[Beowulf] How Can Microsoft's HPC Server Succeed?

Jon Forrest jlforrest at berkeley.edu
Wed Apr 2 16:01:58 PDT 2008


Joe Landman wrote:
> Hi Jon
> 
> Jon Forrest wrote:
>> First of all, I like Microsoft, and I voluntarily use
>> Vista as my desktop of choice. I've built and run the
>> Windows environments for the top CS and Civil Engineering
>> departments in the US, and I was the first to port
>> Postgres to Windows NT.
> 
> Postgres is nice.  Did you do a native (ms C compiler) port or a cygwin 
> port?

It's an interesting story, which is OT to Beowulf.
I was working for Mike Stonebraker in his research group.
Jolly Chen and Andrew Yu and just added SQL support
to Postgres. Mike and I had been to Microsoft several
times to see about them supporting us, and other research.
I was very interested in Windows NT and very impressed
by Microsoft. This was back in about 1994 or 1995.
Anyway, I had NT 3.51 running on a 16MB 486 and I decided
to try to port what was to become PostgreSQL. I used the MS
Visual C compiler, not cygwin, which I'm not sure existed
back then. The Postgres code was surprisingly easy to
port, although the porting went much faster when Mike
was able to get a 64MB MIPS machine donated. The big
accomplishment was that I was able to
run the infamous Wisconsin Benchmark.

> Oddly enough, for a long time I have believed (and we have proposed 
> privately to Microsoft) ways in which I think it could make a 
> difference.  In short, there are codes that are now and will always be 
> windows based, and that is fine.  They may need to run on a cluster, and 
> they should be able to.

What kind of reaction have you received from them?
What code are you thinking of that is now and will always
be Windows based?

> It needs to adapt.  But not necessarily "compete" the way it has in the 
> past.

How can they adapt to an Open/Free Software world?

> The big question that needs to be 
> answered (by Microsoft) is whether or not they need to displace or take 
> over for Linux to be successful in this space.  I believe the answer to 
> this is "no".

But how will they be able to make any money?

> It might be worth engaging John West (InsideHPC.com), and a number of 
> others in this conversation, as there are some good and informed views 
> about this out there.

I hope they read this thread.

Cordially,
-- 
Jon Forrest
Research Computing Support
College of Chemistry
173 Tan Hall
University of California Berkeley
Berkeley, CA
94720-1460
510-643-1032
jlforrest at berkeley.edu



More information about the Beowulf mailing list