• Home
  • Search
  • Software-based branch predication for AMD GPUs
  • Cite Icon9
  • https://doi.org/10.1145/1926367.1926379Copy DOI Icon

Software-based branch predication for AMD GPUs

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Branch predication is a program transformation technique that combines instructions of multiple branches of an if statement into a straight-line sequence and associates each instruction of the sequence with a predicate. The branch predication improves the execution of branch statements on processors that support predicated execution of instruction, e.g., Intel IA-64, because such transformation improves the instruction scheduling and might help cache performance. This paper proposes a novel software-based branch predication technique for GPU. The main motivation is that branch instructions can easily become a performance bottleneck for a GPU program because of the cost of branch instructions compared to ALU instructions and the possibility of low ALU utilization due to separation of ALU instructions within control flow blocks. Due to the SIMD nature and massive multi-threading architecture of the GPU, branching can be costly if more than one path is taken by a set of concurrent threads in a kernel. In this paper we reveal that branch predication can enable instruction packing, a VLIW-like GPU feature that is designed to increase the parallel execution of independent instructions, and can also decrease the number of control flow instructions thereby improving the performance of GPU kernels with both single and multiple branch paths. The key of our novel branch predication technique is a set of transformation rules that takes into consideration the specialties of the GPU architecture and implements software-based predicated execution of instruction on the GPU with little to no overhead. Furthermore, we identify architectural and program factors that affect the effectiveness of our technique and build a benefit analysis model for the transformation. The implementation of our technique on synthetic benchmarks and real-world application proves its effectiveness.

Similar Papers
  • Research Article
  • Citations3

BeCFI: detecting hidden control flow with performance monitoring counters

  • Jan 01, 2016
  • International Journal of High Performance Computing and Networking
  • Hongwei Zhou +3
  • Research Article
  • Citations4

Derivation of Efficient Logic Programs by Specialization and Reduction of Nondeterminism

  • Jun 01, 2005
  • Higher-Order and Symbolic Computation
  • Alberto Pettorossi +2
  • PDF
  • Research Article
  • Citations12

Learning metamorphic malware signatures from samples

  • Feb 19, 2021
  • Journal of Computer Virology and Hacking Techniques
  • Marco Campion +2
  • Conference Article
  • Citations6

Towards the memory forensics of OOP execution behavior

  • Aug 01, 2017
  • Ziad A Al-Sharif +2
  • Book Chapter
  • Citations14

Control Flow Driven Splitting of Loop Nests at the Source Code Level

  • Dec 30, 2005
  • Heiko Falk +2
  • Research Article
  • Citations8

Microarchitectural mechanisms to exploit value structure in SIMT architectures

  • Jun 23, 2013
  • ACM SIGARCH Computer Architecture News
  • Ji Kim +4
  • Conference Article
  • Citations27

Completion time multiple branch prediction for enhancing trace cache performance

  • Jan 01, 2000
  • Ryan Rakvic +2
  • Conference Article
  • Citations1

Urine sediment image recognition method based on re-parameterization network

  • Apr 14, 2022
  • Zhangwei Wu +1
  • PDF
  • Research Article
  • Citations21

The kinetics of multibranch integration on the dendritic arbor of CA1 pyramidal neurons

  • May 13, 2014
  • Frontiers in Cellular Neuroscience
  • Sunggu Yang +2
  • Conference Article

Convergence and Scalarization in Whole Function Vectorization

  • Dec 01, 2013
  • Feng Yue +3
  • Research Article
  • Citations18

Branch elimination by condition merging

  • Nov 17, 2004
  • Software: Practice and Experience
  • William C Kreahling +5
  • Research Article
  • Citations30

Efficient solutions to the placement and chaining problem of User Plane Functions in 5G networks

  • Nov 08, 2021
  • Journal of Network and Computer Applications
  • Irian Leyva-Pupo +1
  • Conference Article

Different Modes of Gas Entrainment Through Bottom Discharge Branch by Using Three Dimensional Particle Image Velocimetry System

  • Jan 01, 2007
  • Wael Fairouz Saleh +1
  • Conference Article
  • Citations2

Fully automated carotid plaque segmentation in combined B-mode and contrast enhanced ultrasound

  • Sep 01, 2014
  • Zeynettin Akkus +8
  • Research Article

Late Quaternary activity of Wulashan Northern fault, North China

  • Aug 16, 2024
  • Frontiers in Earth Science
  • Leihua Wei +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.