Explicit Dependence Metadata in an Active Visual Effects Library

Cornwall, Jay L. T.; Parsonage, Phil; Nicoletti, Bruno

doi:10.1007/978-3-540-85261-2_12

Cited by 4 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous work [4] we described a framework for constructing image processing algorithms from DAGs of primitive operations and generating optimised code for a CPU through cross-component loop and kernel transformations. We revisit and extend this framework in Section 2 to support more complex primitives, but the fundamental principles involved in our earlier CPU optimisation work remain unchanged for SIMT devices: a testament to the robustness of a domain-specific metadata-supported approach.…”

Section: Introductionmentioning

confidence: 99%

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

Cornwall

Howes

Parsonage

et al. 2009

Proceedings of the 6th ACM Conference on Computing Frontiers

Self Cite

View full text Add to dashboard Cite

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 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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Cornwall

Howes

Parsonage

et al. 2009

Proceedings of the 6th ACM Conference on Computing Frontiers

Self Cite

View full text Add to dashboard Cite

show abstract

Optimization techniques for efficient HTA programs

et al. 2012

View full text Add to dashboard Cite

Design and Implementation for Nonblocking Execution in GraphBLAS: Tradeoffs and Performance

Mastoras¹,

Anagnostidis

Yzelman³

2022

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

GraphBLAS is a recent standard that allows the expression of graph algorithms in the language of linear algebra and enables automatic code parallelization and optimization. GraphBLAS operations are memory bound and may benefit from data locality optimizations enabled by nonblocking execution. However, nonblocking execution remains under-evaluated. In this article, we present a novel design and implementation that investigates nonblocking execution in GraphBLAS. Lazy evaluation enables runtime optimizations that improve data locality, and dynamic data dependence analysis identifies operations that may reuse data in cache. The nonblocking execution of an arbitrary number of operations results in dynamic parallelism, and the performance of the nonblocking execution depends on two parameters, which are automatically determined, at run-time, based on a proposed analytic model. The evaluation confirms the importance of nonblocking execution for various matrices of three algorithms, by showing up to 4.11 × speedup over blocking execution as a result of better cache utilization. The proposed analytic model makes the nonblocking execution reach up to 5.13 × speedup over the blocking execution. The fully automatic performance is very close to that obtained by using the best manual configuration for both small and large matrices. Finally, the evaluation includes a comparison with other state-of-the-art frameworks for numerical linear algebra programming that employ parallel execution and similar optimizations to those discussed in this work, and the presented nonblocking execution reaches up to 16.1 × speedup over the state-of-the-art.

show abstract

Explicit Dependence Metadata in an Active Visual Effects Library

Cited by 4 publications

References 13 publications

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

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

Optimization techniques for efficient HTA programs

Design and Implementation for Nonblocking Execution in GraphBLAS: Tradeoffs and Performance

Contact Info

Product

Resources

About