3D Non-Uniform Fast Fourier Transform Program Optimization
Source abstract
Abstract
MRI (magnetic resonance imaging) technology aims to map the internal structure image of organisms. It is an important application scenario of Non-Uniform Fast Fourier Transform (NUFFT), which can help doctors quickly locate the lesion site of patients. However, in practical application, it has disadvantages such as large computation and difficulty in parallel. Under the architecture of multi-core shared memory, using block pretreatment, color block scheduling NUFFT convolution interpolation offers a parallel solution, and then using a static linked list solves the problem of large memory requirements after the parallel solution on the basis of multithreading to cycle through more source code versions. Then, manual vectorization, such as processing, using short vector components, further accelerates the process. Through a series of optimizations, the final Random, Radial, and Spiral dataset obtained an acceleration effect of 273.8×, 291.8× and 251.7×, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced MRI Techniques and Applications · Optical Coherence Tomography Applications · Image and Signal Denoising Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
National Supercomputing Center in Zhengzhou, Zhengzhou University, Zhengzhou 450001, China
Cambricon Technologies Corporation Limited, Beijing 100000, China
State Key Laboratory of Mathematical Engineering and Advanced Computing, Information Engineering University, Zhengzhou 450001, China
Funding
Key Technologies and Industrialization for Intelligent Computing in Large-Scale Video Scenarios under Digital Social Governance
References (15)
Show source-provided references
1. An algorithm for machine calculation of complex Fourier series10.1090/S0025-5718-1965-0178586-1 ↗
2. The top 10 algorithms10.1109/MCISE.2000.814652 ↗
3. High-resolution 3-D radar imaging through nonuniform fast Fourier transform (NUFFT)
4. A fast sinc function gridding algorithm for Fourier inversion in computer tomography10.1109/TMI.1985.4307723 ↗
5. Direct reconstruction of non-Cartesian k-space data using a nonuniform fast Fourier transform10.1002/mrm.1120 ↗
6. An Efficient Fourier Method for 3D Radon Inversion in Exact Cone-Beam CT Reconstructionl
7. Fast algorithm for non-uniformly sampled signal spectrum reconstruction
8. Fast Fourier transforms for non-equispaced data II10.1006/acha.1995.1007 ↗
9. Caporale, S., and Marchi, L.D. (2007, January 3–7). A SVD-based algorithm for dense nonuniform fast Fourier Transform. Proceedings of the 15th European Signal Processing Conference, Poznan, Poland.
10. Accelerating the non-equispaced fast Fourier transform on commodity graphics hardware10.1109/TMI.2007.909834 ↗
11. Kalamkar, D.D., Trzasko, J.D., Sridharan, S., Smelyanskiy, M., Kim, D., Manduca, A., Shu, Y., Bernstein, M.A., Kaul, B., and Dubey, P. (2012, January 21–25). High Performance Non-uniform FFT on Modern X86-based Multi-core Systems. Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium, Shanghai, China.10.1109/IPDPS.2012.49 ↗
12. Trajectory optimized NUFFT: Faster non-Cartesian MRI reconstruction through prior knowledge and parallel architectures10.1002/mrm.27497 ↗
13. Mean square optimal NUFFT approximation for efficient non-Cartesian MRI reconstruction10.1016/j.jmr.2014.01.016 ↗
14. Zhang, Y., Pitsianis, N.P., Kandemir, M., and Sun, X. (2009, January 12–16). Exploring parallelization strategies for NUFFT data translation. Proceedings of the ACM International Conference on Embedded Software, Grenoble, France.10.1145/1629335.1629361 ↗
15. Diagnostic utility of 3D MRI sequences in the assessment of central, recess and foraminal stenoses of the spine: A systematic review10.1007/s00256-024-04689-1 ↗