Here are the numbers for the slowest sparc I have in working condition
(a SparcStation LX), running -current.
[/tmp] martin@somnambulist > ./Falcon-impl-20211101/speed
I finally made the falcon code build on the 1.4T/sparc
SPARCstation-20s. One of them
cpu0 at mainbus0: RT620/625 @ 125 MHz, on-chip FPU
cpu0: 256K byte write-back, 64 bytes/line, sw flush: cache enabled
produced these numbers
time threshold = 2.0000 s
kg = keygen, ek = expand private key, sd = sign (without expanded key)
st = sign (with expanded key), vv = verify
sdc, stc, vvc: like sd, st and vv, but with constant-time hash-to-point
keygen in milliseconds, other values in microseconds
degree kg(ms) ek(us) sd(us) sdc(us) st(us) stc(us) vv(us) vvc(us)
256: 3700.00 9043.82 30821.92 32537.31 19059.83 20818.18 4422.31 5783.78
512: 8680.00 19636.36 63939.39 65151.52 38793.10 41272.73 8803.42 11230.77
1024: 27990.00 41568.63 130000.00 135625.00 78064.52 80689.66 19272.73 22886.60
for what that may be worth. I find the similarities and differences
between these and martin@'s LX numbers interesting.
This was my principal screen-&-keyboard machine, so it was not
otherwise idle. Based on a quick sample with top, I would estimate the
speed tester was getting 65-75 percent of the CPU.
/~\ The ASCII Mouse
\ / Ribbon Campaign
X Against HTML mouse%rodents-montreal.org@localhost
/ \ Email! 7D C8 61 52 5D E7 2D 39 4E F1 31 3E E8 B3 27 4B