The exploration of Processing-In-Memory (PIM) accelerators has garnered
significant attention within the research community. However, the utilization
of large-scale neural networks on Processing-In-Memory (PIM) accelerators
encounters challenges due to constrained on-chip memory capacity. To tackle
this issue, current works explore model compression algorithms to reduce the
size of Convolutional Neural Networks (CNNs). Most of these algorithms either
aim to represent neural operators with reduced-size parameters (e.g.,
quantization) or search for the best combinations of neural operators (e.g.,
neural architecture search). Designing neural operators to align with PIM
accelerators' specifications is an area that warrants further study. In this
paper, we introduce the Epitome, a lightweight neural operator offering
convolution-like functionality, to craft memory-efficient CNN operators for PIM
accelerators (EPIM). On the software side, we evaluate epitomes' latency and
energy on PIM accelerators and introduce a PIM-aware layer-wise design method
to enhance their hardware efficiency. We apply epitome-aware quantization to
further reduce the size of epitomes. On the hardware side, we modify the
datapath of current PIM accelerators to accommodate epitomes and implement a
feature map reuse technique to reduce computation cost. Experimental results
reveal that our 3-bit quantized EPIM-ResNet50 attains 71.59% top-1 accuracy on
ImageNet, reducing crossbar areas by 30.65 times. EPIM surpasses the
state-of-the-art pruning methods on PIM.

为了解决处理内存加速器上大规模神经网络的受限芯片内存容量所带来的挑战，本文介绍了 Epitome，这是一个轻量级神经算子，为处理内存加速器（EPIM）设计了高效的卷积操作符。实验结果表明，我们的 3 位量化 EPIM-ResNet50 在 ImageNet 上达到了 71.59% 的 top-1 准确率，将交叉栏面积降低了 30.65 倍，超过了 PIM 的最先进修剪方法。