ALCF Simulation, Data, and Learning Workshop | Spring 2018

ALCF Staff and Industry Experts
Workshop Intermediate, Advanced
SDL Workshop

Held at the ALCF from February 27–March 1, 2018, our intensive three-day workshop is designed to help users improve Simulation, Data, and Learning applications on Theta.

The ALCF and our user community are driving a new paradigm for scientific computing—the emerging convergence of simulation, data analytics, and machine learning.

From February 27–March 1, 2018, we will host the ALCF Simulation, Data, and Learning Workshop to help users prepare to use Theta, our new KNL system, to advance research in these three areas of scientific computing. Attendees will have the opportunity to:

  • Get dedicated hands-on time with ALCF and industry professionals
  • Learn about using Theta and available tools and frameworks for your science projects involving simulation, data, and learning
  • Test and debug as you go with exclusive full-system reservations on Theta
  • Prepare for proposals to the Aurora Early Science Program for Data and Learning and the ALCF Data Science Program, as well as the INCITE and ALCC programs.

Registrants will be reviewed for experience level and will be asked to provide goals for attending.


Day 1 (Tues, Feb 27)

8:30 Shuttle from Guest House to TCS, Bldg. 240
9:00-9:15 Welcome to the SDL Workshop - Mike Papka, ALCF
9:15-10:45 Getting Started on Theta - Graham Fletcher, ALCF
10:45-11:00 Break
11:00-11:45 Using Math Libraries effectively on KNL - Khang Nguyen, Intel
11:45-12:15 Overview of Machine Learning and Deep Learning at the ALCF - Elise Jennings, ALCF
12:15-12:45 Data-Driven Molecular Engineering of Solar-Powered Windows - Jacqueline Cole, Cambridge University and ANL
12:45-1:30 Aurora Early Science Program for Data and Learning - Tim Williams, ALCF
1:30-2:15 Optimizing MPI on Theta - Peter Mendygral, Cray
2:15-3:00 Using OpenMP Effectively on Theta - Carlos Rosales-Fernandez, Intel
3:00-3:15 Break
3:15-4:00 Using and Scaling Python - William Scullin, ALCF, and Oleksandr Pavlyk, Intel
4:00-5:00 Hands-on
5:15 Shuttle from TCS to Guest House

Day 2 (Wed, Feb 28)

8:30 Shuttle from Guest House to TCS, Bldg. 240
9:00-9:45 Profiling your application with Vtune and Advisor - Carlos Rosales-Fernandez, Intel, and Paulius Velesko, Intel
9:45-10:30 Executing Workflows including running ensemble jobs - Tom Uram, ALCF
10:30-10:45 Break
10:45-12:00 Debugging and Profiling with Allinea DDT and MAP - Ryan Hulguin, ARM
12:00-12:15 Group Photo
12:15-12:45 Performance optimization of WEST and Qbox on Theta - Huihuo Zheng, ALCF
12:45-1:15 ALCF Data Science Program Overview - Elise Jennings, ALCF
1:15-2:00 Performance Profiling on KNL with Cray perftools-lite - Peter Mendygral, Cray
2:00-3:00 Scaling Deep Learning Frameworks - Peter Mendygral, Cray
3:00-3:15 Break
3:15-4:00 Using Containers on Theta - Taylor Childers, ALCF
4:00-5:00 Hands-on
5:15 Shuttle from TCS to Guest House

Day 3 (Thurs. Mar 1)

8:30 Shuttle from Guest House to TCS, Bldg. 240
9:00-9:30 Enabling Multi-Scale Physics for Industrial Design using Deep Learning Networks -
Marc Edgar, GE Global Research
9:30-10:30 Parallel I/O and Storage - Paul Coffman, ALCF
10:30-10:45 Break
10:45-11:30 Using Spark - Mike Ringenburg, Cray
11:30-12:15 Visualizing your Data - Joe Insley, ALCF, and Silvio Rizzi, ALCF
12:15-1:00 Using Balsam for Ensemble Workflows - Misha Salim, ANL
1:00-5:00 Hands-on