Efficient irregular wavefront propagation algorithms on hybrid CPU–GPU machines

Abstract

We address the problem of efficient execution of a computation pattern, referred to here as the irregular wavefront propagation pattern (IWPP), on hybrid systems with multiple CPUs and GPUs. The IWPP is common in several image processing operations. In the IWPP, data elements in the wavefront propagate waves to their neighboring elements on a grid if a propagation condition is satisfied. Elements receiving the propagated waves become part of the wavefront. This pattern results in irregular data accesses and computations. We develop and evaluate strategies for efficient computation and propagation of wavefronts using a multi-level queue structure. This queue structure improves the utilization of fast memories in a GPU and reduces synchronization overheads. We also develop a tile-based parallelization strategy to support execution on multiple CPUs and GPUs. We evaluate our approaches on a state-of-the-art GPU accelerated machine (equipped with 3 GPUs and 2 multicore CPUs) using the IWPP implementations of two widely used image processing operations: morphological reconstruction and euclidean distance transform. Our results show significant performance improvements on GPUs. The use of multiple CPUs and GPUs cooperatively attains speedups of 50× and 85× with respect to single core CPU executions for morphological reconstruction and euclidean distance transform, respectively.

Cooperative and out‐of‐core execution of the irregular wavefront propagation pattern on hybrid machines with Intel® Xeon Phi™

“…In order to evaluate the performance of the proposed methods, we have compared the implementations to efficient CPU 3 and GPU 1,18 implementations of the IWPP.We have also benchmarked the processors using the STREAM benchmark 19 to compute regular memory access bandwidth. The memory bandwidth with these benchmarks are presented in Table 3.…”

“…1 The multi-core CPU version was executed on Intel E5-processors with 2.6 GHz and employed the 16 computing cores available. The SE10P and 7120P devices are equipped with 61 cores, but the latter has a higher clock rate.…”

“…1 Some core operations in image analysis applications share a core computation structure called Irregular Wavefront Propagation Pattern (IWPP). 1 For instance, segmentation operations that use the IWPP include: Morphological Reconstruction, 3 Fill Holes, 4 H-minima/maxima, 4 Watershed, 5 and Distance Transform. 6 …”

Fine-Grained Synchronizations and Dataflow Programming on GPUs

“…By stepping along the incremental direction of f and processing all elements associated, data dependencies can be respected. So far, all the existing implementations of wavefront applications on GPUs adopt this data-parallel pattern [22,31,32]. Figure 6 illustrates the processing trace of this pattern for the Needleman-Wunsch algorithm.…”

High-throughput Analysis of Large Microscopy Image Datasets on CPU-GPU Cluster Platforms

“…To port these algorithms to the GPU, we have implemented a hierarchical and scalable queue to store elements (pixels) in fast GPU memories along with several optimizations to reduce execution time. We refer the reader to the following manuscripts [8], [9] for implementation details. The queue-based implementation resulted in significant performance improvements over previously published GPU-enabled versions of the MR algorithm [10].…”