| Author |
Message |
YKhan
Guest
|
 Posted:
Fri Sep 09, 2005 8:15 am Post subject:
SGI finally on its last legs? |
|
|
"Ernst & Young has advised the Company, however, that its audit report
is likely to contain an explanatory paragraph with respect to the
Company's ability to continue as a going concern."
Silicon Graphics, Inc. Delays 10-K Filing: Financial News - Yahoo!
Finance
http://biz.yahoo.com/prnews/050908/sfth177.html?.v=1
I know it's been said over and over again for the past 15 years that
Silicon Graphics was about to fold, but with it's near complete
reliance on Itanium as its processor of choice, it's really been
cornered into a niche of a niche market.
YOusuf Khan |
|
| Back to top |
|
 |
Dan Koren
Guest
|
| Posted:
Fri Sep 09, 2005 8:15 am Post subject:
Re: SGI finally on its last legs? |
|
|
"YKhan" <yjkhan@gmail.com> wrote in message
news:1126243619.496110.225830@g47g2000cwa.googlegroups.com...
| Quote: | "Ernst & Young has advised the Company, however, that its audit report
is likely to contain an explanatory paragraph with respect to the
Company's ability to continue as a going concern."
Silicon Graphics, Inc. Delays 10-K Filing: Financial News - Yahoo!
Finance
http://biz.yahoo.com/prnews/050908/sfth177.html?.v=1
I know it's been said over and over again for the past 15 years that
Silicon Graphics was about to fold, but with it's near complete
reliance on Itanium as its processor of choice, it's really been
cornered into a niche of a niche market.
|
More to the point -- it cornered itself.
dk |
|
| Back to top |
|
|
John Savard
Guest
|
| Posted:
Sat Sep 10, 2005 5:52 am Post subject:
Re: SGI finally on its last legs? |
|
|
On 8 Sep 2005 22:26:59 -0700, "YKhan" <yjkhan@gmail.com> wrote, in part:
| Quote: | but with it's near complete
reliance on Itanium as its processor of choice, it's really been
cornered into a niche of a niche market.
|
If you're making supercomputers, and you can't make your own chips like
Cray or NEC, the Itanium _is_ the best choice, since it offers the most
performance *per core*. Also, it has population count - and _byte_
matrix multiply.
Of course, people whose applications are highly parallelizable can use
chips that offer more performance per dollar, and still get their
answers as quickly.
John Savard
http://home.ecn.ab.ca/~jsavard/index.html
http://www.quadibloc.com/index.html
_________________________________________
Usenet Zone Free Binaries Usenet Server
More than 140,000 groups
Unlimited download
http://www.usenetzone.com to open account |
|
| Back to top |
|
|
YKhan
Guest
|
| Posted:
Sat Sep 10, 2005 8:15 am Post subject:
Re: SGI finally on its last legs? |
|
|
John Savard wrote:
| Quote: | If you're making supercomputers, and you can't make your own chips like
Cray or NEC, the Itanium _is_ the best choice, since it offers the most
performance *per core*. Also, it has population count - and _byte_
matrix multiply.
|
Cray's future is now with Opteron processors, not its own chips.
Yousuf Khan |
|
| Back to top |
|
|
Guest
|
| Posted:
Sun Sep 11, 2005 6:12 am Post subject:
Re: SGI finally on its last legs? |
|
|
John Savard wrote:
| Quote: | If you're making supercomputers, and you can't make your own chips like
Cray or NEC, the Itanium _is_ the best choice, since it offers the most
performance *per core*.
|
I think the following 4 ratios are each more important than per core
performance:
1) price/performance
2) performance/socket
3) performance/watt
4) performacne/rack
Opteron wins all 4 of these. I bet we see Opteron growing fast on the
top500.org now that they have dual-core chips. You want to bet on
Itanium?
