Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Sun & Fujitsu Team On SPARC Chips & System

timothy posted more than 10 years ago | from the abstraction-to-abstraction dept.

Sun Microsystems 121

An anonymous reader writes "Sun and Fujitsu just announced a 20-year partnership to jointly develop SPARC based technology and systems. It looks like the long-predicted partnership that was hinted at earlier has finally come to pass in a much more comprehensive manner than I've heard anyone predict, i.e. not just chips, but a unified range of systems. My guess: Sun drops Ultrasparc III to provide the Throughput computing chips for the low end / web / network stuff, and takes up the Fujitsu provided SPARC64 chips for the high end and workstation market. Will this spark a new RISC renaissance for Sun and Fujitsu? Or is it a last gasp before Opteron / PowerPC / Itanium crush them? I for one will be interested to see what systems and processors come out of this. This could really revitalize the SPARC system market, especially if Sun's work on Throughput computing proves out."

cancel ×

121 comments

First post (-1, Troll)

Anonymous Coward | more than 10 years ago | (#9313005)

In yo face! Yea yea yea yea yea yea white boy. And I ain't even a GNAA member. Take that!

Re:First post (-1, Troll)

Anonymous Coward | more than 10 years ago | (#9313014)

Are you Stupid American [slashdot.org] ?
Then read This [slashdot.org]
and This [slashdot.org]

Piracy. (1)

Fecal Troll Matter (445929) | more than 10 years ago | (#9313060)

Software is one of the most valuable technologies of the Information Age, running everything from PCs to the Internet. Unfortunately, because software is so valuable, and because computers make it easy to create an exact copy of a program in seconds, software piracy is widespread. From individual computer users to professionals who deal wholesale in stolen software, piracy exists in homes, schools, businesses and government. Software pirates not only steal from the companies that make the software, but with less money for research and development of new software, all users are hurt. That's why all software piracy -- even one copy you make for a friend -- is illegal.

As the number of PCs and Internet use grow, the incidence of software piracy is growing, too. The Business Software Alliance believes new technologies should enhance ways to access and distribute copyrighted works legally, not illegally. I hope you will take this into consideration.

Re:Piracy. (0)

Anonymous Coward | more than 10 years ago | (#9313265)

The Business Software Alliance believes new technologies should enhance ways to access and distribute copyrighted works legally, not illegally.

Couldn't agree more, old chap! [gnu.org] Three cheers for the BSA!

20 years? (1, Insightful)

Motherfucking Shit (636021) | more than 10 years ago | (#9313025)

Sun and Fujitsu just announced a 20-year partnership..
I'm sorry, but a 20-year partnership is not only aggressively optimistic, it's just downright insane. Look at what's changed in the computing world over the past 20 years. Microsoft appeared, Apple came and went and came again, Linux emerged and gained ground. Things change fast in the world of Moore's law.

Will Sun be here 20 years from now? Will Fujitsu? If I were a betting man, I'd gamble on the latter more than the former.

This is an interesting deal, and stands to bring much progress in the short term, assuming both parties stick to their commitments. 20 years is a long time, though.

Re:20 years? (4, Informative)

syphoon (619506) | more than 10 years ago | (#9313053)

You were misled by the OP, but RTFA please. The press release said they're expanding their relationship that's already existed for 20 years. Not that they're announcing a 20 year partnership.

Re:20 years? (4, Informative)

Ratbert42 (452340) | more than 10 years ago | (#9313112)

NEW YORK, NY -- July 8, 1987 -- Sun Microsystems, Inc., introduced today the Sun-4 family of 10-MIPS supercomputing workstations and servers that give users the performance of a VAX 8800 system at one-tenth the price.
...
Sun also announced that it will license the new SPARC architecture... SPARC licensees announced today are Fujitsu Microelectronics, Cypress Semiconductor, and Bipolar Integrated Technology.
...

Re: new millenium to the ass. (0)

Anonymous Coward | more than 10 years ago | (#9314574)

It sounds me to speculative execution of inexistent La Merced.

