前言
当前主流的基于polyhedral model的deep learning compiler 例如Tensor Comprehensions（Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions）都用到了schedule tree技术，这里简单介绍。
from: http://impact.gforge.inria.fr/impact2017/papers/impact-17-a-general-compilation-algorithm-to-parallelize-and-optimize-counted-loops-with-dynamic-data-dependences_slides.pdf
Schedule tree节点类型
Filter node：选择部分statement instances来做schedule
Band node：节点内所有statement instances都进行schedule
sequence与set node：子节点分别是有序和无序执行
Domain node和Context node比较容易理解，上面图中解释已经很清晰了。
mark node：A mark node allows the user to mark specific subtrees of the schedule tree.
extension node：introduce auxiliary computations that are not part of the original iteration domain, which is useful for, e.g., introducing statements copying data to and from shared memory.
Example (from tensor comprehensions):
Schedule tree operation
参考文献Schedule Trees
注：本文主要内容摘自/改编自文中已注释的和下面列出的参考文献等，欢迎大家批评指正。
S. Verdoolaege, S. Guelton, T. Grosser, and A. Cohen. Schedule Trees. In 4th Workshop on
Polyhedral Compilation Techniques (IMPACT, Associated with HiPEAC), page 9, Vienna, Austria,
Jan. 2014.http://impact.gforge.inria.fr/impact2014/papers/impact2014-verdoolaege.pdf
Oleksandr Zinenko, Lorenzo Chelini, Tobias Grosser. Declarative Transformations in the Polyhedral Model. [Research Report] RR-9243, Inria; ENS Paris - Ecole Normale Supérieure de Paris; ETH Zurich; TU Delft; IBM Zürich. 2018. ffhal-01965599f. https://hal.inria.fr/hal-01965599/document
Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
Polyhedral AST Generation Is More Than Scanning Polyhedra.
Polyhedral Parallel Code Generation for CUDA
https://dl.acm/doi/pdf/10.1145/2400682.2400713
Diesel: DSL for linear algebra and neural net computations on gpus
发布者：admin，转转请注明出处：http://www.yc00.com/web/1755003574a5225695.html
评论列表（0条）