Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines
Image processing pipelines combine the challenges of stencil computations and stream programs. They are composed of large graphs of different stencil stages, as well as complex reductions, and stages with global or data-dependent access patterns. Because of their complex structure, the performance d...
Main Authors: | Barnes, Connelly, Adams, Andrew, Paris, Sylvain, Ragan-Kelley, Jonathan Millar, Durand, Fredo, Amarasinghe, Saman P. |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | en_US |
Published: |
Association for Computing Machinery (ACM)
2014
|
Online Access: | http://hdl.handle.net/1721.1/85943 https://orcid.org/0000-0001-9919-069X https://orcid.org/0000-0002-7231-7643 |
Similar Items
-
Decoupling algorithms from schedules for easy optimization of image processing pipelines
by: Adams, Andrew, et al.
Published: (2014) -
Compiling High Performance Recursive Filters
by: Chaurasia, Gaurav, et al.
Published: (2021) -
Decoupled Sampling for Graphics Pipelines
by: Ragan-Kelley, Jonathan Millar, et al.
Published: (2012) -
Decoupled Sampling for Real-Time Graphics Pipelines
by: Ragan-Kelley, Jonathan, et al.
Published: (2010) -
A Verified Compiler for a Functional Tensor Language
by: Liu, Amanda, et al.
Published: (2024)