Related papers: Demonstrating a Pre-Exascale, Cost-Effective Multi…
The advent of High Performance Computing (HPC) has provided the computational capacity required for power system operators (SO) to obtain solutions in the least time to highly-complex applications, i.e., Unit Commitment (UC). The UC…
Recent developments in large language models (LLMs) have demonstrated their remarkable proficiency in a range of tasks. Compared to in-house homogeneous GPU clusters, deploying LLMs in cloud environments with diverse types of GPUs is…
We present Incisor, a cloud HPC job submission system for the ex ante instance selection problem: choosing suitable hardware in the challenging but common setting where only the executable, inputs, and invocation commands are available at…
Function-as-a-Service is a novel type of cloud service used for creating distributed applications and utilizing computing resources. Application developer supplies source code of cloud functions, which are small applications or application…
A pronounced imbalance in GPU resources exists on campus, where some laboratories own underutilized servers while others lack the compute needed for AI research. GPU sharing can alleviate this disparity, while existing platforms typically…
With the increasing number of Machine and Deep Learning applications in High Energy Physics, easy access to dedicated infrastructure represents a requirement for fast and efficient R&D. This work explores different types of cloud services…
By acquiring cloud-like capacities at the edge of a network, edge computing is expected to significantly improve user experience. In this paper, we formulate a hybrid edge-cloud computing system where an edge device with limited local…
At present moment, there is a great interest in development of information systems operating in cloud infrastructures. Generally, many of tasks remain unresolved such as tasks of optimization of large databases in a hybrid cloud…
Cloud-based deployment of content production and broadcast workflows has continued to disrupt the industry after the pandemic. The key tools required for unlocking cloud workflows, e.g., transcoding, metadata parsing, and streaming…
This paper describes the achievements of the H2020 project INDIGO-DataCloud. The project has provided e-infrastructures with tools, applications and cloud framework enhancements to manage the demanding requirements of scientific…
Cloud computing offers on-demand, scalable computing and storage, and has become an essential resource for the analyses of big biomedical data. The usual approach to cloud computing requires users to reserve and provision virtual servers.…
GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes…
Scientific computing is at the core of many High-Performance Computing applications, including computational flow dynamics. Because of the uttermost importance to simulate increasingly larger computational models, hardware acceleration is…
Stencil computation is one of the most important kernels in various scientific computing. Nowadays, most Stencil-driven scientific computing still relies heavily on supercomputers, suffering from expensive access, poor scalability, and…
The reproducibility of scientific experiment is vital for the advancement of disciplines based on previous work. To achieve this goal, many researchers focus on complex methodology and self-invented tools which have difficulty in practical…
We assess costs and efficiency of state-of-the-art high performance cloud computing compared to a traditional on-premises compute cluster. Our use case are atomistic simulations carried out with the GROMACS molecular dynamics (MD) toolkit…
Cloud Computing (CC) is the most prevalent paradigm under which services are provided over the Internet. The most relevant feature for its success is its capability to promptly scale service based on user demand. When scaling, the main…
Cloud users aim to minimize cost while maximizing performance by selecting the most suitable instance types for their workloads. To reduce expenses, spot instances have been widely adopted due to their steep discounts compared to on-demand…
GPUs in High-Performance Computing systems remain under-utilised due to the unavailability of schedulers that can safely schedule multiple applications to share the same GPU. The research reported in this paper is motivated to improve the…
For the past two decades, the DB community has devoted substantial research to take advantage of cheap clusters of machines for distributed data analytics -- we believe that we are at the beginning of a paradigm shift. The scaling laws and…