The authors describe a VLSI processor for pattern recognition based on content addressable memory (CAM) architecture, optimized for on-line track finding in high-energy physics experiments. A large CAM bank stores all trajectories of interest and extracts the ones compatible with a given event. This task is naturally parallelized by a CAM architecture able to output identified trajectories, searching for matches on 96-bit wide patterns, in just a few 40-MHz clock cycles. We have developed this device (called the AMchip03 processor) for the silicon vertex trigger (SVT) upgrade at the Collider Detector experiment at Fermilab (CDF) using a standard-cell VLSI design methodology. This approach provides excellent pattern density; while sparing many of the complexities and risks associated to a full-custom design. The cost/performance ratio is better by well more than one order of magnitude than an FPGA-based design. This processor has a flexible and easily configurable structure that makes it suitable for applications in other experimental environments. They look forward to sharing this technology.
A VLSI processor for fast track finding based on content addressable memories
DELL'ORSO, MAURO;
2006-01-01
Abstract
The authors describe a VLSI processor for pattern recognition based on content addressable memory (CAM) architecture, optimized for on-line track finding in high-energy physics experiments. A large CAM bank stores all trajectories of interest and extracts the ones compatible with a given event. This task is naturally parallelized by a CAM architecture able to output identified trajectories, searching for matches on 96-bit wide patterns, in just a few 40-MHz clock cycles. We have developed this device (called the AMchip03 processor) for the silicon vertex trigger (SVT) upgrade at the Collider Detector experiment at Fermilab (CDF) using a standard-cell VLSI design methodology. This approach provides excellent pattern density; while sparing many of the complexities and risks associated to a full-custom design. The cost/performance ratio is better by well more than one order of magnitude than an FPGA-based design. This processor has a flexible and easily configurable structure that makes it suitable for applications in other experimental environments. They look forward to sharing this technology.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
