Arcalis: 通过轻量级近缓存解决方案加速远程过程调用
Arcalís: Accelerating Remote Procedure Calls Using a Líghtweight Near-Cache Solution
AI总结：
Arcalis通过轻量级近缓存硬件引擎加速RPC，实现端到端加速和高吞吐量，降低微架构开销。
摘要：
现代微服务越来越多地依赖高性能远程过程调用（RPC）来协调细粒度的分布式计算。随着网络带宽的持续增长，与RPC处理相关的CPU开销，特别是序列化、反序列化和协议处理，已成为关键瓶颈。这一挑战在快速的用户空间网络栈（如DPDK）中尤为突出，这些栈将RPC处理作为主要性能限制因素。尽管先前的工作已经探讨了软件优化和基于FPGA的卸载引擎，但这些方法仍然远离CPU的内存层次结构，导致不必要的数据移动和缓存污染。我们提出了Arcalis，一种近缓存RPC加速器，它将一个轻量级硬件引擎置于最后级别缓存（LLC）旁边。Arcalis将RPC处理卸载到接收和发送路径上的专用微引擎上，这些引擎在缓存行延迟内运行，同时保持可编程性。通过解耦RPC处理逻辑，实现微服务特定的执行，并将其置于LLC附近，立即消耗由网络卡注入的数据，Arcalis相比CPU基线实现了1.79-4.16倍的端到端加速，同时将微架构开销降低了高达88%，并实现了比先前解决方案高1.62倍的吞吐量。这些结果突显了近缓存RPC加速作为高性能微服务部署的实用解决方案的潜力。
英文摘要：
Modern microservices increasingly depend on high-performance remote procedure calls (RPCs) to coordinate fine-grained, distributed computation. As network bandwidths continue to scale, the CPU overhead associated with RPC processing, particularly serialization, deserialization, and protocol handling, has become a critical bottleneck. This challenge is exacerbated by fast user-space networking stacks such as DPDK, which expose RPC processing as the dominant performance limiter. While prior hardware accelerators have explored NIC-attached and FPGA-based offload, these approaches remain farther from the cache hierarchy, so the frequent data accesses during RPC processing each pay an extra interconnect traversal cost that inflates RPC time. Therefore, RPC handling should occur as close as possible to the cache; however, a near-cache solution must be small, hence practical and deployable. Our key insight to enable such a solution is taking advantage of a reconfigurable accelerator that can be configured specifically for the services currently running on the CPUs. We present Arcal\'ıs, a near-cache RPC accelerator that positions a lightweight hardware engine adjacent to the last-level cache (LLC). Arcal\'ıs offloads RPC processing to dedicated microengines that operate with cache-line latency while preserving programmability. By decoupling RPC processing logic, enabling microservice-specific execution, and positioning itself near the LLC, Arcal\'ıs achieves a 1.72-4.91$\times$ end-to-end speedup compared to the CPU baseline, significantly reduces microarchitectural overhead by up to 88\%, and achieves up to a 1.67$\times$ higher throughput than prior solutions. These results highlight the potential of near-cache RPC acceleration as a practical solution for high-performance microservice deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
