This paper describes an investigation of potential advantages and pitfalls
of applying an asynchronous design methodology to an advanced microprocesso
r architecture. A prototype complex instruction set length decoding and ste
ering unit was implemented using self-timed circuits. [The Revolving Asynch
ronous Pentium(R) Processor Instruction Decoder (RAPPID) design implemented
the complete Pentium II(R) 32-bit MMX instruction set.] The prototype chip
was fabricated on a 0.25-mu CMOS process and tested successfully. Results
show significant advantages-in particular, performance of 2.5-4.5 instructi
ons per nanosecond-with manageable risks using this design technology, The
prototype achieves three times the throughput and half the latency, dissipa
ting only half the power and requiring about the same area as the fastest c
ommercial 400-MHz clocked circuit fabricated on the same process.