Communication Optimization for Medical Image Reconstruction Algorithms

Authors:
Torsten Hoefler;Maraike Schellmann;Sergei Gorlatch;Andrew Lumsdaine
Affiliations:
Open Systems Lab, Indiana University, Bloomington, USA IN 47405;Institute of Computer Science, University of Münster, Germany;Institute of Computer Science, University of Münster, Germany;Open Systems Lab, Indiana University, Bloomington, USA IN 47405
Venue:
Proceedings of the 15th European PVM/MPI Users' Group Meeting on Recent Advances in Parallel Virtual Machine and Message Passing Interface
Year:
2008

Citing 3
Cited 4

Send-receive considered harmful: Myths and realities of message passing

ACM Transactions on Programming Languages and Systems (TOPLAS)
Analyzing the Impact of Overlap, Offload, and Independent Progress for Message Passing Interface Applications

International Journal of High Performance Computing Applications
Implementation and performance analysis of non-blocking collective operations for MPI

Proceedings of the 2007 ACM/IEEE conference on Supercomputing

Parallel Medical Image Reconstruction: From Graphics Processors to Grids

PaCT '09 Proceedings of the 10th International Conference on Parallel Computing Technologies
Using OpenMP vs. Threading Building Blocks for Medical Imaging on Multi-cores

Euro-Par '09 Proceedings of the 15th International Euro-Par Conference on Parallel Processing
Towards high performance cell segmentation in multispectral fine needle aspiration cytology of thyroid lesions

Computer Methods and Programs in Biomedicine
Parallel medical image reconstruction: from graphics processing units (GPU) to Grids

The Journal of Supercomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents experiences and results obtained in optimizing the parallel communication performance of a production-quality medical image reconstruction application. The fundamental communication operations in the application's principal algorithm are collective reductions. The overhead of these operations was reduced by transforming the algorithm to overlap its computation and communication. Several different approaches to communication progress were studied, both user-directed and asynchronous. Experimental results comparing the new approach to the previous implementation show overall application performance improvements of up to 8%, when run on 32 nodes.