Title :
Massively parallel processor array for mid-/back-end ultrasound signal processing
Author :
Truong, Dean N. ; Baas, Bevan M.
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of California, Davis, CA, USA
Abstract :
Ultrasound remains a popular imaging modality due to its mobility and cost-effectiveness. As general purpose computing and DSPs are entering an era of multi-core architectures, the potential for parallel performance gains are significant when used properly. This work explores the possibility of using a massively parallel processor array to meet realtime throughputs for mid-/back-end ultrasound processing. A many-core array of simple DSP cores, shared memories, and an FFT processor is shown to dissipate 87.79 mW for B-mode, 33.20 mW for color flow, and 29.24 mW for spectral doppler, while achieving a frame rate of 37.6 fps for B-mode and 12.5 fps for color flow.
Keywords :
digital signal processing chips; fast Fourier transforms; general purpose computers; parallel processing; shared memory systems; ultrasonic imaging; DSP; FFT processor; color flow; general purpose computing; many core array; massively parallel processor array; mid-back-end ultrasound signal processing; multicore architecture; parallel performance; shared memory; spectral doppler; Arrays; Demodulation; Digital signal processing; Image color analysis; Imaging; Ultrasonic imaging;
Conference_Titel :
Biomedical Circuits and Systems Conference (BioCAS), 2010 IEEE
Conference_Location :
Paphos
Print_ISBN :
978-1-4244-7269-7
Electronic_ISBN :
978-1-4244-7268-0
DOI :
10.1109/BIOCAS.2010.5709624
