[vcf-midatlantic] Working on a historical microprocessor exhibt

[David Riley]

On Feb 9, 2020, at 3:08 PM, Dave McGuire via vcf-midatlantic <vcf-midatlantic at lists.vcfed.org> wrote:
> 
> On 2/9/20 2:58 PM, Adam Michlin wrote:
>> That fills a huge hole in my understanding of architecture history. It
>> certainly makes sense that there would be separate ICs that eventually
>> merged into one discrete CPU. I just assumed it was done by the
>> minicomputer manufacturers themselves. I had no idea it was AMD! Thanks!
> 
>  Well bit-slice chips were made by many manufacturers.  Keep in mind
> the minicomputer manufacturers were the chip companies' bread & butter
> for a long time.  Even Intel; they made the 3000 series of bit-slice parts.
> 
>  But it wasn't really separate ICs that eventually merged to form
> microprocessors.  The Am2901 was introduced in 1975, well after there
> were a few microprocessors on the market.  These chips, and their
> applications, coexisted with monolithic VLSI microprocessors for a long
> time.  Bit-slice design was commonplace clear up until at least 1990.
> It was just a different way of doing things that was more scalable and
> flexible.
> 
>  And at the time of introduction of the VAX-11/730, for example,
> designing a single VLSI chip that implemented an architecture as complex
> as VAX wasn't really practical.  The first single-chip VLSI
> implementation of the VAX architecture (the 78032, used in the
> MicroVAX-II and others) wouldn't tape out for another three years after
> that.

And it was sloooow by comparison to its contemporary VAXen.  Its primary benefits were board space, component cost and power savings, at the expense of a fair amount of speed.  Fully integrated microprocessors didn't outperform their multi-chip or discrete-part brethren until the era of the NVAX (which was concurrent with the big-ass ECL-based VAX 9000, which it outperformed, much to DEC's chagrin).  That was 1989 or so.


- Dave

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 873 bytes
Desc: Message signed with OpenPGP
URL: <https://lists.vcfed.org/pipermail/vcf-midatlantic/attachments/20200211/580ccc45/attachment.sig>