| Summary: | 碩士 === 國立彰化師範大學 === 電子工程學系 === 98 === Content-addressable memory（CAM）is a memory structure that supports parallel data search. The applications of CAM include the IP address search in a network router, cache memory, data compression, and image processing. The parallel search operation of CAM consumes a significant amount of energy due to the charging and discharging of the search lines and match lines with large capacitance.
This thesis proposed two new CAM match-line sensing circuits, the double positive-feedback match-line sense amplifier (DPF-MLSA) and the pulse current based match-line sense amplifier (PCB-MLSA).
DPF-MLSA uses the pulse current to reduce the power consumption of match lines in a ternary content-addressable memory (TCAM) and employs the double positive-feedback network to boost the search speed of TCAM.
PCB-MLSA uses the pulse current to charge the match lines and then detects the voltage development on match lines to determine whether the match line is matched. In contrast to conventional MLSAs, which adjust the charging current to the match lines based on matching result, PCB-MLSA will not provide additional current to the match lines regardless of the matching result.
We have employed Hspice to evaluate various match-line sensing circuits using the Berkeley Predictive Technology Model (BPTM) for 65nm transistor model with supply voltage of 1.1V and temperature of 25 . The simulation results show that the proposed DPFMLSA and PCBMLSA, respectively, can achieve a search time of 0.49699 ns and 0.41797 ns and a energy consumption of 0.201474 and 0.194466 fJ/bit/search. The measured results show that the proposed DPFMLSA can reduce the energy consumption by 85.481%, 21.195%, and 10.545% compared to the conventional precharge MLSA, the match sensing technique using match-line stability, and the positive-feedback MLSA, respectively. The proposed PCBMLSA can reduce the energy consumption by 85.987%, 23.936%, and 13.657% compared to the conventional precharge MLSA, the match sensing technique using match-line stability, and the positive-feedback MLSA, respectively.
|
|---|
