Date of Event:
June 14, 2016Where:
TIG Corporate Headquarters
10240 Flanders Court, San Diego, CA
Case Study: Predicting Compute Memory Needed for a Computer Job, Tuesday, June 14, 2016
6:00 PM – Networking
6:30pm -- Recap of Hackathorn, Gina Escobar
7:15pm -- Qualcomm Case Study
8:00pm -- close
Recommender System for a Compute Memory Request for a Computer Job by
Taraneh Taghavi, Qualcomm and Maria Lupetini, Qualcomm
Billions of computer jobs are run on Qualcomm compute clusters in a year to design and test semiconductor chips. There is a need to use all compute resources optimally, i.e. processors, storage and memory.
Currently, the engineers estimate the compute memory needed to run a job. When compared to what is actually needed for execution, their estimates overall are too high. This results in too much compute memory being allocated to these computer runs, and thereby reducing the ability to run other jobs on the same multi-processor server. This reduction in throughput delays precious design and testing time. In addition, this behavior drives compute memory purchase costs higher than necessary.
This presentation will highlight the data exploration, development, and deployment of a recommender system that predicts the amount of memory a compute job will need. We will discuss the array of statistical and machine learning techniques we explored, and how we selected the final model.
Taraneh Taghavi serves as the lead of Analytics team at Qualcomm Inc., responsible for analysis and modeling quality metrics of semiconductor chips and engineering management process. Her areas of focus are data mining, machine learning, and analytical modeling. She has over ten years of academic and industry experience in model development, algorithm design and software programming in a variety of applications including pattern recognition, optimization, complexity theory, database management and computer aided design. She holds 4 patents and over 20 conference and journal publications in these areas.
Taraneh earned a Ph.D. in Computer Science from University of California, Los Angeles and a M.Sc. in Applied Statistics from Texas A&M University.
Maria Lupetini’s career spans a broad range predictive analytics and optimization implementations for many Fortune 500 companies. She has tackled challenges in the high tech, internet, marketing, supply chain, and healthcare domains.
As Director of Engineering Operations, she manages the Engineering Advanced Analytics team in Qualcomm Technologies Inc. which implements models to enhance semi-conductor chip characteristics and improve engineering management decision making. In addition, she manages a team which optimizes the portfolio of high dollar software assets used to design semi-conductor chips for cell phones and other devices. Ms. Lupetini earned an MBA at the University of Chicago, and an MS in Operations Research from the University of Minnesota, Institute of Technology.