GPU-Accelerated Fixpoint Algorithms for Faster Compiler Analyses

被引：4
|
作者：
Blass, Thorsten [1 ]
Philippsen, Michael [1 ]
机构：
[1] Friedrich Alexander Univ Erlangen Nurnberg FAU, Erlangen, Germany
来源：
PROCEEDINGS OF THE 28TH INTERNATIONAL CONFERENCE ON COMPILER CONSTRUCTION (CC '19) | 2019年
关键词：
GPU; compiler; parallel interprocedual data-flow analysis; fixpoint algorithms; TOP-DOWN; EFFICIENT;
D O I：
10.1145/3302516.3307352
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
Inter-procedural data-flow analyses are slow. We parallelize these predicate propagation fixpoint algorithms efficiently on a GPU. Our approach is (mostly) synchronization free even though the processed graphs in general are cyclic and have nodes with fan-in and fan-out degrees above 1. We detect and fix any data races that occur while propagating predicates in a SIMD fashion. Additionally, we solve the parallel termination problem by means of heuristics. The GPU-codes of five data-flow analyses are up to 89.8 times faster than their sequential LLVM variants. Offloading the analyses to the GPU saves up to 26.5% of the total compilation time.
引用
收藏
页码：122 / 134
页数：13
相关论文
共 50 条
  • [1] GPU-accelerated parallel algorithms for linear rankSVM
    Jin, Jing
    Cai, Xianggao
    Lai, Guoming
    Lin, Xiaola
    [J]. JOURNAL OF SUPERCOMPUTING, 2015, 71 (11): : 4141 - 4171
  • [2] GPU-accelerated parallel algorithms for linear rankSVM
    Jing Jin
    Xianggao Cai
    Guoming Lai
    Xiaola Lin
    [J]. The Journal of Supercomputing, 2015, 71 : 4141 - 4171
  • [3] GPU-accelerated Faster Mean Shift with euclidean distance metrics
    You, Le
    Jiang, Han
    Chang, C. Hwa
    Chen, Lingxi
    Cui, Xintong
    Zhao, Mengyang
    Hu, Jinyong
    [J]. 2022 IEEE 46TH ANNUAL COMPUTERS, SOFTWARE, AND APPLICATIONS CONFERENCE (COMPSAC 2022), 2022, : 211 - 216
  • [4] Efficient OLAP algorithms on GPU-accelerated Hadoop clusters
    Hongzhi Wang
    Zheng Wang
    Ning Li
    Xinxin Kong
    [J]. Distributed and Parallel Databases, 2019, 37 : 507 - 542
  • [5] GPU-accelerated Hungarian algorithms for the Linear Assignment Problem
    Date, Ketan
    Nagi, Rakesh
    [J]. PARALLEL COMPUTING, 2016, 57 : 52 - 72
  • [6] Efficient OLAP algorithms on GPU-accelerated Hadoop clusters
    Wang, Hongzhi
    Wang, Zheng
    Li, Ning
    Kong, Xinxin
    [J]. DISTRIBUTED AND PARALLEL DATABASES, 2019, 37 (04) : 507 - 542
  • [7] Gpu-accelerated relaxed graph pattern matching algorithms
    Benachour, Amira
    Yahiaoui, Said
    Bouhenni, Sarra
    Kheddouci, Hamamache
    Nouali-Taboudjemat, Nadia
    [J]. JOURNAL OF SUPERCOMPUTING, 2024, 80 (15): : 21811 - 21836
  • [8] Faster than FAST: GPU-Accelerated Frontend for High -Speed VIO
    Nagy, Balazs
    Foehn, Philipp
    Scaramuzza, Davide
    [J]. 2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 4361 - 4368
  • [9] GPU-Accelerated Microdosimetry
    Decunha, J.
    Mohan, R.
    [J]. MEDICAL PHYSICS, 2022, 49 (06) : E467 - E468
  • [10] GPU-accelerated CellProfiler
    Chakroun, Imen
    Michiels, Nick
    Wuyts, Roel
    [J]. PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2018, : 321 - 326
12345