Cadence Design Systems Inc. has enhanced its Xcelium Logic Simulator with machine learning technology that when combined with core computational software enables the software to perform five times faster on randomized regressions.
The machine learning technology directly interfaces to the simulation kernel, learning iteratively over an entire simulation regression. The software analyzes patterns hidden in the verification environment and guides the Xcelium randomization kernel on subsequent regression runs for matching coverage with reduced simulation cycles.
The simulation technology supports both single-core and multi-core simulation, incremental and parallel build, and save/restart with dynamic test reload. The EDA software has been deployed by semiconductor companies in the hyperscale, automotive and consumer electronics segments including Kioxia Corp., which said the Xcelium software has seen a shorter turnaround time in fully random regression runs to reach 99% function coverage of the original. The company also plans to use the technology in production designs to shorten the time to market of devices.