作者: Rajeevan Amirtharajah , Thucydides Xanthopoulos , Anantha Chandrakasan
关键词:
摘要: A recent trend in low power design has been the employment of reduced precision processing methods for decreasing arithmetic activity and average dissipation. Such designs can trade off as system requirements change. This work explores potential Distributed Arithmetic (DA) computation structures precision-on-demand computation. We present two proof-of-concept VLSI implementations whose dissipation changes according to performed.