-- Vince |
|
| Back to top |
|
|
Iain McClatchie
Guest
|
| Posted:
Sun Sep 11, 2005 8:15 am Post subject:
Re: SGI finally on its last legs? |
|
|
YKhan> I know it's been said over and over again for the past 15 years
that
YKhan> Silicon Graphics was about to fold, but with it's near complete
YKhan> reliance on Itanium as its processor of choice, it's really been
YKhan> cornered into a niche of a niche market.
Dan> More to the point -- it cornered itself.
Forest Baskett was the guy who made the call to go with Itanium. Intel
made him (and later, many other engineers) sign NDAs which said,
essentially, that once they'd looked at the Itanium they couldn't work
on CPUs for SGI ever again. So FB signed the thing, took a look, and
then couldn't have a really critical conversation with anyone who
actually knew how to build a CPU. There were a whole lot of people in
the company that could have professionally taken apart Intel's claims
for that thing, but the nature of the business arrangements forced SGI
upper management to make the decision with no technical input.
You can't fault Ed McCracken for decisions made with no technical
input: he's a sales guy, it's not his job to know that stuff. But you
can fault him for getting himself into a position where he had to make
big decisions with essentially no technical input -- i.e. just Forest
Baskett's take. |
|
| Back to top |
|
|
John Savard
Guest
|
| Posted:
Sun Sep 11, 2005 4:15 pm Post subject:
Re: SGI finally on its last legs? |
|
|
On 10 Sep 2005 18:12:04 -0700, vince@offshore.ai wrote, in part:
| Quote: | John Savard wrote:
If you're making supercomputers, and you can't make your own chips like
Cray or NEC, the Itanium _is_ the best choice, since it offers the most
performance *per core*.
I think the following 4 ratios are each more important than per core
performance:
1) price/performance
2) performance/socket
3) performance/watt
4) performacne/rack
Opteron wins all 4 of these. I bet we see Opteron growing fast on the
top500.org now that they have dual-core chips. You want to bet on
Itanium?
|
You want to bet that nine women can have a baby in one month?
Yes, Itanium will soon be history if it remains as badly overpriced as
it is. If Intel is capable of making a multicore Itanium with any yield
at all, they will also be able, soon, to make single-core Itaniums with
much higher yield and lower prices.
Performance per core is important - or, rather, *latency* is important -
because a great many important applications that can benefit from
supercomputer power are not fully parallelizable.
The processors used in the Cray X-1 and the NEC SX-6, for example, are
significantly more powerful than even the Itanium, however. Although
they don't get redesigned for process improvements as frequently.
Multicore, as opposed to multi-chip, offers only one technical benefit -
faster access to a shared cache. It isn't that often that an application
can be parallelized, and yet the separate threads still access the same
memory. The big benefit of multicore seems to come from Microsoft
licensing policies.
The Itanium isn't quite a supercomputer-on-a-chip, but we're getting to
the point where enough transistors are available for that.
John Savard
http://home.ecn.ab.ca/~jsavard/index.html
http://www.quadibloc.com/index.html
_________________________________________
Usenet Zone Free Binaries Usenet Server
More than 140,000 groups
Unlimited download
http://www.usenetzone.com to open account |
|
| Back to top |
|
|
Guest
|
| Posted:
Sun Sep 11, 2005 4:15 pm Post subject:
Re: SGI finally on its last legs? |
|
|
| Quote: | You want to bet that nine women can have a baby in one month?
|
Supercomputers today use lots of processors and applications are
designed for this.
| Quote: | Yes, Itanium will soon be history if it remains as badly overpriced as
it is. If Intel is capable of making a multicore Itanium with any yield
at all, they will also be able, soon, to make single-core Itaniums with
much higher yield and lower prices.
|
Itanium instructions take about 2 times the memory of AMD64
instructions,
and 2 times the memory bandwidth, and 2 times the instruction cache,
and 2 times the instruction cache bandwidth. Can't imagine Itanium
ever
matching AMD price/performance.
| Quote: | Performance per core is important - or, rather, *latency* is important -
because a great many important applications that can benefit from
supercomputer power are not fully parallelizable.
|
The Opteron performance per core is not that far behind (even ahead on
integer).
