A configurable algorithm for parallel image-compositing applications

• Published in: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis pp. 1 - 10
• Main Authors: Peterka, Tom, Goodell, David, Ross, Robert, Shen, Han-Wei, Thakur, Rajeev
• Format: Conference Proceeding
• Language: English
• Published: New York, NY, USA ACM 14.11.2009
• Series: ACM Conferences
• Subjects: Bandwidth; communication; Costs; Government; image compositing; Information systems > Information systems applications; Libraries; Lower bound; Optimization; parallel scientific visualization; Pipelines; Program processors; Rendering (computer graphics); Vectors; communication; parallel scientific visualization; image compositing
• ISBN: 1605587443; 9781605587448
• ISSN: 2167-4329
• DOI: 10.1145/1654059.1654064

Collective communication operations can dominate the cost of large-scale parallel algorithms. Image compositing in parallel scientific visualization is a reduction operation where this is the case. We present a new algorithm called Radix-k that in many cases performs better than existing compositing algorithms. It does so through a set of configurable parameters, the radices, that determine the number of communication partners in each message round. The algorithm embodies and unifies binary swap and direct-send, two of the best-known compositing methods, and enables numerous other configurations through appropriate choices of radices. While the algorithm is not tied to a particular computing architecture or network topology, the selection of radices allows Radix-k to take advantage of new supercomputer interconnect features such as multiporting. We show scalability across image size and system size, including both powers of two and nonpowers-of-two process counts.