Related papers: SuperSONIC: Cloud-Native Infrastructure for ML Inf…
The most of computing environments in the IT support organization like NIC are designed to run in centralized datacentre. The centralized infrastructure of various development projects are used to deploy their services on it and connecting…
Recent advancements in Machine Learning (ML) have substantially improved its predictive and computational abilities, offering promising opportunities for surrogate modeling in scientific applications. By accurately approximating complex…
Microservice applications are created as loosely coupled application components and they leverage cloud elasticity to reduce costs and increase development speed. However, microservice applications exhibit complex interactions among…
In this paper, we report the performance benchmarking results of deep learning models on MLCommons' Science cloud-masking benchmark using a high-performance computing cluster at New York University (NYU): NYU Greene. MLCommons is a…
An increasing number of applications rely on complex inference tasks that are based on machine learning (ML). Currently, there are two options to run such tasks: either they are served directly by the end device (e.g., smartphones, IoT…
In the past decade, we have witnessed a dramatically increasing volume of data collected from varied sources. The explosion of data has transformed the world as more information is available for collection and analysis than ever before. To…
Neural network (NN) accelerators with multi-chip-module (MCM) architectures enable integration of massive computation capability; however, they face challenges of computing resource underutilization and off-chip communication overheads.…
The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-sized models and infrequent requests. While existing serverless solutions follow exclusive GPU allocation, we take a step back to explore…
The Computing Continuum (CC) integrates different layers of processing infrastructure, from Edge to Cloud, to optimize service quality through ubiquitous and reliable computation. Compared to central architectures, however, heterogeneous…
Scientific simulation leveraging high-performance computing (HPC) systems is crucial for modeling complex systems and phenomena in fields such as astrophysics, climate science, and fluid dynamics, generating massive datasets that often…
The revolution in artificial intelligence (AI) has brought sustainable challenges in data center management due to the high carbon emissions and short cooling response time associated with high-power density racks. While machine learning…
Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a…
IoT devices are increasingly the source of data for machine learning (ML) applications running on edge servers. Data transmissions from devices to servers are often over local wireless networks whose bandwidth is not just limited but, more…
The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computational demands on execution platforms, posing challenges to real-time control deadlines.…
This paper explores a prevailing trend in the industry: migrating data-intensive analytics applications from on-premises to cloud-native environments. We find that the unique cost models associated with cloud-based storage necessitate a…
Recent years have seen many successful applications of machine learning (ML) to facilitate fluid dynamic computations. As simulations grow, generating new training datasets for traditional offline learning creates I/O and storage…
The deployment of ML models on edge devices is challenged by limited computational resources and energy availability. While split computing enables the decomposition of large neural networks (NNs) and allows partial computation on both edge…
High Performance Computing (HPC) clouds are becoming an alternative to on-premise clusters for executing scientific applications and business analytics services. Most research efforts in HPC cloud aim to understand the cost-benefit of…
The MIT SuperCloud database management system allows for rapid creation and flexible execution of a variety of the latest scientific databases, including Apache Accumulo and SciDB. It is designed to permit these databases to run on a High…
Next-generation mixed-criticality Systems-on-chip (SoCs) for robotics, automotive, and space must execute mixed-criticality AI-enhanced sensor processing and control workloads, ensuring reliable and time-predictable execution of critical…