arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.01629cs.DCcs.AR
收藏

TeraPool:一种具有物理设计意识的、包含1024个RISC-V核心的共享L1内存扩展集群设计,配备高带宽主内存链路

TeraPool: A Physical Design Aware, 1024 RISC-V Cores Shared-L1-Memory Scaled-up Cluster Design with High Bandwidth Main Memory Link

ETH Zurich(苏黎世联邦理工学院);University of Bologna(博洛尼亚大学)

Yichao Zhang, Marco Bertuletti, Chi Zhang, Samuel Riedel, Diyou Shen, Bowen Wang, Alessandro Vanelli-Coralli, Luca Benini

AI总结:

TeraPool通过低延迟分层互连实现高带宽主内存链路,支持1024个RISC-V核心的共享L1内存扩展集群,实现高能效和高性能。

摘要:

在现代大规模并行计算架构(例如GP-GPU)中,流线型指令处理器(处理元素-PEs)的共享L1内存集群常被用作基本构建块。通过增加集群数量来扩展这些架构会带来计算和功耗开销,这是由于需要将大数据结构分割成块并通过高延迟的全局互连在内存层次结构中移动块。扩展集群可以减少缓冲、复制和同步开销。然而,完全连接的核到L1内存交叉开关的复杂性随着PE数量的增加而呈二次增长,这构成了主要的物理实现挑战。我们提出了TeraPool,这是一种可物理实现的、具有>1000个浮点运算能力的RISC-V PE扩展集群设计,通过低延迟的分层互连(1-7/9/11周期,取决于目标频率)共享多兆字节>4000银行的L1内存。在12nm FinFET工艺中实现,TeraPool达到了接近吉赫兹频率(910MHz)的典型值,0.80V/25°C。能量高效的PE到L1内存分层互连仅消耗9-13.5pJ用于内存银行访问,仅是FP32 FMA成本的0.74-1.1倍。设计了一条高带宽主内存链路以管理共享L1内存的数据传输,以维持在HBM2E主内存的完整带宽下的数据传输。在910MHz下,该集群在基准内核中可提供高达1.89单精度TFLOP/s的峰值性能,以及高达200GFLOP/s/W的能效(在平均较高的IPC/PE为0.8的情况下),证明了将共享L1集群扩展到1000个PE的可行性,这比文献中报告的最大集群的PE数量大四倍。

英文摘要:

Shared L1-memory clusters of streamlined instruction processors (processing elements - PEs) are commonly used as building blocks in modern, massively parallel computing architectures (e.g. GP-GPUs). Scaling out these architectures by increasing the number of clusters incurs computational and power overhead, caused by the requirement to split and merge large data structures in chunks and move chunks across memory hierarchies via the high-latency global interconnect. Scaling up the cluster reduces buffering, copy, and synchronization overheads. However, the complexity of a fully connected cores-to-L1-memory crossbar grows quadratically with PE-count, posing a major physical implementation challenge. We present TeraPool, a physically implementable, >1000 floating-point-capable RISC-V PEs scaled-up cluster design, sharing a Multi-MegaByte >4000-banked L1 memory via a low latency hierarchical interconnect (1-7/9/11 cycles, depending on target frequency). Implemented in 12nm FinFET technology, TeraPool achieves near-gigahertz frequencies (910MHz) typical, 0.80 V/25C. The energy-efficient hierarchical PE-to-L1-memory interconnect consumes only 9-13.5pJ for memory bank accesses, just 0.74-1.1x the cost of a FP32 FMA. A high-bandwidth main memory link is designed to manage data transfers in/out of the shared L1, sustaining transfers at the full bandwidth of an HBM2E main memory. At 910MHz, the cluster delivers up to 1.89 single precision TFLOP/s peak performance and up to 200GFLOP/s/W energy efficiency (at a high IPC/PE of 0.8 on average) in benchmark kernels, demonstrating the feasibility of scaling a shared-L1 cluster to a thousand PEs, four times the PE count of the largest clusters reported in literature.

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。

↑