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

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 activelibrary 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

• Type: Conference
• Year: 2009
• Where: CF
• Authors: Jay L. T. Cornwall, Lee W. Howes, Paul H. J. Kelly, Phil Parsonage, Bruno Nicoletti
• Keywords: Activelibrary Supported Approach, Applied Computing, CF 2009, Generation Gpus, Optimisation-driven Code Transformations