DocumentCode :
602930
Title :
A 64-core platform for biomedical signal processing
Author :
Bisasky, J. ; Homayoun, Houman ; Yazdani, F. ; Mohsenin, Tinoosh
Author_Institution :
CSEE Dept., Univ. of Maryland Baltimore County, Baltimore, MD, USA
fYear :
2013
fDate :
4-6 March 2013
Firstpage :
368
Lastpage :
372
Abstract :
This paper presents a programmable many-core platform containing 64 cores routed in a hierarchical network for biomedical signal processing applications. Individual core processors are based on a RISC architecture with DSP enhancement blocks. Given the number of conditional program loops in DSP applications such as FFT, additional hardware blocks are added that operate in parallel to each core processor. The two blocks calculate the FFT input addresses and determine if a conditional loop is necessary. Performing these operations in parallel to the main processor greatly reduces the time to completion for a DSP application. Each processor is implemented in 65 nm CMOS using standard cell libraries. The 64-core platform occupies 19.51 mm2 and runs at 1.18 GHz at 1 V. For demonstration, Electroencephalogram (EEG) seizure detection and analysis and ultrasound spectral doppler are mapped onto the cores. The seizure detection and analysis algorithm utilizes 60 processors and takes 890 ns to execute. Spectral doppler utilizes 29 processors and takes 715 ns to run.
Keywords :
CMOS integrated circuits; Doppler effect; biomedical electronics; biomedical ultrasonics; digital signal processing chips; diseases; electroencephalography; fast Fourier transforms; medical signal processing; multiprocessing systems; reduced instruction set computing; spectral analysis; 64-core platform; CMOS; DSP application; DSP enhancement block; EEG seizure detection; FFT; RISC architecture; biomedical signal processing application; conditional program loop; core processor; electroencephalogram seizure detection; frequency 1.18 GHz; hierarchical network; programmable many-core platform; seizure analysis algorithm; size 65 nm; standard cell libraries; time 890 ns; ultrasound spectral Doppler; voltage 1 V; CMOS integrated circuits; Clocks; Doppler effect; Market research; Random access memory; Ultrasonic imaging; 65 nm CMOS; DSP; biomedical signal processing; many-core; seizure detection; ultrasound;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Quality Electronic Design (ISQED), 2013 14th International Symposium on
Conference_Location :
Santa Clara, CA
ISSN :
1948-3287
Print_ISBN :
978-1-4673-4951-2
Type :
conf
DOI :
10.1109/ISQED.2013.6523637
Filename :
6523637
Link To Document :
بازگشت