LC Hotline: 2-4531

From offsite: (925) 422-4531

 

Hours

Monday–Friday
8am–12pm, 1–4:45pm
B453 R1103 | Q-clearance area

 

Clone of Parallel Performance Evaluation Using TAU

August 28–29, 2018
 

Date / Time

August 28-29, 2018    9:00am - 5:00pm

Description

Optimizing parallel codes is becoming increasingly important to ensure those codes run efficiently on modern and future HPC machines. To aid in this, LLNL will be hosting a workshop on optimizing code using the TAU Performance System, on Livermore Computing HPC systems for HPC code developers and users. In this training, we will have the TAU principal developer, Dr. Sameer Shende of ParaTools, Inc., onsite to provide free instruction and consultation. Introductory sessions will cover the basics of using TAU and advanced topics will be covered to further participants ability to use TAU. The workshop will include sample codes that illustrate the different instrumentation and measurement choices available and will be leveraged in hands-on sessions designed to guide participants through TAU's capabilities. One-on-one consultation sessions are available for further, more in-depth, instruction and help in addressing performance bottlenecks in your codes. Those already familiar with TAU are more than welcome to participate in any session.

Introductory sessions will cover the following topics:

  • Performance data collection, analysis, and optimization of parallel programs written in Python, Fortran, C++, C, UPC, MPI, and other runtime layers such as OpenSHMEM, CUDA, OpenCL, Kokkos, and OpenACC
  • Accurate profiling, tracing, and debugging
  • I/O and memory profiling and debugging
  • TAU's instrumentation support for compiler-based instrumentation, binary re-writing, library preloading, and automatic instrumentation of source code
  • TAU's interfaces to other tools such as PAPI, Likwid, Score-P, OTF2, and Vampir

The following new and advanced features will be covered:

  • TAU’s Kokkos profiling interface that provides detailed kernel level performance data for un-modified Trilinos applications
  • TAU’s use on ARM64 systems with PAPI hardware performance counter library
  • Accurate profiling of OpenMP codes using the new OMPT TR6 API
  • Callstack tracking at the point of program failure to isolate runtime faults
  • Usage of TAU in container environments such as ECP SDK Docker and Singularity containers
  • TAU Commander - a tool to simplify TAU's usage, callsite instrumentation, Python and CUDA support, as well as support for MPI_T
  • Instrumentation techniques that require no changes to the binary

More information on TAU can be found here: http://tau.uoregon.edu

Workshop (Aug 28): Attendees may use their own Livermore Computing (LC) computer accounts on clusters such as quartz, vulcan, etc. If you do not have an account on an LC cluster, you can use a temporary workshop account provided during the workshop, or you can request an account in advance through the LC Hotline ( lc-support@llnl.gov). 

Individual Sessions (Aug 29): Interested developers can schedule individual meeting times with the speaker, which can include hands-on work with their codes/projects (bring your own laptop if you wish to do this). These individual sessions must be scheduled in advance by contacting Blaise Barney at 422-2578 or blaiseb@llnl.gov

Agenda

Aug 28 Workshop: (T1889 classroom 1) 

9:00 - 10:30:  Introduction to TAU
10:30 - 10:45: Break
10:45 - 12:00: Hands-on
12:00 - 1:30:  Lunch (on your own)
1:30 - 3:30:   Advanced Topics and New Features
3:30 - 3:45:   Break
3:45 - 5:00:   Hands-on


Aug 29 Individual Sessions: (B453 R1016)

9:00:  One-on-one consulting sessions
12:00: Lunch (on your own)
1:00:  One-on-one consulting sessions;

NOTE:  Time slots must be reserved in advance - contact Blaise Barney (925-422-2578 / blaiseb@llnl.gov) for details.

About the Instructor Sameer Shende (sameer@paratools.com) serves as the Director of the Performance Research Laboratory at the University of Oregon and the President of ParaTools, Inc. He received his Ph.D. from the University of Oregon and B.Tech from the Indian Institute of Technology, Bombay. He has helped develop the TAU Performance System, Program Database Toolkit (PDT), Parallel Tools Runtime Environment (PToolsRTE), and the HPCLinux distribution. His areas of interest include tools and techniques for performance instrumentation, measurement, performance analysis, runtime systems, and compiler optimizations.
Location Workshop: Aug 28, 2018 9:00am – 5:00pm; Laboratory Training Center 2, Trailer 1889 (near the West Gate Badge Office). This is a Common Access Area. Directions and contact information are available at: https://lab-training-center-int.llnl.gov/xlocation.html

Individual Sessions: Aug 29, 2018 9:00am – 5:00pm; Building 453, Room 1016 (Viz Development Lab). Note: Time slots for these must be scheduled in advance.
This is a Property Protection Area. Foreign national temporary escorted building access procedures apply.

What to Bring Computers are provided for the workshop on Aug 28.  For the individual sessions on Aug 29, attendees should bring a laptop computer
Fee No cost
Level/Prerequisites Introductory level. A basic understanding of parallel programming with C or Fortran is essential.
Registration

Aug 28 Workshop: You must register in advance. Registration is limited to LLNL employees, students and collaborators. Note that enrollment is limited due to the number of available workstations.

  • Register for course number EC3528 through LTRAIN.
  • Foreign Nationals: T1889 is a Common Access Area, so no escort is required for employee foreign nationals.


Aug 29 Individual Sessions: Those wishing to schedule individual sessions with the instructor must do this in advance by contacting Blaise Barney at 422-2578 or blaiseb@llnl.gov

Questions? Please call or email Blaise Barney (925-422-2578 / blaiseb@llnl.gov)

 

 

UCRL-MI-138859