BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal//recurring_events_ical//2.0//EN
BEGIN:VEVENT
UID:7851e343-12ce-4cd0-8349-a395054e0ad2@support.access-ci.org
DTSTAMP:20250102T133542Z
DTSTART:20250311T180000Z
DTEND:20250311T193000Z
SUMMARY:The TAU Performance System and E4S (Advanced HPC-CI Webinar Series)
DESCRIPTION:The talk will highlight the advances in the TAU Performance Sys
 tem(R). The TAU Performance System is a versatile performance evaluation t
 oolkit supporting both profiling and tracing modes of measurement. It supp
 orts performance evaluation of applications running on CPUs and GPUs and s
 upports runtime-preloading of a Dynamic Shared Object (DSO) that allows us
 ers to measure the performance without modifying the source code or binary
 . It will describe how TAU may be used with MVAPICH MPI and support advanc
 ed performance introspection capabilities at the runtime layer. TAU's supp
 ort for tracking the idle time spent in implicit barriers within collectiv
 e operations will be demonstrated. TAU also supports event-based sampling 
 at the function, file, and statement level. TAU's support for runtime syst
 ems such as CUDA (for NVIDIA GPUs), Level Zero (for Intel oneAPI DPC++/SYC
 L), ROCm (for AMD GPUs), OpenMP with support for OMPT and Target Offload d
 irectives, Kokkos, and MPI allow instrumentation at the runtime system lay
 er while using sampling to evaluate statement-level performance data. It w
 ill describe the different instrumentation, measurement and analysis optio
 ns that are available and how TAU is integrated in the Extreme-scale Scien
 tific Software Stack (E4S). E4S is a curated, Spack based software distrib
 ution of 100+ HPC and AI/ML packages. A hands-on demo on AWS with the Extr
 eme-scale Scientific Software Stack (E4S) will be shown.InstructorSameer S
 hende, Research Professor, University of OregonSameer Shende serves as a R
 esearch Professor and the Director of the Performance Research Laboratory 
 at the University of Oregon and the President and Director of ParaTools, I
 nc. (USA) and ParaTools, SAS (France). He serves as the Technical Lead of 
 the Extreme-scale Scientific Software Stack (E4S), ParaTools Pro for E4S(T
 M), TAU Performance System, Program Database Toolkit (PDT), and HPCLinux p
 rojects. His research interests include scientific software stacks, perfor
 mance instrumentation, compiler optimizations, measurement, and analysis t
 ools for HPC. He received his B.Tech. in Electrical Engineering from IIT B
 ombay in 1991, and his M.S. and Ph.D. in Computer and Information Science 
 from the University of Oregon in 1996 and 2001 respectively.See a full lis
 t of SDSC's upcoming training and events here.
URL:https://support.access-ci.org/events/7721
END:VEVENT
END:VCALENDAR