Computer Systems and Architecture

insight - Computer Systems and Architecture

Efficient System Design for Emerging Multi-Modal Generative AI Models: Insights from Text-to-Image and Text-to-Video Workloads

Emerging multi-modal generative AI models, such as text-to-image (TTI) and text-to-video (TTV) models, exhibit unique system characteristics that require tailored optimizations beyond those designed for traditional large language models (LLMs). Careful characterization of these workloads is critical to enable efficient deployment at scale.

LearnedFTL: A Learning-Based Page-Level Flash Translation Layer for Reducing Double Reads in Flash-Based Solid-State Drives

LearnedFTL employs learned indexes to improve the address translation efficiency of flash-based SSDs, reducing the number of double reads induced by address translation in random read accesses.

Benchmarking Machine Learning Applications on Heterogeneous Architectures using the Reframe Framework

The authors extend the Reframe testing framework to support Kubernetes as a backend scheduler, and utilize this framework to benchmark the performance of various machine learning applications, including ResNet-50, DeepCAM, and CosmoFlow, across a range of heterogeneous hardware platforms managed by EPCC.

Efficient Online Scheduling of Deep Neural Networks on Multi-Tenant Multi-Accelerator Systems using Deep Reinforcement Learning

A deep reinforcement learning-based online scheduling algorithm, RELMAS, that efficiently schedules deep neural network inference requests on a multi-tenant multi-accelerator system, optimizing service-level agreement satisfaction rates while considering heterogeneous accelerator capabilities and memory bandwidth constraints.

About

Products | Resources

Insights