Latency makes me think of Pathscale.com's Infinipath. This is a low
latency
interface card that lets Opterons use cheap infiniband switches. They
say
1.32 Microseconds MPI Latency (8-byte, 1/2 round trip). Seems like
this
should do well. What do you think?
| Quote: | Multicore, as opposed to multi-chip, offers only one technical benefit -
faster access to a shared cache.
|
I think the main benefit is better use of transistors. If you have 1
billion
transistors and you make one core and cache, while I use 1 billion
transistors and make 2 cores and 2 caches, I ought to be able to beat
you
if I am any good and our benchmark is reasonably parallel.
| Quote: | The big benefit of multicore seems to come from Microsoft licensing policies.
|
I have had some fun emails with them. They say that multi-chip-modules
count as multiple processors for licensing. They said each die counts
as a
processor. I then asked if the soon to be released Paxville from
Intel, with
2 die (and I gave them a link to a picture), counted as 2 processors.
They
said they were reviewing their policy. If they come up with some
definition
where Paxville's 2 die don't make it a multi-chip-module, I will be
amused
to see it.
| Quote: | The Itanium isn't quite a supercomputer-on-a-chip, but we're getting to
the point where enough transistors are available for that.
|
Any of the current chips is supercomputer level performance from some
10 or 15 years back. And remember, if Itanium is close to being a
Supercomputer, then Opteron must already be there. |
|
| Back to top |
|
|
Dan Koren
Guest
|
| Posted:
Sun Sep 11, 2005 10:49 pm Post subject:
Re: SGI finally on its last legs? |
|
|
"Iain McClatchie" <iain-3@truecircuits.com> wrote in message
news:1126423597.626875.320600@g47g2000cwa.googlegroups.com...
| Quote: | YKhan> I know it's been said over and over again for the past 15 years
that
YKhan> Silicon Graphics was about to fold, but with it's near complete
YKhan> reliance on Itanium as its processor of choice, it's really been
YKhan> cornered into a niche of a niche market.
Dan> More to the point -- it cornered itself.
Forest Baskett was the guy who made the call to go with Itanium. Intel
made him (and later, many other engineers) sign NDAs which said,
essentially, that once they'd looked at the Itanium they couldn't work
on CPUs for SGI ever again. So FB signed the thing, took a look, and
then couldn't have a really critical conversation with anyone who
actually knew how to build a CPU. There were a whole lot of people in
the company that could have professionally taken apart Intel's claims
for that thing, but the nature of the business arrangements forced SGI
upper management to make the decision with no technical input.
You can't fault Ed McCracken for decisions made with no technical
input: he's a sales guy, it's not his job to know that stuff. But you
can fault him for getting himself into a position where he had to make
big decisions with essentially no technical input -- i.e. just Forest
Baskett's take.
|
I would not try to pin the blame on any one person.
In the big picture it is completely irrelevant who
made the decision and how. In fairness one must also
consider the dilemma these people are/were facing:
computer vendors with less than $15B/year revenue
can no longer afford to do processor development.
dk |
|
| Back to top |
|
|
Greg Lindahl
Guest
|
| Posted:
Mon Sep 12, 2005 12:15 am Post subject:
Re: SGI finally on its last legs? |
|
|
In article <43241db8.4481061@news.usenetzone.com>,
John Savard <jsavard@excxn.aNOSPAMb.cdn.invalid> wrote:
| Quote: | Multicore, as opposed to multi-chip, offers only one technical benefit -
faster access to a shared cache.
|
Er, no, a shared cache is actually more cycles in the uncontended
case. So that's a dubious benefit. And that's why most multi-core
chips don't have a shared cache.
