深度神经网络加速器快速准确性能模型的自动生成
Automatic Generation of Fast and Accurate Performance Models for Deep Neural Network Accelerators
AI总结：
本文提出一种面向DNN加速器的性能模型自动生成方法，通过DNN/硬件依赖图联合分析，在保持低MAPE的同时以远快于RTL仿真的速度估计延迟。
摘要：
在资源受限的边缘设备上实现深度神经网络（DNN）是一项具有挑战性的任务，需要定制的硬件加速器架构，并清晰理解其在执行目标AI工作负载时的性能特征。为此，我们提出一种快速性能模型的自动生成方法，用于准确估计映射到系统化建模且简洁描述的加速器架构上的DNN延迟。利用我们的加速器架构描述方法，我们对代表性DNN加速器进行了建模，例如Gemmini、UltraTrail、Plasticine衍生架构以及可参数化的脉动阵列。结合这些建模架构的DNN映射，我们执行DNN/硬件依赖图的联合分析，在最佳情况下仅需评估154次循环内核迭代即可估计41.9亿条指令的性能，实现显著加速。与仿真结果相比，我们在平均绝对百分比误差（MAPE）方面优于回归模型和分析模型，同时比RTL仿真快数个数量级。
英文摘要：
Implementing Deep Neural Networks (DNNs) on resource-constrained edge devices is a challenging task that requires tailored hardware accelerator architectures and a clear understanding of their performance characteristics when executing the intended AI workload. To facilitate this, we present an automated generation approach for fast performance models to accurately estimate the latency of a DNN mapped onto systematically modeled and concisely described accelerator architectures. Using our accelerator architecture description method, we modeled representative DNN accelerators such as Gemmini, UltraTrail, Plasticine-derived, and a parameterizable systolic array. Together with DNN mappings for those modeled architectures, we perform a combined DNN/hardware dependency graph analysis, which enables us, in the best case, to evaluate only 154 loop kernel iterations to estimate the performance for 4.19 billion instructions achieving a significant speedup. We outperform regression and analytical models in terms of mean absolute percentage error (MAPE) compared to simulation results, while being several magnitudes faster than an RTL simulation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
