Title
Schedule synthesis for halide pipelines through reuse analysis
Author
Sioutas, S.
Stuijk, S.
Waeijen, L.
Basten, T.
Corporaal, H.
Somers, L.
Publication year
2019
Abstract
Efficient code generation for image processing applications continues to pose a challenge in a domain where high performance is often necessary to meet real-time constraints. The inherently complex structure found in most image-processing pipelines, the plethora of transformations that can be applied to optimize the performance of an implementation, as well as the interaction of these optimizations with locality, redundant computation and parallelism, can be indentified as the key reasons behind this issue. Recent domain-specific languages (DSL) such as the Halide DSL and compiler attempt to encourage high-level design-space exploration to facilitate the optimization process. We propose a novel optimization strategy that aims to maximize producer-consumer locality by exploiting reuse in image-processing pipelines. We implement our analysis as a tool that can be used alongside the Halide DSL to automatically generate schedules for pipelines implemented in Halide and test it on a variety of benchmarks. Experimental results on three different multi-core architectures show an average performance improvement of 40% over the Halide Auto-Scheduler and 75% over a state-of-the art approach that targets the PolyMage DSL.
Subject
Infostructures
Information Society
To reference this document use:
http://resolver.tudelft.nl/uuid:2d80111e-732c-4461-957b-d2b0a247ebc8
DOI
https://doi.org/10.1145/3310248/
TNO identifier
867360
Publisher
Association for Computing Machinery
ISSN
1544-3566
Source
ACM Transactions on Architecture and Code Optimization, 16 (16)
Document type
article