@inproceedings{491e19bae5b34f638596081831cdfd06,
title = "Simplifying low-level GPU programming with GAS",
abstract = "Many low-level optimizations for NVIDIA GPU can only be implemented in native hardware assembly (SASS). However, programming in SASS is unproductive and not portable. To simplify low-level GPU programming, we present GAS (Gpu ASsembly), a PTX-like language that provides a stable instruction set across hardware architectures while giving programmers a low-level control of code execution. We demonstrate that GAS can be used with ease for low-level benchmarking and performance tuning in the context of Tensor Core HGEMM. ",
keywords = "compiler, GPU, SASS",
author = "Da Yan and Wei Wang and Xiaowen Chu",
note = "Publisher Copyright: {\textcopyright} 2021 Owner/Author. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2021 ; Conference date: 27-02-2021 Through 03-03-2021",
year = "2021",
month = feb,
day = "17",
doi = "10.1145/3437801.3441591",
language = "English",
series = "Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP",
publisher = "Association for Computing Machinery (ACM)",
pages = "469--471",
booktitle = "PPoPP 2021 - Proceedings of the 2021 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming",
address = "United States",
}