Active Access: A Mechanism for High-Performance Distributed Data-Centric Computations

Remote memory access (RMA) is an emerging high-performance programming model that uses RDMA hard-ware directly. Yet, accessing remote memories cannot in-voke activities at the target which complicates implementa-tion and limits performance of data-centric algorithms. We propose Active Access (AA), a mechanism that integrates well-known active messaging (AM) semantics with RMA to enable high-performance distributed data-centric computa-tions. AA supports a new programming model where the user specifies handlers that are triggered when incoming puts and gets reference designated addresses. AA is based on a set of extensions to the Input/Output Memory Manage-ment Unit (IOMMU), a unit that provides high-performance hardware support for remapping I/O accesses to memory. We illustrate that AA outperforms existing AM and RMA designs, accelerates various codes such as distributed hashta-bles or logging schemes, and enables new protocols such as incremental checkpointing for RMA. We also discuss how extended IOMMUs can support a virtualized global address space in a distributed system that offers features known from on-node memory virtualization. We expect that AA and other IOMMU features can enhance the design of HPC op-erating and runtime systems in large computing centers. 1