-- greg |
|
| Back to top |
|
|
Dan Koren
Guest
|
| Posted:
Mon Sep 12, 2005 12:15 am Post subject:
Re: SGI finally on its last legs? |
|
|
\"Greg Lindahl" <lindahl@pbm.com> wrote in message
news:4324934a$1@news.meer.net...
| Quote: | In article <43241db8.4481061@news.usenetzone.com>,
John Savard <jsavard@excxn.aNOSPAMb.cdn.invalid> wrote:
Multicore, as opposed to multi-chip,
offers only one technical benefit -
faster access to a shared cache.
Er, no, a shared cache is actually
more cycles in the uncontended case.
^^^^^^^^^^^ |
---------------------+++++++++++
Why? Do you think there is some
inherent reason, or it is just
an artifact of current designs?
Thx,
dk |
|
| Back to top |
|
|
Dan Koren
Guest
|
| Posted:
Mon Sep 12, 2005 12:15 am Post subject:
Re: SGI finally on its last legs? |
|
|
"Dan Koren" <dankoren@yahoo.com> wrote in message
news:43249e75$1@news.meer.net...
| Quote: |
\"Greg Lindahl" <lindahl@pbm.com> wrote in message
news:4324934a$1@news.meer.net...
In article <43241db8.4481061@news.usenetzone.com>,
John Savard <jsavard@excxn.aNOSPAMb.cdn.invalid> wrote:
Multicore, as opposed to multi-chip,
offers only one technical benefit -
faster access to a shared cache.
Er, no, a shared cache is actually
more cycles in the uncontended case.
^^^^^^^^^^^
---------------------+++++++++++
Why? Do you think there is some
inherent reason, or it is just
an artifact of current designs?
|
Obviously to support two cores or
processors efficiently, a cache
would have to be dual- or multi-
ported. Beyond which I cannot
see any obstacles.
dk |
|
| Back to top |
|
|
Bill Bradley
Guest
|
| Posted:
Mon Sep 12, 2005 6:34 am Post subject:
Re: SGI finally on its last legs? |
|
|
Dan Koren wrote:
| Quote: | "Dan Koren" <dankoren@yahoo.com> wrote in message
news:43249e75$1@news.meer.net...
\"Greg Lindahl" <lindahl@pbm.com> wrote in message
news:4324934a$1@news.meer.net...
In article <43241db8.4481061@news.usenetzone.com>,
John Savard <jsavard@excxn.aNOSPAMb.cdn.invalid> wrote:
Multicore, as opposed to multi-chip,
offers only one technical benefit -
faster access to a shared cache.
Er, no, a shared cache is actually
more cycles in the uncontended case.
^^^^^^^^^^^
---------------------+++++++++++
Why? Do you think there is some
inherent reason, or it is just
an artifact of current designs?
Obviously to support two cores or
processors efficiently, a cache
would have to be dual- or multi-
ported. Beyond which I cannot
see any obstacles.
|
You seem to be missing the fact that a particular line contains several
bytes (64 for L1 on P4s, 8 for Athlon64s) which the processors may want
to claim ownership of one or more. Lots of ugly logic and
communications with the cache to only claim some instead of the whole
line. Other fun stuff comes in depending on tagging by virtual vs.
physical address (bus snooping means only having to worry about physical
and allowing a processor which is not running the same thread to look at
the TLB is probably not the best security either) Speculative
operations and unretired instructions would probably get entertaining too.
Bill |
|
| Back to top |
|
|
Dan Koren
Guest
|
| Posted:
Mon Sep 12, 2005 8:15 am Post subject:
Re: SGI finally on its last legs? |
|
|
"Bill Bradley" <senator2@NOSPAMearthlink.net> wrote in message
news:YW4Ve.9084$Wd7.4383@newsread1.news.pas.earthlink.net...
| Quote: | Dan Koren wrote:
"Dan Koren" <dankoren@yahoo.com> wrote in message
news:43249e75$1@news.meer.net...
