arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.05321cs.AR
收藏

MultiVic:一种用于神经网络推断的优化RISC-V多核处理器

MultiVic: A Time-Predictable RISC-V Multi-Core Processor Optimized for Neural Network Inference

FZI Research Center for Information Technology(FZI信息技术研究中心);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Maximilian Kirschner, Konstantin Dudzik, Ben Krusekamp, Jürgen Becker

AI总结:

MultiVic是一种优化用于神经网络推断的RISC-V多核处理器,通过可预测的核心和本地暂存器内存实现高性能和低时间波动。

摘要:

实时系统,特别是用于自动驾驶等领域的系统,正在越来越多地采用神经网络。从这一趋势中产生了对高性能硬件具有可预测定时行为的需求。虽然最先进的实时硬件往往面临内存和计算资源有限的问题,而现代AI加速器通常由于内存干扰缺乏关键的可预测性。我们提出了一种新的硬件架构来弥合性能和可预测性之间的差距。该架构包含具有本地暂存器内存的多核向量处理器,每个核心都配备了本地暂存器内存。一个中央管理核心按照静态确定的计划协调对共享外部内存的访问。为了评估所提出的硬件架构,我们分析了我们参数化设计的不同变体。我们将这些变体与由单核向量处理器和大向量寄存器组成的基线架构进行比较。我们发现,具有更多较小核心的配置由于增加的有效内存带宽和更高的时钟频率而性能更好。对于实时系统来说,执行时间波动仍然非常低,展示了该平台的时间可预测性。

英文摘要:

Real-time systems, particularly those used in domains like automated driving, are increasingly adopting neural networks. From this trend arises the need for high-performance hardware exhibiting predictable timing behavior. While state-of-the-art real-time hardware often suffers from limited memory and compute resources, modern AI accelerators typically lack the crucial predictability due to memory interference. We present a new hardware architecture to bridge this gap between performance and predictability. The architecture features a multi-core vector processor with predictable cores, each equipped with local scratchpad memories. A central management core orchestrates access to shared external memory following a statically determined schedule. To evaluate the proposed hardware architecture, we analyze different variants of our parameterized design. We compare these variants to a baseline architecture consisting of a single-core vector processor with large vector registers. We find that configurations with a larger number of smaller cores achieve better performance due to increased effective memory bandwidth and higher clock frequencies. Crucially for real-time systems, execution time fluctuation remains very low, demonstrating the platform's time predictability.

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。

↑