DMCA
Single-particle 3D reconstruction from cryo-electron microscopy images on GPU (2009)
| Venue: | in: Proceedings of the International conference on Supercomputing ICS |
| Citations: | 3 - 3 self |
BibTeX
@INPROCEEDINGS{Tan09single-particle3d,
author = {Guangming Tan and Ziyu Guo and Mingyu Chen and Dan Meng},
title = {Single-particle 3D reconstruction from cryo-electron microscopy images on GPU},
booktitle = {in: Proceedings of the International conference on Supercomputing ICS},
year = {2009},
pages = {380--389}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Single-particle 3D reconstruction from cryo-electron microscopy (cryo-EM) images is a kernel application of biological molecules analysis, as the computational requirement of which is now beyond PetaFlop for a high-resolution 3D structure. In this paper, we quantitatively analyze the workload, com-putational intensity and memory performance of the ap-plication, parallelize it on an emerging multicore architec-ture GPU-CUDA. Further we apply a percolation technique to decouple computation with memory operations and or-chestrate thread-data mapping to reduce the overhead off-chip memory operations. Finally we tested our optimiza-tion strategy on a popular open-source package EMAN to GPU-CUDA, which achieves a relative speedup of about 10X to the original CPU-only EMAN. The experimental results also show that the proposed percolation program-ming greatly improves utilization of memory bandwidth and floating-point units.
Keyphrases
cryo-electron microscopy image computational requirement floating-point unit overhead off-chip memory operation cryo-electron microscopy optimiza-tion strategy memory operation popular open-source package eman relative speedup percolation technique com-putational intensity biological molecule analysis experimental result memory performance architec-ture gpu-cuda original cpu-only eman or-chestrate thread-data memory bandwidth kernel application
