On Aug 7, 2025, at 6:52 PM, David Brownlee
<abs(a)absd.org> wrote:
On Thu, 7 Aug 2025 at 23:26, Maciej W. Rozycki via cctalk
<cctalk(a)classiccmp.org> wrote:
>
> On Thu, 7 Aug 2025, Paul Koning wrote:
>
>>> Well, the very same year MIPS Computer Systems came up with the R2000, a
>>> classic RISC design, featuring a(n almost) non-interlocked pipeline design
>>> and with the same 4GiB paged virtual addressing capability and memory
>>> protection also giving true multitasking. A processor architecture the
>>> descendants of which live in millions of devices around the world, and
>>> which inspired other architectures such as DEC Alpha or more recently
>>> RISC-V.
>>
>> I believe the ancestry of Alpha is a bit different, given that it was
>> DEC's third generation RISC design, after the R&D one-off Titan (1982,
>> see
https://bitsavers.org/pdf/dec/tech_reports/WRL-86-1.pdf) and the
>> canceled PRISM (spring 1985,
>>
https://bitsavers.org/pdf/dec/prism/memos/850528_NONVAX.pdf which
>> mentions Titan and Berkeley but not MIPS as inspiration).
>
> Well, the similarity of the ISA is striking, unlike with say the ARM or
> POWER ISAs, and the timeline and the use of MIPS processors in DEC systems
> makes it hard to believe there was no influence. That does not preclude
> other inspirations and it's worth noting that a key architectural mistake
> was avoided (learnt from?), that is the lack of pipeline interlocking.
I don't think of them as all that similar, apart from the inherent similarity of RISC
architectures generally. For example, it avoided the horrors of the delay slot. And it
had some odd decisions, like the initial lack of unaligned load/store and the omission of
the divide instruction.
Given that DEC shipped their first MIPS based
DECstations in 1989, and
PRISM was (I believe) still morphing between 32 bit and 64 bit in that
timescale, it seems very likely that the engineers working on Alpha
were not only aware of MIPS but had direct experience of DEC hardware
and software running on MIPS...
PRISM was cancelled in June 1988, see
https://bitsavers.org/pdf/dec/prism/memos/880617_PRISM_killed.pdf. MIPS was the
replacement at that time. BTW, the PRISM systems overview (1986) lists various
competitors, MIPS is not mentioned.
I'm not sure when Alpha was started. It seems that the may have been a gap where DEC
thought MIPS was enough, but they must have realized it wasn't, or wanted to control
their own destiny, I don't really know. I was never close to that project. FWIW, on
Bitsavers there is the Rev 2 Alpha Calling Standard document, and the revision history
shows the original rev 0.1 draft was from June 1989, i.e., 3 years after PRISM was
cancelled. So while undoubtedly a lot of the Alpha people knew PRISM, there doesn't
appear to be a direct line from one project to the next.
paul