CXL 内存扩展器中低开销通用近数据处理
Low-overhead General-purpose Near-Data Processing in CXL Memory Expanders
AI总结:
本文提出面向 CXL 内存的低开销通用近数据处理架构 M²NDP,通过内存映射函数和微线程机制实现高性能细粒度 NDP 卸载,相比被动式 CXL 内存的 CPU/GPU 主机实现最高 128 倍加速和 87.9% 能耗降低。
摘要:
新兴的 Compute Express Link (CXL) 能够在处理器本地 DRAM 之外实现高成本效益的内存扩展。尽管其 CXL.mem 协议通过优化的协议栈提供了极低的延迟开销,但频繁的 CXL 内存访问仍可能导致内存受限型应用出现显著减速,无论这些应用是延迟敏感型还是带宽密集型。CXL 控制器中的近数据处理(NDP)有望克服被动式 CXL 内存的这些局限。然而,先前关于 CXL 内存中 NDP 的工作提出了面向特定应用的单元,这些单元不适用于应支持各种应用的实用 CXL 内存系统。另一方面,现有的 CPU 或 GPU 核心对于 NDP 而言并不具备成本效益,因为它们并未针对内存受限型应用进行优化。此外,用于 NDP 卸载的主机处理器与 CXL 控制器之间的通信应当实现低延迟,但现有的基于 CXL.io/PCIe 的机制会产生微秒级延迟,不适合细粒度 NDP。为了实现端到端的高性能 NDP,我们提出了一种面向 CXL 内存的低开销通用 NDP 架构,称为 Memory-Mapped NDP (M²NDP),该架构由内存映射函数(M²func)和内存映射微线程(M²μthread)组成。M²func 是一种兼容 CXL.mem 的低开销通信机制,用于主机处理器与 CXL 内存中 NDP 控制器之间的通信。M²μthread 通过引入轻量级微线程来支持内核的高度并发执行,同时最大限度地减少资源浪费,从而实现低成本、通用的 NDP 单元设计。将二者结合,M²NDP 与配备被动式 CXL 内存的基线 CPU/GPU 主机相比,为各种工作负载实现了最高 128 倍(总体 14.5 倍)的显著加速,并将能耗降低了最高 87.9%(总体 80.3%)。
英文摘要:
Emerging Compute Express Link (CXL) enables cost-efficient memory expansion beyond the local DRAM of processors. While its CXL$.$mem protocol provides minimal latency overhead through an optimized protocol stack, frequent CXL memory accesses can result in significant slowdowns for memory-bound applications whether they are latency-sensitive or bandwidth-intensive. The near-data processing (NDP) in the CXL controller promises to overcome such limitations of passive CXL memory. However, prior work on NDP in CXL memory proposes application-specific units that are not suitable for practical CXL memory-based systems that should support various applications. On the other hand, existing CPU or GPU cores are not cost-effective for NDP because they are not optimized for memory-bound applications. In addition, the communication between the host processor and CXL controller for NDP offloading should achieve low latency, but existing CXL$.$io/PCIe-based mechanisms incur $μ$s-scale latency and are not suitable for fine-grained NDP. To achieve high-performance NDP end-to-end, we propose a low-overhead general-purpose NDP architecture for CXL memory referred to as Memory-Mapped NDP (M$^2$NDP), which comprises memory-mapped functions (M$^2$func) and memory-mapped $μ$threading (M$^2μ$thread). M$^2$func is a CXL$.$mem-compatible low-overhead communication mechanism between the host processor and NDP controller in CXL memory. M$^2μ$thread enables low-cost, general-purpose NDP unit design by introducing lightweight $μ$threads that support highly concurrent execution of kernels with minimal resource wastage. Combining them, M$^2$NDP achieves significant speedups for various workloads by up to 128x (14.5x overall) and reduces energy by up to 87.9% (80.3% overall) compared to baseline CPU/GPU hosts with passive CXL memory.
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。