For those who want throughput in known units (rather than the weird ones
I used in the previous message, for comparison purposes only) ..
Assume it takes x nsec to get on and off chip (either pure DES, EDE2 or XOR),
y nsec to do the single DES, z nsec to do EDE2 and w nsec to do XOR and v nsec
to do DES-CBC on-chip.
Scheme Total Latency Throughput
EDE#-CBC 2x+z+w 8/(2x+z+w) GB/sec
(DES**3)-CBC 4x+3y+w 8/(4x+3y+w) GB/sec
(DES-CBC)**3 3x+3v 8/(x+v) GB/sec
I would also assume that to a first approximation:
z = 3y
v = y+w
w << y
- Carl