Deep Learning Acceleration with Neuron-to-Memory Transformation
2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)(2020)
摘要
Deep neural networks (DNN) have demonstrated effectiveness for various applications such as image processing, video segmentation, and speech recognition. Running state-of-theart 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 on-chip memory and data transfer bandwidth. In this work, we propose a novel framework, called RAPIDNN, which performs neuron-to-memory transformation in order to accelerate DNNs in a highly parallel architecture. 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 pre-computed 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 improve computation efficiency further. Our evaluation shows that RAPIDNN achieves 68.4×, 49.5× energy efficiency improvement and 48.1×, 10.9× speedup as compared to ISAAC and PipeLayer, the state-of-the-art DNN accelerators, while ensuring less than 0.5% quality loss.
更多查看译文
关键词
on-chip memory,data transfer bandwidth,neuron-to-memory transformation,highly parallel architecture,DNN model,nonvolatile memory blocks,in-memory processing,accelerator memory blocks,in-memory search capability,DNN accelerators,deep neural networks,data movements,RAPIDNN
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要