[Colloquium] [CS] Reminder - Matt Baughman MS Presentation/Aug 17, 2021

[nitayack at cs.uchicago.edu]

This is an announcement of Matt Baughman's MS Presentation
===============================================
Candidate: Matt Baughman

Date: Tuesday, August 17, 2021

Time: 11 am CST

Remote Location: Zoom:  https://uchicago.zoom.us/j/97996344786?pwd=RERpQ1NEV1JlbnNBUlNGY2tpdEZZZz09

M.S. Paper Title: PROFILING, PREDICTING, AND PROVISIONING: ENABLING COST-AWARE COMPUTATION FOR THE CLOUD AND MODERN HETEROGENEOUS ENVIRONMENTS

Abstract: The growing prevalence of cloud resources and specialized hardware in the form of GPUs, ASICs, and IoT devices requires increasingly efficient end intentional use of these resources. Moreover, the complexity of choice these diverse resources presents creates an optimization problem largely intractable to the human mind. Therefore, modern computation in heterogeneous environments must be executed in a cost-aware, automated fashion. This control system can be decomposed into three discrete tasks: profiling, prediction, and provisioning. We profile the execution characteristics of a range of workloads on a range of hardware. Given those characteristics, we optimize our choice of resources for workload deployment based on predicted cost. Finally, we seamlessly provision any necessary resources and deploy the workload given the optimized choice of resource.
In this work, we integrate several projects spanning the profiling, predicting, and provisioning cycle towards a unified system for the cost-aware distribution of workloads in dynamic, heterogeneous computing environments. Specifically, we use statistical analysis and machine learning to predict the cost of using preemptible cloud resources, employ a modular profiling system that characterizes the execution performance of scientific workflows deployed on cloud resources, evaluate the economics of Amazon Web Service’s (AWS’s) Spot Instances, examine the role of computational tradeoffs in machine learning workflows, and build on existing Function-as-a-Service frameworks to demonstrate a novel, cost-aware function distribution system. Through this work, we show the significant cost and time reductions for scientific workflow execution, while enabling function-based distributed computing in a cost-aware heterogeneous environment.

Advisors: Ian Foster

_______________________________________________
One-Click Unsubscribe: https://mailman.cs.uchicago.edu/mailman/options/cs/nitayack%40uchicago.edu?password=crNNhtKB&unsub=1&unsubconfirm=1


When unsubscribing manually please use your cnetid at cs.uchicago.edu address to unsubscribe if your cnetid at uchicago.edu does not work.

cs mailing list  -  cs at mailman.cs.uchicago.edu
Edit Options and/or Unsubscribe: https://mailman.cs.uchicago.edu/mailman/listinfo/cs
More information here: https://howto.cs.uchicago.edu/techstaff:mailinglist