Implementing Fast MRI Gridding on GPUs via CUDA

  title={Implementing Fast MRI Gridding on GPUs via CUDA},
  author={Anthony E. Gregerson},
Modern graphics processing units (GPUs) have made high-performance SIMD designs available to consumers at commodity prices. This has made them an attractive platform for parallel applications, however developing efficient general-purpose code for graphics-optimized architectures has proven challenging. To explore the challenges and opportunities of exploiting general-purpose GPU processing, we implemented the non-equispaced Fast-Fourier Transform algorithm, commonly known as ‘gridding’, on a… CONTINUE READING


Publications citing this paper.
Showing 1-10 of 10 extracted citations

Fast electrostatic halftoning

Journal of Real-Time Image Processing • 2011
View 4 Excerpts
Highly Influenced

Non-Equispaced FFT Computation with CUDA and GPU

2016 International Conference on Virtual Reality and Visualization (ICVRV) • 2016

Accelerating the Nonuniform Fast Fourier Transform Using FPGAs

2010 18th IEEE Annual International Symposium on Field-Programmable Custom Computing Machines • 2010
View 1 Excerpt


Publications referenced by this paper.
Showing 1-4 of 4 references

Fast Gridding on Commodity Graphics Hardware

T. S. Sorensen, T. Schaeffter, K. O. Noe, M. Schacht- Hansen
Proceedings of Workshop on Non- Cartesian MRI, ISMRM: Arizona, 2007. • 2007

Similar Papers

Loading similar papers…