应用驱动的致密铁电嵌入式非易失性存储器设计探索
Application-driven Design Exploration for Dense Ferroelectric Embedded Non-volatile Memories
摘要:
内存墙瓶颈是许多数据密集型应用程序面临的一个关键挑战。基于多层FeFET的嵌入式非易失性存储器是一种有前途的解决方案,用于更密集和更节能的片上存储器。然而,可靠的多级单元存储需要仔细优化,以最大限度地减少设计开销成本。在这项工作中,我们研究FeFET器件特性,编程方案和存储器阵列架构之间的相互作用,并探索不同的设计选择,以优化关键数据密集型工作负载的性能,能源,面积和精度指标。从我们的跨栈设计探索中,我们发现我们可以以超过8 MB/mm^2的密度和低于2ns的读取访问延迟存储DNN权重和社交网络图,而不会损失应用程序的准确性。
英文摘要:
The memory wall bottleneck is a key challenge across many data-intensive applications. Multi-level FeFET-based embedded non-volatile memories are a promising solution for denser and more energy-efficient on-chip memory. However, reliable multi-level cell storage requires careful optimizations to minimize the design overhead costs. In this work, we investigate the interplay between FeFET device characteristics, programming schemes, and memory array architecture, and explore different design choices to optimize performance, energy, area, and accuracy metrics for critical data-intensive workloads. From our cross-stack design exploration, we find that we can store DNN weights and social network graphs at a density of over 8MB/mm^2 and sub-2ns read access latency without loss in application accuracy.
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。