arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.12558cs.ETcs.DCcs.LG
收藏

IMAC:6 T SRAM阵列中的内存多位乘法andACcumulation

IMAC: In-memory multi-bit Multiplication andACcumulation in 6T SRAM Array

Purdue University(普渡大学)

Mustafa Ali, Akhilesh Jaiswal, Sangamesh Kodge, Amogh Agrawal, Indranil Chakraborty, Kaushik Roy

摘要:

“存内计算”作为一种新的计算范例正在被广泛研究,以缓解众所周知的存储器瓶颈。这种新兴的范例旨在将计算的某些方面嵌入存储器阵列内,从而避免计算单元和存储存储器之间频繁且昂贵的数据移动。关于硅存储器的存内计算已经在各种存储器位单元上被广泛探索。在6晶体管(6 T)SRAM阵列内部嵌入计算是特别感兴趣的,因为它是最广泛使用的片上存储器。在本文中,我们提出了一种新的存储器中的乘法后累加操作能够执行并行点积在6 T SRAM中,而不需要任何改变的标准位单元。我们进一步研究了电路非理想性和工艺变化对LeNet-5和VGG神经网络架构分别针对MNIST和CIFAR-10数据集的准确性的影响。建议在内存中的点积机制实现了88.8%和99%的准确性CIFAR-10和MNIST,分别。与标准的冯诺依曼系统相比,该系统的能耗是标准系统的6.24倍,延迟是标准系统的9.42倍。

英文摘要:

`In-memory computing' is being widely explored as a novel computing paradigm to mitigate the well known memory bottleneck. This emerging paradigm aims at embedding some aspects of computations inside the memory array, thereby avoiding frequent and expensive movement of data between the compute unit and the storage memory. In-memory computing with respect to Silicon memories has been widely explored on various memory bit-cells. Embedding computation inside the 6 transistor (6T) SRAM array is of special interest since it is the most widely used on-chip memory. In this paper, we present a novel in-memory multiplication followed by accumulation operation capable of performing parallel dot products within 6T SRAM without any changes to the standard bitcell. We, further, study the effect of circuit non-idealities and process variations on the accuracy of the LeNet-5 and VGG neural network architectures against the MNIST and CIFAR-10 datasets, respectively. The proposed in-memory dot-product mechanism achieves 88.8% and 99% accuracy for the CIFAR-10 and MNIST, respectively. Compared to the standard von Neumann system, the proposed system is 6.24x better in energy consumption and 9.42x better in delay.

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。

↑