Toward a Scalable Heterogeneous Runtime System for the Convey MX Architecture

Given the recent advent of the multicore era [1], research efforts in the area of high performance, low latency runtime systems have increased significantly. This research has given birth to new techniques in low-overhead scheduling techniques, small-memory footprint parallel execution units and kernel-free contextual environments. This paper presents a framework and runtime system for a truly heterogeneous approach to low-latency, high performance runtime techniques on the Convey MX-100 platform and CHOMP micro-architecture [14]. This framework, deemed the Convey Lightweight Runtime [CLR], is designed to provide high performance, programming-model agnostic parallel library support to the massively parallel CHOMP infrastructure. This work explores the fundamental design requirements and implementation details behind constructing the CLR system as a truly heterogeneous low-level runtime system for a wide array of parallel programming model targets.