Massively multithreaded maxflow for image segmentation on the Cray XMT‐2

Abstract

SUMMARY Image segmentation is a very important step in the computerized analysis of digital images. The maxflow mincut approach has been successfully used to obtain minimum energy segmentations of images in many fields. Classical algorithms for maxflow in networks do not directly lend themselves to efficient parallel implementations on contemporary parallel processors. We present the results of an implementation of Goldberg-Tarjan preflow-push algorithm on the Cray XMT-2 massively multithreaded supercomputer. This machine has hardware support for 128 threads in each physical processor, a uniformly accessible shared memory of up to 4 TB and hardware synchronization for each 64 bit word. It is thus well-suited to the parallelization of graph theoretic algorithms, such as preflow-push. We describe the implementation of the preflow-push code on the XMT-2 and present the results of timing experiments on a series of synthetically generated as well as real images. Our results indicate very good performance on large images and pave the way for practical applications of this machine architecture for image analysis in a production setting. The largest images we have run are 320002 pixels in size, which are well beyond the largest previously reported in the literature.

A computationally efficient algorithm for the 2D covariance method

“…(24) Fig. 6(a) shows the ratio between the number of operations required by the straightforward approach as given in (2) and those required by the new approach for both multiplications and additions. This ratio is also indicative of the possible sequential speedup.…”

“…The Cray XMT2 was used for image segmentation based on a maxflow mincut approach on 32k × 32k images [2]. CUDA is used for CT reconstruction [18].…”