Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: 64 Bit Programs

Author: Robert Hyatt

Date: 07:53:42 07/07/03

Go up one level in this thread


On July 06, 2003 at 17:41:19, Tom Kerrigan wrote:

>On July 06, 2003 at 13:29:55, Robert Hyatt wrote:
>
>>On July 05, 2003 at 17:44:17, Tom Kerrigan wrote:
>>
>>>On July 04, 2003 at 23:49:25, Robert Hyatt wrote:
>>>
>>>>>>The _first_ was the 8080 and it was _not_ a 16 bit cpu.  The 8086 was the
>>>>>Uhhhhhhhhhhh, Bob? Does it make a lot of sense to call the 8080 an "x86"? Hint:
>>>>>there's a reason why the 8086, 80186, 80286, 80386, and 80486 are called "x86"s.
>>>>>Can you think of what that reason is?
>>>>Yes.  Do you know why the 8086 was called the 8086?  Because it was a
>>>>"new and improved" 8080.  Notice the number simularity?  However, they
>>>>"ran out of numbers" and inserted a digit in the middle.  But the 8080
>>>
>>>Uhh, which number do you insert in the middle of 8080 to get 8086?
>>
>>Can't read?
>>
>>8080 -> 8085 -> 8086 -> 8088 and now they are almost "out" of new
>>numbers, so 8086 -> 80186 -> etc.
>>
>>Same family from the start.
>
>Read my other post to this thread, about the BMW 3-series.
>
>>This is no "play land".  Just research the _first_ "personal computer".
>>Hint:  MITS.  Albuquerque, New Mexico.
>>Tell me what processor "started it all".  And while it may well be true that
>>the 8080 and 8086 were not binary compatible, they were certainly
>>_architecturally_ compatible.  My electronic chess board source compiled
>>and ran with nothing more than adjustments for the changed way the new
>>processor did I/O as compared to the old S100 bus my 8080/z80 machines
>>used.
>
>Well, shit, my chess program compiles and runs on an Alpha with no adjustments
>at all. That must mean the Alpha is an x86 and it's architecturally compatible
>with the Pentium. ("Architecturally compatible"?? What kind of nonsense is that?
>Did you mean pin compatible?)

No, I meant _architecturally_ compatible.  Same assembly instructions.  Same
registers.  Same way of doing compares, loops, you-name-it.  I thought it was
a pretty simple-to-follow concept when I told you that my assembly program from
the 8080 compiled and ran perfectly on the 8086 when I upgraded the chess board,
with the only change being the change in I/O caused by a new bus structure.



>
>>_clearly_ the 8088 was a kludge.  If you look at the bus specifications,
>>the nonsense about reading two bytes in two cycles was a kludge from the
>>get-go.  A necessary one if using old 8-bit memory was important, to be
>>sure, but a kludge is a kludge.  (Kludge == doing something in an ugly
>>or inelegant way.)
>
>Reading two bytes over a one byte bus? How many cycles would you EXPECT that to
>take? And how is that a kludge? Do you also think it's a kludge that it takes a
>few cycles to fill a cache line in the P4?

I would have simply used the 8086 and read _two_ bytes at a time.  If you don't
think modifying that basic design to do one byte at a time, just to maintain
compatibility with an old and slow memory module was a "kludge" then I don't
know what a "kludge" would be.  Even Intel designers referred to it in the
same way, with the same reason for doing it that way anyway.

>
>-Tom



This page took 0 seconds to execute

Last modified: Thu, 15 Apr 21 08:11:13 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.