A Domain-Specific Language and GPU Target Code Generator for Image Processing Applications

Internally funded project


Project Details

Project leader:
PD Dr.-Ing. Frank Hannig

Project members:
Richard Membarth
Oliver Reiche
Mehmet Akif Özkan

Contributing FAU Organisations:
Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design)

Acronym: HIPAcc
Start date: 01/01/2009


Abstract (technical / expert description):


HIPAcc allows to design image processing kernels and algorithms in a domain-specific language (DSL). From this high-level description, low-level target code for GPU accelerators is generated using source-to-source translation. As back ends, the framework supports CUDA, OpenCL, and Renderscript. The framework runs on GNU/Linux and Mac OS X and is licensed under the Simplified BSD License.



Publications

Fickenscher, J., Hannig, F., & Teich, J. (2019). DSL-based Acceleration of Automotive Environment Perception and Mapping Algorithms for embedded CPUs, GPUs, and FPGAs. In Martin Schoeberl, Christian Hochberger, Sascha Uhrig, Jürgen Brehm, Thilo Pionteck (Eds.), Architecture of Computing Systems -- ARCS 2019 (pp. 71 - 86). Copenhagen, DK: Cham: Springer International Publishing.
Qiao, B., Reiche, O., Hannig, F., & Teich, J. (2018). Automatic Kernel Fusion for Image Processing DSLs. In Proceedings of the 21th International Workshop on Software and Compilers for Embedded Systems (pp. 76-85). Sankt Goar, DE.
Reiche, O., Özkan, M.A., Hannig, F., Teich, J., & Schmid, M. (2018). Loop Parallelization Techniques for FPGA Accelerator Synthesis. Journal of Signal Processing Systems, 90(1), 3-27. https://dx.doi.org/10.1007/s11265-017-1229-7
Özkan, M.A., Reiche, O., Hannig, F., & Teich, J. (2017). A Highly Efficient and Comprehensive Image Processing Library for C++-based High-Level Synthesis. In Proceedings of the Fourth International Workshop on FPGAs for Software Programmers (FSP). Ghent, BE: VDE.
Reiche, O., Kobylko, C., Hannig, F., & Teich, J. (2017). Auto-vectorization for Image Processing DSLs. In ACM (Eds.), Proceedings of the 18th International Conference on Languages, Compilers, Tools, and Theory for Embedded Systems (LCTES) (pp. 21 - 30). Barcelona, ES.
Reiche, O., Özkan, M.A., Membarth, R., Teich, J., & Hannig, F. (2017). Generating FPGA-based Image Processing Accelerators with Hipacc. In IEEE (Eds.), Proceedings of the International Conference On Computer Aided Design (pp. 1026-1033). Irvine, US: IEEE.

Last updated on 2018-06-11 at 17:45