[Info-vax] Dave Cutler, Prism, DEC, Microsoft, etc.

[JF Mezei]

Neil Rieck wrote:

> I'm not sure I agree with these points. In the book "DEC is Dead, Long
> Live DEC" it was stated that clock-for-clock comparisons between CISC
> and RISC showed that RISC out performed CISC two-to-one without any
> special tuning.

One need not forget that the VAX instruction set is far more complex
than the 8086 or IBM 360/370/390 or whatever it is called this week.

The 8086 and 360 architectures are more compatible with a CISC to RISC
translator inside the chip.

To me, one of the biggest mistake is to not make "VEST" standard AND
more integrated. If they had done a VAX emulators with the same
flexibility and transprency as Apple did the 68k emulator when it moved
to PowerPC (or the Rosetta PPC emulator when it moved to Intel), then
the VAX to Alpha migration would have been far more succesfull with
fewer VAX->SUN migrations. And DEC wouldn't have had to terminate a
whole chunk of the VMS softwre base since it could have continued to run
on VMS in emulated mode until it would have been recompiled to run Alpha
native. This would have greatly reduced the costs and allowed the whole
software library to run on Alpha, even for defunct software whose owners
were no longer there to recompile for Alpha.


> Let's also remember that DEC/Compaq sold more Alphas than
> VAX.

Nice statistic, but it would need to be put into context. In the 1970s
and early/mid 1980s, DEC grew at the same pace as the market.  But in
the 1990s, DEC shrank while the market expanded a lot. So while hard
numbers may show more alpha sold, I would say that when put relative to
market, Alpha was far less significant to the whole market in its
lifetime than VAX was during it tenure.


>Apparently Intel has sold more Itaniums than VAX + Alpha combined
> so the world didn't exactly fall to pieces with the end of VAX.

And Intel has sold orders of magnitudes more 8086s than it has I64s
during the same time period. IA64 serves one company (HP) which is now
much bigger than Digital ever was. And the overall market continues to
grow. So yeah, even a low volume proprietary chip like IA64 will have no
problem outselling Alpha.

Also, one needs to consider manufacturing costs.  Building a Nehalem
8086 with quickpath requires a huge investment in sophisticated FAB and
you need to produce a lot to get payback on investment. The 8086s have
tons of volume to justify these investments.   IA64 gets "hand me downs"
since it is one or two generations behind in process, so it can use
older FABs.  The high development costs coupled with low volumes are not
a recipe for success for IA64.

The big question is whether the Alpha architecture, if it had been
adopted by Intel in 1999, could have progressed at a faster pace and
lower development costs than what Intel has been able to achieve with IA64.


But as it stands, IA64 is late to the game and nobody is missing it.
That says a lot about its lack of importance in the market.