一句话：提出首个端到端编译流 CINM，以层次化抽象统一异构 CIM/CNM 设备并实现设备无关与设备感知优化。
数据密集型应用暴露了传统冯·诺依曼架构的访存瓶颈，存内计算（CIM）与近存计算（CNM）等非冯·诺依曼范式可大幅提升性能与能效，但其编程模型仍过于底层且绑定特定实现，可编程性差。本文提出 CINM（Cinnamon），首个端到端编译流，利用层次化抽象统一不同 CIM/CNM 设备，支持设备无关与设备感知优化。Cinnamon 对输入程序进行渐进式 lowering，并在流水线各层执行优化。作者在真实 CNM 系统 UPMEM 与忆阻器 CIM 加速器上用一组基准评估，表明其能为多硬件目标生成与现有最优实现相当或更优的高性能代码。
The rise of data-intensive applications exposed the limitations of conventional processor-centric von-Neumann architectures that struggle to meet the off-chip memory bandwidth demand. Therefore, recent innovations in computer architecture advocate compute-in-memory (CIM) and compute-near-memory (CNM), non-von-Neumann paradigms achieving orders-of-magnitude improvements in performance and energy consumption. Despite significant technological breakthroughs in the last few years, the programmability of these systems is still a serious challenge. Their programming models are too low-level and specific to particular system implementations. Since such future architectures are predicted to be highly heterogeneous, developing novel compiler abstractions and frameworks becomes necessary. To this end, we present CINM (Cinnamon), a first end-to-end compilation flow that leverages the hierarchical abstractions to generalize over different CIM and CNM devices and enable device-agnostic and device-aware optimizations. Cinnamon progressively lowers input programs and performs optimizations at each level in the lowering pipeline. To show its efficacy, we evaluate CINM on a set of benchmarks for a real CNM system (UPMEM) and the memristors-based CIM accelerators. We show that Cinnamon, supporting multiple hardware targets, generates high-performance code comparable to or better than state-of-the-art implementations.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2301-07486,
title = {CINM (Cinnamon): A Compilation Infrastructure for Heterogeneous Compute In-Memory and Compute Near-Memory Paradigms},
author = {Asif Ali Khan and Hamid Farzaneh and Karl Friedrich Alexander Friebel and Clément Fournier and Lorenzo Chelini and Jeronimo Castrillon},
booktitle = {ASPLOS},
year = {2024},
doi = {10.1145/3622781.3674189}
}