-efficient scheduling on multiprocessors, where the speed of each processor can be individually scaled, and a processor consumes power $s^{\alpha}$ when running at speed $s$, for $\alpha>1$. A scheduling algorithm needs to…
This paper introduces TARDIS (Temporal Allocation for Resource Distribution using Intelligent Scheduling), a novel power-aware job scheduler for High-Performance Computing (HPC) systems that minimizes electricity costs through both temporal…
This paper addresses a single machine scheduling problem with non-preemptive jobs to minimize the total electricity cost. Two latest trends in the area of the energy-aware scheduling are considered, namely the variable energy pricing and…
The ever-increasing gap between compute and I/O performance in HPC platforms, together with the development of novel NVMe storage devices (NVRAM), led to the emergence of the burst buffer concept - an intermediate persistent storage layer…
One typical use case of large-scale distributed computing in data centers is to decompose a computation job into many independent tasks and run them in parallel on different machines, sometimes known as the "embarrassingly parallel"…
Resource allocation is crucial for the performance optimization of cloud-assisted multi-agent intelligence. Traditional methods often overlook agents' diverse computational capabilities and complex operating environments, leading to…