Auto-vectorization for Image Processing DSLs
Reiche O, Kobylko C, Hannig F, Teich J (2017)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2017
Publisher: ACM
Pages Range: 21 - 30
Conference Proceedings Title: Proceedings of the 18th International Conference on Languages, Compilers, Tools, and Theory for Embedded Systems (LCTES)
Event location: Barcelona
Abstract
The parallelization of programs and distributing their workloads to multiple threads can be a challenging task. In addition to multi-threading, harnessing vector units in CPUs proves highly desirable. However, employing vector units to speed up programs can be quite tedious. Either a program developer solely relies on the auto-vectorization capabilities of the compiler or he manually applies vector intrinsics, which is extremely error-prone, difficult to maintain, and not portable at all.
Based on whole-function vectorization, a method to replace control flow with data flow, we propose auto-vectorization techniques for image processing DSLs in the context of source-to-source compilation. The approach does not require the input to be available in SSA form. Moreover, we formulate constraints under which the vectorization analysis and code transformations may be greatly simplified in the context of image processing DSLs. As part of our methodology, we present control flow to data flow transformation as a source-to-source translation. Moreover, we propose a method to efficiently analyze algorithms with mixed bit-width data types to determine the optimal SIMD width, independently of the target instruction set. The techniques are integrated into an open source DSL framework. Subsequently, the
vectorization capabilities are compared to a variety of existing state-of-the-art C/C++ compilers. A geometric mean speedup of up to 3.14 is observed for benchmarks taken from ISPC and image processing, compared to non-vectorized executions.
Authors with CRIS profile
Oliver Reiche
Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design)
Frank Hannig
Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design)
Jürgen Teich
Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design)
Additional Organisation(s)
Related research project(s)
GRK 1773: Heterogeneous Image Systems, Project B3 (GRK 1773)
RTG 1773: Heterogeneous Image Systems
Oct. 1, 2012 - March 31, 2017
A Domain-Specific Language and GPU Target Code Generator for Image Processing Applications (HIPAcc)
Jan. 1, 2009 - Jan. 1, 2012
How to cite
APA:
Reiche, O., Kobylko, C., Hannig, F., & Teich, J. (2017). Auto-vectorization for Image Processing DSLs. In Proceedings of the 18th International Conference on Languages, Compilers, Tools, and Theory for Embedded Systems (LCTES) (pp. 21 - 30). Barcelona, ES: ACM.
MLA:
Reiche, Oliver, et al. "Auto-vectorization for Image Processing DSLs." Proceedings of the 18th International Conference on Languages, Compilers, Tools, and Theory for Embedded Systems (LCTES), Barcelona ACM, 2017. 21 - 30.
BibTeX: Download