PDP-11 = Pentium Killer?

From: Allison J Parent <allisonp_at_world.std.com>
Date: Wed Apr 22 19:01:36 1998

<But, since Alphas must share SOMETHING in common with the PDP-11,
<wouldn't it be possible to write a normal program for the Alpha,
<running under NT or Linux, that would give PDP emulation at P-II-like

Not even close. Alpha isn't even like vax. PDP-11 and VAX were lighly
CISC machines where the alpha is vary RISC like. I'm sure PAL code
in the alpha could emulate PDP11 instructions and it would be very fast
but it would still be 16bit and to munge a large array the system would
have to map it into the 4mb max using MMU emulation.

<Now, making a VAX that would do that is a bit more interesting, though
<probably already done. VAX is much more useful these days than PDP-11.

Emulating PDP-11 on a 11/780 vax was a compatability bit and ran it
directly. For later vaxen RTEM ran PDP-11 programs on vax and generally
faster than the PDP11 (assuming the vax was faster itself).

<More on this subject: I have long thought that some computers that
<are now mostly PD, like the C-64, should be rebuilt in kit form and
<sold to kids for $20 each. Now THAT would be nice. Oh, and make them
<make their own kernel, and hold a contest for the best one. The

Get real, few if any are PD. The design is copyrighted or at least
the vendor specific portions(PROMS, PALS, custom LSI) are.

<>fits in the primary cache of an Alpha. If possible, you'd be using the
<>essentially as a programmable microengine and programming it to be
<>The reason to fit it in the primary cache is because of how the Alpha

Huh? a PDP11 emulator for alpha would be written as PAL to get the best
results. Caching it is pointless as it's still a 16bit machine and
would still flog itself to death trying to manage a data file greater
than fits in ram (4mb max on PDP11 and some of that would be code!).

The point being, going to VAX(32bits) and later alpha(64bits) was not
raw speed but the limits of having enough bits to address really huge data
arrays in RAM and to express disk data addresses in values that fit in one
register. PDP-11 was 16bits and the MMU allowed it to may that 16bits
into 22bit address space. The however of that was at any time you could
only reach 16bit address worth of data or you had to remap the MMU.
That later step was a limiting factor if your data file was 32mb in size.
PDP-11s were fast and good but the limits of 16bit addressing were well
known by the late 1970s and that was why DEC moved to 32bit VAX in 1978.
Even then a really fast 11/70 could nearly outrun it unless the data file
operated on was say several megabytes in size and the VAX would leave the
11 behind everytime. If that weren't true we'd be running 500mhz PDP-8s!

Received on Wed Apr 22 1998 - 19:01:36 BST

This archive was generated by hypermail 2.3.0 : Fri Oct 10 2014 - 23:30:41 BST