\"Greg Lindahl" <lindahl@pbm.com> wrote in message
news:4324934a$1@news.meer.net...
In article <43241db8.4481061@news.usenetzone.com>,
John Savard <jsavard@excxn.aNOSPAMb.cdn.invalid> wrote:
Multicore, as opposed to multi-chip,
offers only one technical benefit -
faster access to a shared cache.
Er, no, a shared cache is actually
more cycles in the uncontended case.
^^^^^^^^^^^
---------------------+++++++++++
Why? Do you think there is some
inherent reason, or it is just
an artifact of current designs?
Obviously to support two cores or
processors efficiently, a cache
would have to be dual- or multi-
ported. Beyond which I cannot
see any obstacles.
You seem to be missing the fact that a particular line contains several
bytes (64 for L1 on P4s, 8 for Athlon64s) which the processors may want to
claim ownership of one or more. Lots of ugly logic and communications
with the cache to only claim some instead of the whole line. Other fun
stuff comes in depending on tagging by virtual vs. physical address (bus
snooping means only having to worry about physical and allowing a
processor which is not running the same thread to look at the TLB is
probably not the best security either) Speculative operations and
unretired instructions would probably get entertaining too.
|
No, I'm not missing any of it.
Greg's original statement was about the *uncontended* case,
which I take to mean an entire cache line is being accessed
for reads by multiple cores -- no ownership needs to be
claimed for bits, bytes or crumbs. Maybe Greg had something
different in mind -- if so a clarification would be welcome.
As to the logic for everything else, it wouldn't be much
(if any) different from the logic that is already there
anyway to deal with multiple processor access, right?
(at least in first approximation).
Or is there something else you think I may have missed?
Incidentally, the topic of shared caches was explored in
a Ph.D. dissertation from Stanford around the mid '90s,
whose author's name escapes my feeble memory right now.
As a footnote, I am not aware of any currently shipping
architectures that use virtual address tagging. The cost
of it has sunk more than one architecture (MIPS RS-6000
comes to mind immediately).
dk |
|
| Back to top |
|
|
Del Cecchi
Guest
|
| Posted:
Mon Sep 12, 2005 9:28 pm Post subject:
Re: SGI finally on its last legs? |
|
|
Iain McClatchie wrote:
| Quote: | YKhan> I know it's been said over and over again for the past 15 years
that
YKhan> Silicon Graphics was about to fold, but with it's near complete
YKhan> reliance on Itanium as its processor of choice, it's really been
YKhan> cornered into a niche of a niche market.
Dan> More to the point -- it cornered itself.
Forest Baskett was the guy who made the call to go with Itanium. Intel
made him (and later, many other engineers) sign NDAs which said,
essentially, that once they'd looked at the Itanium they couldn't work
on CPUs for SGI ever again. So FB signed the thing, took a look, and
then couldn't have a really critical conversation with anyone who
actually knew how to build a CPU. There were a whole lot of people in
the company that could have professionally taken apart Intel's claims
for that thing, but the nature of the business arrangements forced SGI
upper management to make the decision with no technical input.
You can't fault Ed McCracken for decisions made with no technical
input: he's a sales guy, it's not his job to know that stuff. But you
can fault him for getting himself into a position where he had to make
big decisions with essentially no technical input -- i.e. just Forest
Baskett's take.
|
I can fault some doof for signing a NDA with such terms. Where were the
lawyers that should have advised him? Although he should have been wise
enough not to recognize the problem on his own.
My guess is that he had decided to transition to Intel for business
reasons, and the notion that Itanium would be a technical flop never
occurred to him. Besides, what choice did he have?
--
Del Cecchi
"This post is my own and doesn’t necessarily represent IBM’s positions,
strategies or opinions.” |
|
| Back to top |
|
|
|
|
|
|
FAQ
Memberlist
Register
Profile
Log in to check your private messages
Log in