Workshop: Sixth Workshop on Accelerator Programming Using Directives (WACCPD)
Event TypeWorkshop
Registration Categories
Parallel Application Frameworks
Parallel Programming Languages, Libraries, and Models
Scientific Computing
Software Engineering
TimeMonday, 18 November 20199am - 5:30pm
DescriptionThe ever-increasing heterogeneity in supercomputing applications has given rise to complex compute node architectures offering multiple, heterogeneous levels of massive parallelism. Exploiting the maximum available parallelism out of such systems necessitates sophisticated programming approaches that can provide scalable as well as portable solutions without compromising on performance. Software abstraction-based programming models, such as OpenMP and OpenACC, have been raising the abstraction of code to reduce the burden on the programmer while improving productivity.

Recent architectural trends indicate a heavy reliance of future exascale machines on accelerators for performance. Toward this end, the workshop will highlight the improvements over state-of-art through the accepted papers and prompt discussion through keynotes and panel. The workshop aims to showcase all aspects of heterogeneous systems discussing innovative high-level language features, lessons learned while using directives to migrate scientific legacy code to parallel processors, compilation and runtime scheduling techniques among others.
9:00am - 9:01amSixth Workshop on Accelerator Programming Using Directives (WACCPD)
9:01am - 9:10amWACCPD Opening Remarks
9:10am - 10:00amKeynote: Perlmutter - A 2020 Pre-Exascale GPU-Accelerated System for NERSC: Architecture and Application Performance Optimization
10:00am - 10:30amWACCPD Morning Break
10:30am - 11:00amGPU Implementation of a Sophisticated Implicit Low-Order Finite Element Solver with FP21-32-64 Computation Using OpenACC
11:00am - 11:30amAcceleration in Acoustic Wave Propagation Modeling Using OpenACC/OpenMP and Its Hybrid for the Global Monitoring System
11:30am - 12:00pmAccelerating the Performance of Modal Aerosol Module of E3SM Using OpenACC
12:00pm - 12:30pmEvaluation of Directive-Based GPU Programming Models on a Block Eigensolver with Consideration of Large Sparse Matrices
12:30pm - 2:00pmWACCPD Lunch Break
2:00pm - 2:30pmInvited Talk: The SPEC ACCEL Benchmark – Results and Lessons Learned
2:30pm - 3:00pmPerformance of the RI-MP2 Fortran Kernel of GAMESS on GPUs via Directive-Based Offloading with Math Libraries
3:00pm - 3:30pmWACCPD Afternoon Break
3:30pm - 4:00pmPerformance Portable Implementation of a Kinetic Plasma Simulation Mini-App
4:00pm - 4:30pmA Portable SIMD Primitive Using Kokkos for Heterogeneous Architectures
4:30pm - 4:35pmWACCPD Best Paper Award
4:35pm - 5:25pmPanel: Convergence, Divergence, or New Approaches? - The Future of Software-Based Abstractions for Heterogeneous Supercomputing
5:25pm - 5:30pmWACCPD Closing Remarks
Back To Top Button