基于CUDA的蛋白质点检测快速实现方法  

Fast Implementation Method of Protein Spots Detection Based on CUDA

作　　者：熊邦书[1] 叶毅嘉 欧巧凤[1] 张郝东 

机构地区：[1]南昌航空大学图像处理与模式识别江西重点实验室,南昌330063

出　　处：《生物医学工程学杂志》2016年第1期83-88,共6页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(61163047);江西省自然科学基金资助项目(20114BAB201036);江西省教育厅科技资助项目(GJJ14532);江西省研究生创新专项资金项目资助(YC2013-S219)

摘　　要：为提高蛋白质点检测的效率,利用图像处理单元(GPU)在并行计算和内存管理方面的优势,提出一种基于CUDA的蛋白质点检测快速实现方法。首先,对蛋白质点检测算法中最耗时的图像预处理、蛋白质点粗检测和重叠蛋白质点分割三部分进行并行化设计;然后,根据CUDA单指令多线程的执行方式对数据空间进行二维分块,利用共享寄存器和二维纹理内存的内存管理措施实现了蛋白质点快速检测。通过本文方法与中央处理器(CPU)串行方法进行真实凝胶图像的检测对比实验,结果表明,本文方法的执行效率明显高于CPU串行方法,并且随着图像大小的增加,效率也随之提高,对于2 048×2 048大小的图像数据,CPU串行实现时间为52 641ms,GPU则为4 384ms,效率提高了11倍。In order to improve the efficiency of protein spots detection,a fast detection method based on CUDA was proposed.Firstly,the parallel algorithms of the three most time-consuming parts in the protein spots detection algorithm：image preprocessing,coarse protein point detection and overlapping point segmentation were studied.Then,according to single instruction multiple threads executive model of CUDA to adopted data space strategy of separating two-dimensional（2D）images into blocks,various optimizing measures such as shared memory and 2Dtexture memory are adopted in this study.The results show that the operative efficiency of this method is obviously improved compared to CPU calculation.As the image size increased,this method makes more improvement in efficiency,such as for the image with the size of 2 048×2 048,the method of CPU needs 5 2641 ms,but the GPU needs only 4 384 ms.

关 键 词：蛋白质点检测 CUDA 并行处理 内存管理 

分 类 号：Q51[生物学—生物化学]