Performance Evaluation and Analysis Consortium (PEAC) End Station

PI Name: 
Leonid Oliker
PI Email: 
loliker@lbl.gov
Institution: 
Lawrence Berkeley National Laboratory
Allocation Program: 
INCITE
Allocation Hours at ALCF: 
85 Million
Year: 
2013
Research Domain: 
Computer Science

To maximize the utility of forthcoming Department of Energy (DOE) leadership-class systems we must understand how to use each system most efficiently. The performance research community can provide tools, runtimes, and methodologies to enable scientists to exploit leadership-class machines, but only if they have adequate system access.

This project will focus on five primary goals: (1) develop new programming models and runtime systems for emerging and future generation leadership computing platforms; (2) update and extend performance evaluation of all systems using suites of both standard and custom micro, (3) continue to port performance tools and performance middleware to the BG/Q and XK6, (4) validate and modify performance prediction technologies to improve their utility for production runs on the leadership-class systems; and (5) analyze and help optimize current or candidate leadership-class application codes.

Catalyst: