TY - GEN
T1 - Linear Bregman algorithm implemented in parallel GPU
AU - Li, Pengyan
AU - Ke, Jue
AU - Sui, Dong
AU - Wei, Ping
N1 - Publisher Copyright:
© 2015 SPIE.
PY - 2015
Y1 - 2015
N2 - At present, most compressed sensing (CS) algorithms have poor converging speed, thus are difficult to run on PC. To deal with this issue, we use a parallel GPU, to implement a broadly used compressed sensing algorithm, the Linear Bregman algorithm. Linear iterative Bregman algorithm is a reconstruction algorithm proposed by Osher and Cai. Compared with other CS reconstruction algorithms, the linear Bregman algorithm only involves the vector and matrix multiplication and thresholding operation, and is simpler and more efficient for programming. We use C as a development language and adopt CUDA (Compute Unified Device Architecture) as parallel computing architectures. In this paper, we compared the parallel Bregman algorithm with traditional CPU realized Bregaman algorithm. In addition, we also compared the parallel Bregman algorithm with other CS reconstruction algorithms, such as OMP and TwIST algorithms. Compared with these two algorithms, the result of this paper shows that, the parallel Bregman algorithm needs shorter time, and thus is more convenient for real-time object reconstruction, which is important to people™s fast growing demand to information technology.
AB - At present, most compressed sensing (CS) algorithms have poor converging speed, thus are difficult to run on PC. To deal with this issue, we use a parallel GPU, to implement a broadly used compressed sensing algorithm, the Linear Bregman algorithm. Linear iterative Bregman algorithm is a reconstruction algorithm proposed by Osher and Cai. Compared with other CS reconstruction algorithms, the linear Bregman algorithm only involves the vector and matrix multiplication and thresholding operation, and is simpler and more efficient for programming. We use C as a development language and adopt CUDA (Compute Unified Device Architecture) as parallel computing architectures. In this paper, we compared the parallel Bregman algorithm with traditional CPU realized Bregaman algorithm. In addition, we also compared the parallel Bregman algorithm with other CS reconstruction algorithms, such as OMP and TwIST algorithms. Compared with these two algorithms, the result of this paper shows that, the parallel Bregman algorithm needs shorter time, and thus is more convenient for real-time object reconstruction, which is important to people™s fast growing demand to information technology.
KW - CPU
KW - GPU
KW - Linear Bregman algorithm
KW - compressed sensing
KW - object reconstruction
KW - parallel computing
UR - http://www.scopus.com/inward/record.url?scp=84943529815&partnerID=8YFLogxK
U2 - 10.1117/12.2193282
DO - 10.1117/12.2193282
M3 - Conference contribution
AN - SCOPUS:84943529815
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - 2015 International Conference on Optical Instruments and Technology
A2 - Shi, Guangming
A2 - Huang, Bormin
A2 - Li, Xuelong
PB - SPIE
T2 - 2015 International Conference on Optical Instruments and Technology: Optoelectronic Imaging and Processing Technology, OIT 2015
Y2 - 17 May 2015 through 19 May 2015
ER -