libMPNode

Abstract

In this work we describe libMPNode, an OpenMP runtime designed for efficient multithreaded execution across systems composed of multiple non-cache-coherent domains. Rather than requiring extensive compiler-level transformations or building new programming model abstractions, libMPNode builds on recent works that allow developers to use a traditional shared-memory programming model to build applications that are migratable between incoherent domains. libMPNode handles migrating threads between domains, or nodes, and optimizes many OpenMP mechanisms to reduce cross-node communication. While applications may not scale as written, we describe early experiences in simple code refactoring techniques that help scale performance by only changing a handful of lines of code. We describe and evaluate the current implementation, report on experiences using the runtime, and describe future research directions for multidomain OpenMP. CCS Concepts • Computing methodologies → Parallel computing methodologies; • Computer systems organization → Multicore architectures;

Sharing non‐cache‐coherent memory with bounded incoherence

“…Hare 10 uses message passing to implement a distributed file‐system across nodes in a non‐CC system. libMPNode 43 implements an OpenMP runtime for incoherent domains. It leverages thread migration and distributed shared memory to provide consistency between incoherent nodes.…”

An OpenMP Runtime for Transparent Work Sharing Across Cache-Incoherent Heterogeneous Nodes

“…libHetMP uses the thread hierarchy for many types of synchronization, including barriers, reductions and work distribution. libHetMP builds upon previous work by Lyerly et al [37], which refactors OpenMP execution for DSM on homogeneous clusters. Figure 3 illustrates using the thread hierarchy for synchronization.…”