Ohhh, there is not better than Tomasulo or Scoreboard's Algorithm out-of-order execution.

Why not a VLIW 64-bit architecture with 2000-pins chip and a good VLIW64 64-bit compiler?

where is the LaMerced-Killer?

open4free ©

Re:20 years? (3, Interesting)

Billly Gates (198444) | more than 10 years ago | (#9313366)

And its not going good.

The reason Sun is losing is because the SparcV should be out that is comptetive agaisnt (theoritical) agaisnt the power, mips, and Opteron.

TI who actually fabricates teh chips is pulling a Motorolla in order to gain more profits by not upgrading their plants.

Either they innovate and skip the sparcIV and leep to the sparcV and develop the sparcVI or give in to Opteron now and save the company.

Re:20 years? (2, Interesting)

christophersaul (127003) | more than 10 years ago | (#9313602)

Why 'give in' to Opteron? It fits in well with the Sparc kit and Sun are already aggressively marketing Opteron.

Sun are capable of having a strategy that can move with the market, as well as dictating to the market, as appropriate. I get tired of people on Slashdot claiming one company or product is 'dead' just because it has a competitor.

Sun also aren't particularly 'losing', as you put it. Unit shipments were up 26% for the first quarter of 2004, with the UIIIi systems selling extremely well - and they're positioned directly against the Xeon based stuff that Slashdot readers tell us is going to take over the world.

Re:20 years? (1)

CrudPuppy (33870) | more than 10 years ago | (#9313724)

thank you! people saying that the Opteron is going to crush Sun is almost as dumb as people saying the Celeron is going to crush Dell.

Sun's current Opteron lineup is *very* impressive and their roadmap is even more impressive. They compare extremely favorably with Dell server offerings, and Dell is their main competitor in this arena IMHO.

It's a good time to be a consumer because Dell makes very nice and inexpesive cabinets that you can fill with your new Sun gear =)

Re:20 years? (1)

Jim_Maryland (718224) | more than 10 years ago | (#9314236)

Opteron can have some impact on Sun as it changes Sun's image a bit. Wether this is a positive or negative change depends on your point of view. Personally, I see that Sun is looking to provide more economical hardware for the small to medium sized organizations while providing a clear road map should they need to scale up. On the other hand, people who already have a negative opinion of Sun will see the Opteron agreement as Sun giving up on their own chip. The chips can have a perceived affect on Sun which in turn makes it real. Hopefully the affect is a positive one.

In my opinion, Sun's real problem is acceptability in the home desktop market. Microsoft has dominated the home market to the point that people have been raised on MS products and expect to see the same thing in their work environment, at least at the desktop level. In the server room, ideally IT managers would deploy the best solution for a given problem rather than showing their bias toward an OS. Unfortunately for many smaller to medium sized organizations the MS solution is the only possible solution as the view of non-MS solutions is that training and maintenance cost are too expensive.

Dell is their main competitor in this arena

I couldn't agree with you more on this. Sun's current hardware lineup is very competitive on price and, in my opinion, easily out scales the Dell/MS Win32 Server solutions.

Re:20 years? (1)

nelsonal (549144) | more than 10 years ago | (#9314063)

If anything they should have bought AMD when they signed the partnership.

Re:20 years? (1)

grahamlee (522375) | more than 10 years ago | (#9313380)

You seem to have been equally misled by TFA, as Fujitsu were founded in 1985. They could not have had a partnership with anyone twenty years ago. Sun, on the other hand, formed in 1982 so it's feasible that they did. But it wasn't any Fuji rep that Bechtolstein, McNealy, Joy and Khosla shook hands with, if they did.

Re:20 years? (3, Informative)

Dj (224) | more than 10 years ago | (#9313528)

And you seem to not do your research.

http://www.wordiq.com/definition/Fujitsu [wordiq.com]

The company was established in 1935 under the name Fuji Tsshinki Seiz, a spinoff of the Fuji Electric company, this in turn being a joint venture between the Furukawa mining company and German conglomerate Siemens.

