The International Conference for High Performance Computing, Networking, Storage, and Analysis
The International Conference for High Performance Computing, Networking, Storage, and Analysis
Workshop: ExaMPI: Workshop on Exascale MPI
Authors: Shiyi Cao, Salvatore Di Girolamo, and Torsten Hoefler (ETH Zürich)
Abstract: Efficient data communication is a major goal for scalable and cost-effective use of datacenter and HPC system resources. To let applications communicate efficiently, exchanged data must be serialized at the source and deserialized at the destination. The serialization/deserialization process enables exchanging data in a language- and machine-independent format. However, serialization/deserialization overheads can negatively impact application performance. For example, a server within a microservice framework must deserialize all incoming requests before invoking the respective microservices. We show how data deserialization can be offloaded to fully programmable SmartNICs and performed on the data path, on a per-packet basis. This solution avoids intermediate memory copies, enabling on-the-fly deserialization. We showcase our approach by offloading Google Protocol Buffers, a widely used framework to serialize/deserialize data. We show through microservice throughput modeling how we can improve the overall throughput by pipelining the deserialization and actual application activities with PsPIN.
Back to ExaMPI: Workshop on Exascale MPI Archive Listing