Consider the following machines, and compare their
performanceusing the spec cpuint 2000 data from fig.3.26 on page
228.
m1: the multicycle datapath of chap.5 with 1 ghzclock.
m2: a machine like the multicycle datapath of chap.5, except
thatthe register updates are done in the same clock cycle as the
amemory read or alu operation. thus in fig. 5.38 on page 339,
states6 and 7 and states 3 and 4 are combined. this machine has an
3.2ghz clock, since the register update increases the length of
thecritical path.
m3: a machine like m2 except that the effective
addresscalculations are done in the same clock cycle as memory
access. thus states 2,3, and 4 are combined as can 2 and 5 as well
as 6 and7. this machine has a 2.8 ghz clock because of the long
cyclecreated by combining address calculation and memory
access.
find out which of the machines is fastest. are there
instructionmixes that would make another machine faster, and if so,
what arethey?