Or how about more obviously....

http://pr.fujitsu.com/en/profile/profile.html [fujitsu.com]

Fujitsu is a leading provider of customer-focused information technology and communications solutions for the global marketplace. Since Fujitsu's establishment in 1935, we have maintained a commitment to cutting-edge technological innovation and uncompromising product quality.

So only 50 years out there old chap. :)

Re:20 years? (1)

grahamlee (522375) | more than 10 years ago | (#9313709)

Or 1985 [computerhope.com] . The problem with the web rears its ugly head once more.

Re:20 years? (1)

stiggle (649614) | more than 10 years ago | (#9314765)

But thats only Fujitsu ICL's creation.
ICL was created from the UK computer pioneers (Lyons - with LEO, etc).
They dropped the ICL name about 10 years after the "merger" with Fujitsu.
They sold stuff as Fujitsu Siemens for a while too - dunno if they still do.

Fujitsu have been a long time user/developer of Sparc stuff.

that's why... (5, Funny)

hutkey (709330) | more than 10 years ago | (#9313028)

...Japan is called "Land of the rising Sun"

Here's some more inside information (1, Informative)

Anonymous Coward | more than 10 years ago | (#9314473)

First, check out my previous article [slashdot.org] . I must write anonymously because I currently work in the server division.

To put the matter simply, what killed Sun Microsystems is a pathetic engineering team in the microprocessor division. With the exception of the UltraSPARC I and II, all the other processors were poorly designed and managed. What is unique about Sun's microprocessor division is that the managers consistently and actively hired H-1B workers from Taiwan and India. Foreign engineers were the rule, not the exception.

Not so with Fujitsu. Admittedly Fujitsu had a similar problem with the SPARC64-I, SPARC64-II, SPARC64-III, and SPARC64-IV because all these processors were developed at HAL in Campbell, California. HAL also hired mainly foreign engineers, and previous generations of SPARC64 sucked. Then, Fujitsu became tired of this nonsense, shutdown HAL, and fired everyone. Fujitsu then developed the SPARC64-V entirely in-house, using only Japanese engineers. No foreign engineers.

There is a myth that, somehow, tech companies absolutely need H-1B workers. Well, now we have yet another example of why that myth is just a myth. SPARC64-V built by native engineers crush UltraSPARC III built by H-1B engineers.

To understand how pathetic Sun's microprocessor engineers are, we in the server division actually had servers ready to accept the new UltraSPARC III by the end of 1999. Unfortunately, the processor team was two years late. So, our test machines sat idle.

Note that the server division is not dominated by H-1B engineers. The server division and the microprocessor division are two different worlds: first world versus 3rd world.

I, for one, am glad that we are relying on Fujistu. Its processors are much better designed and built than Sun's own processors. I am glad that Fujitsu will soon OEM high-end servers to Sun. Sun will stop designing and building high-end servers in 2006. (I work on the low-end servers running x86.)

I simply do not see Niagara and Rock as the savior of the company because those designs are well-known public knowledge. Check out Professor Kunle's Hydra work: it is 70% of Niagara. Intel has now embraced the Hydra work and will produce an x86 chip based on Hydra.

Here's a dumb question: Which company will build the fastest, highest performance multi-core chip based on Hydra? Intel or Sun?

Wonder how this fits into the free hardware (5, Funny)

uberkuba (554839) | more than 10 years ago | (#9313034)

Hehehe... hope they know that Sun wants to give their hardware away.

Re:Wonder how this fits into the free hardware (2, Informative)

hutkey (709330) | more than 10 years ago | (#9313146)

no problem for Fujitsu [fujitsu.com] . they are customer oriented [fujitsu.com] people.

so they will not find it diffcult to adapt to the innovative "giving away hardware" teminology, i guess. they will concentrate more on what happens after customers get free hardware.

Throughput computing (4, Interesting)

shoppa (464619) | more than 10 years ago | (#9313037)

I always thought Sun's only realistic market for "Throughput computing" (maximizing ops/watt) was dense server farms (e.g. blades). Now it is true that this market is playing out quite like everyone (especially Sun) wanted it to, but it is a real market.

