一句话：针对异构加速器上张量库手工开发周期长的问题，提出 FlexTensor 以实现灵活、可移植、高性能的张量计算。
张量计算在机器学习、数据分析和科学计算中极为重要，但其高昂计算代价要求面向 GPU、FPGA 等异构加速器提供灵活、可移植且高性能的库实现。现有张量库通常依赖程序员从算法、体系结构和编译等层面手工设计底层实现并进行优化，开发周期常达数月甚至数年，远慢于应用算法的快速演进。论文题目为 FlexTensor，摘要主要陈述上述问题与需求；所给摘要未具体披露其技术方法、系统组成或实验评估结果。
Tensor computation plays a paramount role in a broad range of domains, including machine learning, data analytics, and scientific computing. The wide adoption of tensor computation and its huge computation cost has led to high demand for flexible, portable, and high-performance library implementation on heterogeneous hardware accelerators such as GPUs and FPGAs. However, the current tensor library implementation mainly requires programmers to manually design low-level implementation and optimize from the algorithm, architecture, and compilation perspectives. Such a manual development process often takes months or even years, which falls far behind the rapid evolution of the application algorithms.
DOI 原文 ·
@inproceedings{paperbot5410,
title = {FlexTensor},
author = {Size Zheng and Yun Liang and Shuo Wang and Renze Chen and Kaiwen Sheng},
booktitle = {ASPLOS},
year = {2020},
doi = {10.1145/3373376.3378508}
}