research
∙
06/22/2023
Sustainable HPC: Modeling, Characterization, and Implications of Carbon Footprint in Modern HPC Systems
The rapid growth in demand for HPC systems has led to a rise in energy c...
share
research
∙
04/19/2023
Green Carbon Footprint for Model Inference Serving via Exploiting Mixed-Quality Models and GPU Partitioning
This paper presents a solution to the challenge of mitigating carbon emi...
research
∙
10/12/2022
Building Heterogeneous Cloud System for Machine Learning Inference
Online inference is becoming a key service product for many businesses, ...
research
∙
07/23/2022
RIBBON: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instances
Deep learning model inference is a key service in many businesses and sc...
research
∙
07/23/2022
MISO: Exploiting Multi-Instance GPU Capability on Multi-Tenant Systems for Machine Learning
GPU technology has been improving at an expedited pace in terms of size ...
research
∙
05/19/2022
Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language Models
The energy requirements of current natural language processing models co...
research
∙
04/12/2022
The MIT Supercloud Workload Classification Challenge
High-Performance Computing (HPC) centers and cloud providers support an ...
research
∙
01/28/2022
Benchmarking Resource Usage for Efficient Distributed Deep Learning
Deep learning (DL) workflows demand an ever-increasing budget of compute...
research
∙
08/04/2021