With technology scaling, process constraints and imperfections result in significant variation of post-Si performance and stability of SRAM from designed/target pre-Si parameters. Modification/ re-optimization of SRAM cell and/or tuning of process parameters to meet target performance and stability are limited by area constraints and involve several technology ramp-up cycles. For reducing access failures, if process is not fine tuned, memory access clock cycle period may need to be increased thereby compromising performance. We propose a design methodology to meet the target performance and reduce access failures by tuning the SRAM array peripherals instead of tuning the SRAM cell and process parameters. Proposed design methodology is supported by numerical framework and validated by simulation results on 45nm PDSOI technology. We further show that our methodology does not impact the READ stability of a cell.
|Title of host publication||IEEE Workshop on Machine Learning for Signal Processing|
|State||Published - 2008|