Inter-kernel communication facility of a distributed operating system for NoC-based lightweight manycores

Abstract

Lightweight manycore processors deliver high performance and scalability by bundling in a single chip hundreds of low-power cores, a distributed memory architecture and Networks-on-Chip (NoCs). Operating Systems (OSes) for these processors feature a distributed design, in which a communication layer enables kernels to exchange information and interoperate. Currently, this communication infrastructure is based on mailboxes, which enable fixed-size message exchanges with low latency. However, this solution is suboptimal because it can neither fully exploit the NoC nor efficiently handle the diversity of OS communication protocols. We propose an Inter-Kernel Communication (IKC) facility that exposes two kernel-level communication abstractions in addition to mailboxes: syncs, for enabling a process to signal and unlock another process remotely, and portals, for handling dense data transfers with high bandwidth. We implemented the proposed facility in Nanvix, the only open-source distributed OS that runs on a baremetal lightweight manycore, and we evaluated our solution on a 288-core processor (Kalray MPPA-256). Our results showed that our IKC facility achieves up to 16.87× and 1.68× better performance than a mailbox -only solution, in synchronization and dense data transfers, respectively.

Port do Sistema Operacional Nanvix para Arquitetura RISC-V Plataforma PULP

“…Diversos trabalhos no Nanvix já foram feitos para que outras arquiteturas fossem suportadas. Pedro Penna apresentou o uso já funcional de um port do Nanvix para outra arquitetura chamada MPPA [Penna et al 2021]. Foi usado um processador many-core de 288 núcleos que mostrou um ganho significativo de desempenho quando usado um modelo IKC Facility (proposto no artigo em referência), quando comparado com o modelo mailbox (modelo até então vigente).…”

LWMPI: An MPI library for NoC‐based lightweight manycore processors with on‐chip memory constraints

“…In Nanvix, user-level threads allocated in the same Compute Cluster share the same physical communication resources, which are distinguished only by their logical addresses. 20 Since we do not know in advance which thread will check the underlying buffers when receiving a requisition, all threads in the same Compute Cluster need to agree on a common address from which they can all consume and store messages to unlock the communication mechanisms. Thus, all requests arrive at a common address that is prefixed and known by all threads in the system, and only from…”