Abstract
A performance framework is introduced to facilitate the development and optimization of extreme-scale abstract execution models and the future systems derived from them. SLOWER defines a six-dimensional design trade-off space based on sources of performance degradation that are invariant across system classes. Exemplar previous generation execution models (e.g., vector) are examined in terms of the SLOWER parameters to illustrate their alternative responses to changing enabling technologies. New technology trends leading to nano-scale and the end of Moore's Law demand future innovations to address these same performance factors. An experimental execution model, ParalleX, is described to postulate one possible advanced abstraction upon which to base next generation hardware and software systems. A detailed examination is presented of how this class of dynamic adaptive execution model addresses SLOWER for advances in efficiency and scalability. To represent the SLOWER trade-off space, a queue model has been developed and is described. A set of simulation experiments spanning ranges of key parameters is presented to expose some initial properties of the SLOWER framework.
Highlights
As technology advances, the means to effectively benefit from its improved properties changes, sometimes significantly, in computer architecture, programming models, supporting system software, and other aspects
This paper describes one such performance model, SLOWER, that is serving in this capacity for research into extreme-scale execution models, runtime system software, and programming interfaces
SLOWER defines a six-dimensional design trade-off space based on sources of performance degradation that are derived from the physics of the underlying hardware systems and the control software
Summary
The means to effectively benefit from its improved properties changes, sometimes significantly, in computer architecture, programming models, supporting system software, and other aspects. Together these reflect a crosscutting execution model, which must evolve to respond to opportunities and challenges of the emerging enabling technologies. The history of high performance computing is punctuated with dramatic paradigm shifts resulting in a succession of innovative execution models as the device technologies have progressed. They share in common a set of key factors to which each has responded. This paper describes one such performance model, SLOWER, that is serving in this capacity for research into extreme-scale execution models, runtime system software, and programming interfaces
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
