From: Eugene Miya on
>>>>>>> A step backward John.
>>not an app perspective.

In article <et8mc8$8qk_001(a)s787.apx1.sbo.ma.dialup.rcn.com>,
<jmfbahciv(a)aol.com> wrote:
>Of course not. But it had damned well be from the OS' perspective.
>That is the mindset change that has to happen.

It's the world we are given.
The LISP guys (hey, didn't they start on 10s and 20s and 6s and 7090s)
would not have had it that way. They lost (some what).


>>>TOPS-10 was described
>>>as general purpose timesharing. This implies "anybody".
>>How long do you want to wait for solution?
>
>But it is not a difficult problem.

When you have problems measured in Cray-years, you tend to toss out the
higher end, longer running ideas. But you still really want to solve
those. Triage is not a useful idea for long.

>>>>>It is against human nature laws to produce a computer that
>>>>>is perfect for everybody.
>>>>Likely true.
>>>There is no likely about it. One man's hell is another man's
>>>paradise.
>>
>>While hell and paradise likely have Dantean depths, the analogy is too
>>simple.
>
>No, it is not. You have to keep that in your head if you design
>anything that is going to try to be the "perfect, can work for
>anybody" goal.

Anybody can oversimplify Barb.
The world has more shades of gray.
It's not just pink or blue.

>>>>>I think this is your tradeoff litmus test.
>>>>Not bad.
>>>??
>>Means that I think you are likely in the right directions (maybe a
>>quadrant) but too binary.
>
>I may be too binary, but I know how to do it. I just can't talk
>using the details in my lanaguage. It's a mindset; the technology
>falls out.

Then consider, like Cray, when you die, you will take your thinking to
the grave.


>> Better papers that litmus exist if you insist
>>on a chemistry analogy. So I reserve judgment on your fuller analogy
>>on nature's laws.
>
>It has more to do with how humans work and think rather than
>laws of nature. There is already one guy who is actively
>working on this kind of stuff. I've been watching his progress;
>his approach will be a part of the solution....or it should be
>if people bother to think things through first.

Humans have to live in the natural universe.
Humans when living among themselves work many ways but in some
contraints of social settings. Distance keep us from killing wach other
off along with rule ideas.

--
From: John L on
>Why does everybody keep assuming that PDP-10s have to be limited
>to 18-bit addressing? Isn't it simply a small matter of wiring
>to fetch more than 18bits for effective address calculations?

The 6/10 instruction set had 18 bit address fields and 18 bit address
calculation rules. All the software assumed that was how the
addressing worked.

You could easily have designed a machine similar to the -10 with wider
address calculcations, which is what they did for the -20's extended
addressing, but then you had a different instruction set. If you were
going to have to change all your programs anyway, it made more sense
to switch to something with a larger flat address space than the
segmented -20 addresses.

R's,
John

From: glen herrmannsfeldt on
Nick Maclaren wrote:

(snip)

> Reread what I said. Did you never use systems with twos complement
> floating-point?

The PDP-10 uses twos complement floating point. That is, the whole
word is complemented for negative values. It seems strange to me,
but it does allow one to use the same compare instructions as
for fixed point.

Some DSPs use twos complement, but not like the PDP-10.
Only the fraction is complemented, which still seems strange
to me, but not so strange as above.

-- glen

From: Peter Flass on
jmfbahciv(a)aol.com wrote:

> In article <mddtzwpgcq7.fsf(a)panix5.panix.com>,
> Rich Alderson <news(a)alderson.users.panix.com> wrote:
>
>>jmfbahciv(a)aol.com writes:
>>
>>
>>>In article <et4hl0$1vlg$1(a)gal.iecc.com>, johnl(a)iecc.com (John L) wrote:
>>
>>>>>So what was missing in the PDP-10 architecture?
>>
>>>>Address bits, the same thing that killed every other old architecture.
>>
>>>Address bits with respect to what? I don't see the problem.
>>>I'm not a hardware type but a fetch for effective address
>>>calculations can be 36-bits wide. Can it not?
>>
>>No, it cannot. The largest offset from an index base (the only way to go
>>beyond 18 bits of address) is 2^18, and there's no way to get around that.
>
>
> Why? I still don't understand why you are constraining the index
> base to be 18 bits. I'd make it 36 (if we had a 36-bit word
> boundary architecture). Those 18 bits is 18 wires, right?

This would work. It makes the architecture effectively
base-displacement, with the 36-bit index registers now base registers,
and the address field in the instruction the displacement. Like 360,
but with *much* larger amounts of data addressable from one base register.

From: Peter Flass on
jmfbahciv(a)aol.com wrote:

> In article <45f730c0$0$16659$4c368faf(a)roadrunner.com>,
> Peter Flass <Peter_Flass(a)Yahoo.com> wrote:
>
>>jmfbahciv(a)aol.com wrote:
>>
>>
>>>In article <et4hl0$1vlg$1(a)gal.iecc.com>, johnl(a)iecc.com (John L) wrote:
>>>
>>>
>>>>>So what was missing in the PDP-10 architecture?
>>>>
>>>>Address bits, the same thing that killed every other old architecture.
>>>
>>>
>>>Address bits with respect to what? I don't see the problem.
>>>I'm not a hardware type but a fetch for effective address
>>>calculations can be 36-bits wide. Can it not?
>>>You don't have to change current instructions. You can
>>>add, or extend, existing instructions to manipulate greater
>>>than 18-bit addresses.
>>
>>If I'm doing the math right, this is 64 Giga-*Words*, or 256 Gigabytes
>>assuming you pick 9-bit bytes. Should be enough. If you need more,
>>change the page-table format (paging makes it a -20, right?)
>
>
> Wrong. You want to be able to "extend" it without any changes.
> Changes imply that something of old would no longer work.

Only the OS would see this.

>
>
>
>> One adress
>>space could still only map 64GW, but you could have lots of address spaces.
>
>
> You are thinking grom the app up POV. YOu need to also think
> from the OS down POV.
>
> For instance why does an app need to know the physical number of
> the maximum? YOu have the OS give a number if it thinks it needs
> one.

64GW is 2**36, if I exponentiated right. This is the physical limit of
a 36-bit address.