VWC-SDK: Convolutional Weight Mapping Using Shifted and Duplicated Kernel With Variable Windows and Channels
- 9 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 12 (2) , 408-421
Abstract
With their high energy efficiency, processing-in-memory (PIM) arrays are being increasingly used for the convolutional neural network (CNN) inference. In the PIM-based CNN inference, the computational latency and energy are dependent on how the CNN weights are mapped to the PIM array. A recent study proposed the shifted and duplicated kernel (SDK) mapping that reuses input feature maps with a unit of a parallel window, which is convolved with duplicated kernels to obtain multiple output elements in parallel. However, the existing SDK-based mapping algorithm does not always result in minimum computing cycles because it only maps a square-shaped parallel window with the entire channels. In this paper, we introduce a novel mapping algorithm called variable-window SDK (VW-SDK), which adaptively determines the shape of the parallel window that leads to the minimum computing cycles for the given convolutional layer and PIM array. By allowing rectangular-shaped windows with partial channels, VW-SDK utilizes the PIM array more efficiently, thereby further reducing the number of computing cycles. To further remove the inefficient computing cycles caused by the residual channels, we extend the VW-SDK algorithm into VWC-SDK (SDK with variable windows and channels) that additionally performs residual channel pruning. The simulation with a $512\times 512$ PIM array and ResNet-20 shows that VW-SDK improves the inference speed by $1.29\times $ compared to the existing SDK-based algorithm. The results also show that residual channel pruning improves the inference speed of ResNet-20 by up to $\sim 1.38\times $ when compared to the original network without pruning.
Keywords
Funding Information
- Ministry of Science and ICT (MSIT) of Korea under the National Research Foundation (2020M3H2A1076786)
- Institute of Information and Communication Technology Planning Evaluation (IITP) Grants for the AI Graduate School Program (IITP-2019-0-00421)
- Information Technology Research Center (ITRC) Program (IITP-2021-0-02052)
- ICT Creative Consilience program (IITP-2020-0-01821)
- Artificial Intelligence Innovation Hub Program (IITP-2021-0-02068)
This publication has 28 references indexed in Scilit:
- CONV-SRAM: An Energy-Efficient SRAM With In-Memory Dot-Product Computation for Low-Power Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2018
- Mixed size crossbar based RRAM CNN accelerator with overlapped mapping method2018
- A Multi-Functional In-Memory Inference Processor Using a Standard 6T SRAM ArrayIEEE Journal of Solid-State Circuits, 2018
- Channel Pruning for Accelerating Very Deep Neural Networks2017
- Deep Pyramidal Residual Networks2017
- In-Memory Computation of a Machine-Learning Classifier in a Standard 6T SRAM ArrayIEEE Journal of Solid-State Circuits, 2017
- PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning2017
- Efficient Mobile Implementation of A CNN-based Object Recognition System2016
- Switched by input2016
- Deep Residual Learning for Image Recognition2016