High-Throughput Approximate Multiplication Models in PyTorch
2023 26th International Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS)(2023)
摘要
Approximate multipliers can reduce the resource consumption of neural network accelerators. To study their effects on an application, they need to be simulated during network training. We develop simulation models for a common class of approximate multipliers. Our models speed up execution by replacing time-consuming type conversions and memory accesses with fast floating-point arithmetic. Across six different neural network architectures, these models increase throughput by 2.7× over the commonly used array lookup while recreating behavioral simulation with high fidelity.
更多查看译文
关键词
neural networks, approximate computing, deep learning
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