10 Apr
2026
10 Apr
'26
10:23 p.m.
On Apr 10, 2026, at 10:54 AM, Mark Matlock
<mark(a)matlockfamily.com> wrote:
Johnny, Dave,
I did find some old floating point bench mark info in one of my Saturn Calc
spreadsheets (that I can now read once again). The floating point bench mark was a tight
loop in F77 with a REAL*4 multiplication. The Sieve prime number test computed primes unto
8192 with F77 code.
System Sieve Flops Sieve Float Dhrystones
VUPS VUPS
PDP 11/23 2.027900 9693 .11 .05 (microcode FP)
PDP 11/24 11500 .06 (this 11/24 had the clock
potentiometer cranked up as fast as it could go)
PDP 11/44 .568600 61473 .39 .33 (using FPEM)
PDP 11/73 .319948 38837 .69 .21 833 (15 Mhz, microcode FP)
PDP 11/83 .241563 359416 .92 1.92 1153. (15 Mhz, FPP chip)
PDP 11/84 .388500 363774 .57 1.94 (18 Mhz, FPP chip)
M100-04 .218359 382592 1.02 2.04 1250. (20 Mhz, FPP)
VAX 11/780 .222200 187135 1.00 1.00 1500
uVAX II .259100 144829 .86 .77
VAX 8600 .059300 1035673 3.75 5.53
VAX 8700 .044920 885201 4.95 4.73
VAX 6420 .032160 1412804 6.91 7.55 17141
VAX 6610 .007305 9230000 30.42 49.32 66578
VAX 3500 .084370 525590 2.63 2.81 5612
MV3100 10e .057030 766470 3.90 4.10 8834
MV3100 30 .038906 1132743 5.71 6.05 15974
MV3100 80 .022187 1987578 10.01 10.62 22727
VS4000 90A .007289 9270000 30.48 49.54 66578
Alpha 666Mhz .000340 204000000 653.53 1090 2783964 (Alpha 666Mhz, EV67)
Best,
Mark
Wow, that Alpha number is amazing. Funny that the VAX 780 was half the speed of an 11/83.
Did the 780 have an optional separate FPP? I forget. I wonder what an Aridus (VAX 9000)
would produce.
It would be interesting to see numbers for the 11/45, 11/70, and 11/60 with FPP, since
those were supposedly pretty fast at least for the time. One interesting property (great
to give headaches to compiler writers) is that a PDP-11 with FFP is basically a dual
pipeline machine, with an integer and a float pipe. But they are not fully separate; FPP
instructions take some time in the integer pipe for addressing mode handling, then the
actual execution is handed off to the floating operation pipe. I thought a bit about an
instruction scheduler description for GCC, but it made my head hurt. :-)
paul