RAPIDNN: In-Memory Deep Neural Network Acceleration Framework

Abstract

Deep neural networks (DNN) have demonstrated effectiveness for various applications such as image processing, video segmentation, and speech recognition. Running state-of-the-art DNNs on current systems mostly relies on either generalpurpose processors, ASIC designs, or FPGA accelerators, all of which suffer from data movements due to the limited onchip memory and data transfer bandwidth. In this work, we propose a novel framework, called RAPIDNN, which processes all DNN operations within the memory to minimize the cost of data movement. To enable in-memory processing, RAPIDNN reinterprets a DNN model and maps it into a specialized accelerator, which is designed using non-volatile memory blocks that model four fundamental DNN operations, i.e., multiplication, addition, activation functions, and pooling. The framework extracts representative operands of a DNN model, e.g., weights and input values, using clustering methods to optimize the model for in-memory processing. Then, it maps the extracted operands and their precomputed results into the accelerator memory blocks. At runtime, the accelerator identifies computation results based on efficient in-memory search capability which also provides tunability of approximation to further improve computation efficiency. Our evaluation shows that RAPIDNN achieves 68.4x, 49.5x energy efficiency improvement and 48.1x, 10.9x speedup as compared to ISAAC and PipeLayer, the state-of-the-art DNN accelerators, while ensuring less than 0.3% of quality loss.

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Scikit-learn: Machine Learning in Python
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Compressing Neural Networks with the Hashing Trick
• A Complementary Resistive Switch-based Crossbar Array Adder
• SC-DCNN: Highly-Scalable Deep Convolutional Neural Network using Stochastic Computing
• NullaNet: Training Deep Neural Networks for Reduced-Memory-Access Inference
• Teaching Deep Convolutional Neural Networks to Play Go
• Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks

Cited by in corpus (3)

• MemTorch: An Open-source Simulation Framework for Memristive Deep Learning Systems
• FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator
• EDEN: Enabling Energy-Efficient, High-Performance Deep Neural Network Inference Using Approximate DRAM