High-performance SIMT code generation in an active visual effects library

Jay L.T. Cornwall, Lee Howes, Paul H.J. Kelly, Phil Parsonage, Bruno Nicoletti
Department of Computing, Imperial College London, UK
Proceedings of the 6th ACM conference on Computing frontiers, CF ’09, 2009


   title={High-performance SIMT code generation in an active visual effects library},

   author={Cornwall, J.L.T. and Howes, L. and Kelly, P.H.J. and Parsonage, P. and Nicoletti, B.},

   booktitle={Proceedings of the 6th ACM conference on Computing frontiers},





Download Download (PDF)   View View   Source Source   



SIMT (Single-Instruction Multiple-Thread) is an emerging programming paradigm for high-performance computational accelerators, pioneered in current and next generation GPUs and hybrid CPUs. We present a domain-specific active-library supported approach to SIMT code generation and optimisation in the field of visual effects. Our approach uses high-level metadata and runtime context to guide and to ensure the correctness of optimisation-driven code transformations and to implement runtime-context-sensitive optimisations. Our advanced optimisations require no analysis of the original C++ kernel code and deliver 1.3x to 6.6x speedups over syntax-directed translation on GeForce 8800 GTX and GTX 260 GPUs with two commercial visual effects.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2020 hgpu.org

All rights belong to the respective authors

Contact us: