Sat 22 Jun 2019 12:10 - 12:35 at 212A - Chapel Performance and Optimizations Chair(s): David G. Wonnacott

This talk will highlight communication optimizations made to the Chapel compiler and runtime over the past year. It will focus on improvements to core benchmarks that have benefited from fine-grained and bulk communication optimizations as well as remote task-spawning improvements. Several benchmarks including HPC Challenge (HPCC) RandomAccess, HPCC Stream Triad, and an integer sort code ISx will be briefly introduced, and a relevant performance optimization will be showcased. These benchmarks represent core idioms that are common in many HPC applications. Performance results on up to 1,024 nodes (25,000 cores) will demonstrate that with each release Chapel is becoming more competitive against hand tuned MPI+OpenMP, SHMEM, and UPC.

Sat 22 Jun

Displayed time zone: Tijuana, Baja California change

11:20 - 12:35
Chapel Performance and OptimizationsCHIUW at 212A
Chair(s): David G. Wonnacott Haverford College
11:20
25m
Talk
Towards Radix Sorting in the Chapel Standard Library
CHIUW
11:45
25m
Research paper
Implementing Stencil Problems in Chapel: An Experience Report
CHIUW
Per Fuchs Vrije Universiteit (VU) Amsterdam, Pieter Hijma Vrije Universiteit (VU) Amsterdam, Clemens Grelck University of Amsterdam
12:10
25m
Talk
Chapel Unblocked: Recent Communication Optimizations in Chapel
CHIUW
Elliot Ronaghan Cray Inc., Ben Harshbarger Cray Inc., Gregory Titus Cray Inc., Michael Ferguson Cray Inc.