<ul><li>Lookup tables (LUTs) are commonly used to store precomputed values for mathematical computations.</li><li>ReducedLUT is a novel method to reduce the size of LUTs by injecting don't cares into the compression process.</li><li>This method introduces more self-similarities in LUTs which can be exploited using known decomposition techniques.</li><li>In a machine learning application, this method achieves up to $1.63	imes$ reduction in LUT utilization with minimal accuracy degradation.</li></ul>

ReducedLUT: Table Decomposition with "Don't Care" Conditions

Discover more