DocumentCode :
2954773
Title :
An integrated 20-bit 33/5M events/s AER sensor interface with 10ns time-stamping and hardware-accelerated event pre-processing
Author :
Hofstatter, Michael ; Schön, Peter ; Posch, Christoph
Author_Institution :
AIT - Austrian Inst. of Technol., Vienna, Austria
fYear :
2009
fDate :
26-28 Nov. 2009
Firstpage :
257
Lastpage :
260
Abstract :
This paper presents a custom data bridge that interfaces the continuous-time world of asynchronous address-events (AER) to the realm of conventional digital data processing. The main focus in the design of the interface was on precisely maintaining the inherent timing information of AER sensor data while providing robust peak-rate handling, DMA functionality and a novel event-rate dependent system control mechanism. The sensor interface can be integrated with standard CMOS logic in an AER processing system-on-chip and implements hardware-accelerated event pre-processing including pre-FIFO high-resolution time-stamping, address masking for ROI and event-rate dependent IRQ generation without loading a downstream processing device. The sensor interface has been implemented in a 0.18 ¿m CMOS process and achieves peak AER event rates of 33M events/sec and sustained AER event rates of 5.125 M events/sec at 10 ns time-stamp resolution. We discuss design considerations and implementation details and show measurement results from the fabricated chip.
Keywords :
CMOS logic circuits; VLSI; biomedical engineering; neural chips; AER sensor interface; CMOS logic; DMA functionality; address masking; asynchronous address events; digital data processing; event preprocessing; hardware acceleration; storage capacity 20 bit; time stamping; Bridges; CMOS logic circuits; CMOS process; Control systems; Data processing; Logic devices; Robust control; Sensor systems; System-on-a-chip; Timing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Circuits and Systems Conference, 2009. BioCAS 2009. IEEE
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-4917-0
Electronic_ISBN :
978-1-4244-4918-7
Type :
conf
DOI :
10.1109/BIOCAS.2009.5372034
Filename :
5372034
Link To Document :
بازگشت