Brad Parker wrote:
I know it's crazy, but I finally got my FPGA based
PDP-8/I to boot TSS/8.
http://colo3.heeltoe.com/download/pdp8/README.html
It's been sort of working for a while but had some odd bugs. I did a
lot of simulation and comparison
with simh. I think it's pretty close to correct now. There are still
a few bugs to clean up but it seems to run
everything correctly and save files to the disk
Congratulations are in order! This is certainly a different approach
from the software implementation
approach taken
by SIMH. Many times, using two different methods will
highlight problems that each
one has since the results should be identical. By this time, SIMH is
likely to be getting almost everything
right, but there always seems to be isolated cases.
As most of the classiccmp list knows, my addiction is the software on
the PDP-11, mostly
running RT-11, but of late making the same program also run under
RSTS/E, TSX-Plus and
RTEM. From that point of view, can you possibly answer two questions?
(a) Without being very accurate, and based on your experience with the
PDP-8, how
long do you think that it would take you to implement a PDP-11? Just a
rough estimate
in months or years!
(b) About how fast might the FPGA solution be compared to something
like a PDP-11/93?
Again, just a rough estimate like 10 or 20 times as fast.
One advantage of SIMH and Ersatz-11 is that when a faster X86 CPU
arrives, the emulation
is automatically faster. Plus there is no additional FPGA hardware
required for each additional
user, just a standard PC which are usually generally available for other
purposes such as e-mail.
Note, however, that terminal emulation such as a VT100 may not be
automatic, especially under
Ersatz-11 for 132 character mode text lines in full screen mode. I had
to test a number of
video cards before I found one that managed to support 132 character
text lines using the full
screen mode.
As for how fast the emulation can be, my preliminary tests on a 2.66 GHz
Intel 8200 core 2 duo
CPU is about 100 times the speed of a PDP-11/93 for just the CPU speed
and about 200 times
the hard disk speeds of most Qbus EDSI or SCSI hard drives using SATA II
300 GB drives.
And talk about crazy, how much am I addicted to RT-11 when a Y3K bug fix
is actively
being researched as to what the technical problems will be? Or fixing
bugs that no one
else even knows about, let alone cares about?
Any idea why you did an FPGA implementation of the PDP-8?
Jerome Fine