Key points are not available for this paper at this time.
A fully integrated phase-locked loop (PLL) is used to time-align the hi-Z/low-Z transitions of a CMOS CPU and its floating-point coprocessor (FPC), resulting in minimum timing difference (skew) between the two devices at their shared data bus, and decreasing the bus cycle time. The PLL circuit abandons the traditional voltage-controlled oscillator function, instead using a CMOS voltage-controlled delay line to improve noise immunity, ease loop stabilization, and permit dynamically adjustable clock periods. With the PLL enable, measured timing skew between the CPU and FPC is below 1 ns.>
Johnson et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: