A unified resistive RAM (ReRAM) processing-in-memory accelerator for a CNN-LSTM attention workload that integrates convolutional, recurrent, attention, and multi-layer perceptron (MLP) stages within a crossbar-based framework, reducing intermediate data movement between spatial and temporal branches.
Abstract
Early screening of depression requires efficient analysis of audio and speech data, while conventional CPU and GPU platforms incur high latency and energy consumption for CNN-LSTM inference. To address this challenge, we propose a unified resistive RAM (ReRAM) processing-in-memory accelerator for a CNN-LSTM attention workload. The architecture integrates convolutional, recurrent, attention, and multi-layer perceptron (MLP) stages within a crossbar-based framework, reducing intermediate data movement between spatial and temporal branches. CNN operations are mapped through im2col-based vectorization, while LSTM gate computations are reformulated using concatenated input-state vectors and mapped onto ReRAM crossbars. We further provide module-level workload breakdown, parameter sensitivity analysis, and matched-workload context against representative ReRAM/PIM accelerators. Experimental results show 32.1 times and 9.3 times latency reduction over CPU and GPU baselines, respectively, with about 160 times and 140 times energy reduction. Simplified weight-perturbation tests characterize ASLF sensitivity in an untrained pipeline with synthetic spectrogram-shaped inputs. Task-level prediction accuracy and robustness remain to be evaluated.
Deep learning (DL) models for real-time wearable sleep staging often rely on long-kernel temporal convolutions, a requirement that current accelerators struggle to support efficiently. To overcome this, we present an FPGA-based CNN-BiLSTM accelerator that incorporates several algorithm-hardware co-design techniques to...
Aaron Zhou, Ya-Qian Xu, Chen Chen et al.· 1 citation
This letter presents a mixed-precision CNN–LSTM accelerator for EEG-based sleep staging. To efficiently execute long temporal convolutions, a serpentine dataflow propagates activations between neighboring processing elements (PEs), reducing memory accesses by <inline-formula> <tex-math notation="LaTeX">$6.2\times $ </t...
The domain-specific hardware accelerators for deep neural network (DNN) inference have been widely adopted, particularly in resource-constrained edge computing scenarios but face a fundamental tradeoff among accuracy, on-chip resource utilization, and inference latency. Traditional compression techniques, such as pruni...
Chung-Mou Pan, Swarnalata Panigrahy, Salma Elmalaki et al.· IEEE Embedded Systems Letter...· 0 citations
As CPUs alone are often insufficiently efficient for running Vision Transformers (ViTs), contemporary computing platforms, particularly edge systems, increasingly adopt heterogeneous architectures that combine CPUs with GPUs and Neural Processing Units (NPUs). This paper presents a detailed energy assessment of individ...
Li-Xian Ho, C. Kachris· Applied Sciences· 0 citations