arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.13378cs.AR
收藏

MultPIM:用于内存处理的快速状态乘法

MultPIM: Fast Stateful Multiplication for Processing-in-Memory

Orian Leitersdorf, Ronny Ronen, Shahar Kvatinsky

摘要:

内存处理(PIM)试图使用支持存储和逻辑的设备来消除计算/内存数据传输。有状态逻辑技术,如IMPERT、MAGIC和FELIX,可以在具有大规模并行性的忆阻交叉开关阵列内执行逻辑门。基于状态逻辑的乘法运算由于其广泛的应用前景而成为一个活跃的研究领域。最近,RIME已经成为最先进的有状态单行乘法算法,通过使用忆阻分区,将之前最先进的延迟减少了5.1倍。在本文中,我们首先提出了新的基于分区的计算技术的广播和移动数据。然后,我们设计了一个基于进位保留加法移位(CSAS)技术的内存乘法算法。最后,我们开发了一种新的有状态全加器,显着提高了国家的最先进的(FELIX)的设计。这些贡献构成了MultPIM,一种将最先进的时间复杂度从二次降低到线性对数的乘法器。对于32位数字,MultPIM将延迟提高了RIME的4.2倍,同时还略微降低了面积开销。此外,我们优化了MultPIM的全精度矩阵向量乘法,并将延迟提高了25.5倍。

英文摘要:

Processing-in-memory (PIM) seeks to eliminate computation/memory data transfer using devices that support both storage and logic. Stateful logic techniques such as IMPLY, MAGIC and FELIX can perform logic gates within memristive crossbar arrays with massive parallelism. Multiplication via stateful logic is an active field of research due to the wide implications. Recently, RIME has become the state-of-the-art algorithm for stateful single-row multiplication by using memristive partitions, reducing the latency of the previous state-of-the-art by 5.1x. In this paper, we begin by proposing novel partition-based computation techniques for broadcasting and shifting data. Then, we design an in-memory multiplication algorithm based on the carry-save add-shift (CSAS) technique. Finally, we develop a novel stateful full-adder that significantly improves the state-of-the-art (FELIX) design. These contributions constitute MultPIM, a multiplier that reduces state-of-the-art time complexity from quadratic to linear-log. For 32-bit numbers, MultPIM improves latency by an additional 4.2x over RIME, while even slightly reducing area overhead. Furthermore, we optimize MultPIM for full-precision matrix-vector multiplication and improve latency by 25.5x over FloatPIM matrix-vector multiplication.

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。

↑