Hardware-aware 3D Model Workload Selection and Characterization for Graphics and ML Applications
Hardware-aware 3D Model Workload Selection and Characterization for Graphics and ML Applications
复制标题
DOI：
10.1109/isqed54688.2022.9806296
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Ruihao Li;Aman Arora;Sikan Li;Qinzhe Wu;L. John
中科院分区：
文献类型：
--
作者：
Ruihao Li;Aman Arora;Sikan Li;Qinzhe Wu;L. John
3D模型被广泛用于计算机图形，计算机视觉和机器人技术应用程序中。多个硬件加速器用于运行3D模型相关的应用程序，因为3D空间中模型所需的计算比2D空间中的计算高的数量级。由于3D模型工作负载的高计算强度，因此在加速器设计期间，使用大型3D模型数据集进行性能表征并不是可行的选择。代表性子集被广泛用于节省执行时间或仿真时间，例如ModelNet10（ModelNet40的子集）在机器学习（ML）域中广泛使用以节省训练和推理时间。但是，该子集由程序员从软件和应用程序的角度选择。在本文中，我们部署了基于统计分析的方法来指导识别硬件感知的代表性子集，该子集可以保持更高的性能准确性，并在尊重方面实现更大的执行时间节省。由软件程序员选择的子集。我们认为，本文提出的方法可以帮助硬件建筑师和工程师迅速设计有效的图形或ML加速器。
3D models are widely used in computer graphics, computer vision, and robotics applications. Multiple hardware accelerators are used for running 3D model related applications, since the computations required for models in 3D space are an order of magnitude higher than the computations in 2D space. Due to the high computation intensity of 3D model workloads, using large 3D model datasets for performance characterization is not a feasible choice during accelerator design. Representative subsets are widely used to save the execution or simulation time, e.g, ModelNet10, a subset of ModelNet40, is widely used in the machine learning (ML) domain to save training and inference time. However, this subset is picked by programmers from a software and application perspective.In this paper, we deploy statistical analysis based methodologies to guide the identification of hardware-aware representative subsets, which can maintain higher performance accuracy and achieve larger execution time savings with respect to subsets picked by software programmers. We believe that the methodology proposed in this paper can help hardware architects and engineers design efficient graphics or ML accelerators rapidly.