For thin-client stuff, while low power consumption is a priority, it's not a big enough one to warrant the amount of money that Sun and others have spent on it. Maybe, just maybe, as a spinoff.

These "find a market for our new processor" discussions are getting a little depressing. I remember being excited about the DEC Alpha for embedded applications, but since then it all feels hollow.

other market (3, Informative)

millahtime (710421) | more than 10 years ago | (#9313262)

They have another market in high end engineering desktops. For people who design chips and other detailed components and need to simulate them there is still a market for their work stations.

Now, the other chips are catching quick on this so they need to stay ahead or they could loose that market too.

Re:other market (2, Informative)

afidel (530433) | more than 10 years ago | (#9314011)

They already lost that market. I know quite a few engineers that two years ago couldn't wait for the Opteron to ship so that they could get a cheap fast system to do design work on. They absolutly HAD to have 64bit support as their chip routing would often take 8-12GB of RAM to run in a single process but they were tired of paying SUN prices. When you can get a dual Opteron system with 16GB for less than the 16GB RAM upgrade from SUN you can see why they have lost the market.

What's actually going on here... (5, Interesting)

Anonymous Coward | more than 10 years ago | (#9313038)

1) Sun is having troubles convincing its partners that its multi-core "throughput computing" chip will be competitive. That Gartner report is causing people to ask questions about whether Sun can deliver on its promises. And who wants a 500Mhz 16 core chip anyway? Think of the memory bandwidth problems!

2) Fujitsu Sparc core spanks Suns own core.

My prediction? Sun will abandon its multi-core, asynchronous research pipedreams and farm out all CPU design to Fujitsu. CPU design is a very costly (comoditised) business for Sun to be in, and as Apple have shown its the system that matters, not the processor.

Re:What's actually going on here... (1)

Frit Mock (708952) | more than 10 years ago | (#9313052)


And what do you think, Sun will concentrate on? The software? ... not a big deal in such a partnership for fujitsu then ...

Re:What's actually going on here... (-1, Troll)

Anonymous Coward | more than 10 years ago | (#9313078)

Why the fuck did you add that comma there?

Re:What's actually going on here... (1)

Frit Mock (708952) | more than 10 years ago | (#9313096)


hjm ... in my native language there has to be a comma in this place ;)

Re:What's actually going on here... (1, Funny)

Anonymous Coward | more than 10 years ago | (#9313115)

Sorry, I didn't realise you're an American. My apologies.

Re:What's actually going on here... (-1)

Anonymous Coward | more than 10 years ago | (#9313181)

Are you Stupid American [slashdot.org] ?
If so, then you should read This [slashdot.org]
And This [slashdot.org]

Re:What's actually going on here... (4, Funny)

turgid (580780) | more than 10 years ago | (#9313080)

And who wants a 500Mhz 16 core chip anyway? Think of the memory bandwidth problems!

Who wants a single (or dual) core 5GHz chip anyway? Think of the memory bandwidth problems.

Re:What's actually going on here... (2, Interesting)

larien (5608) | more than 10 years ago | (#9313114)

Well, there are other issues like lock contentions (making sure 2 CPUs aren't using the same chunk of RAM) but the point is correct. The problem with 16 500MHz cores is that a single threaded app will still run at the same speed as a single 500MHz core; you would be able to run more of them at the same time on the 16 cores, though.

Re:What's actually going on here... (4, Informative)

turgid (580780) | more than 10 years ago | (#9313128)

You run Solaris on SPARC processors. Solaris is highly multi-threaded from the ground up. It's extremely fine-grained. It also has some sophisticated algorithms for migrating threads to the most appropriate processor based on things like memory locality and load. (Forgive me if my terminology isn't terribly accurate, I'm not an OS kernel expert). The Niagra and ROCK processors are designed to execute highly multithreaded loads. Fujitsu SPARC64 is more traditional, in that it is designed for loads with fewer concurrent threads. By adopting Fujitsu's high-end gear, Sun gets performance on less thread-intesive loads too. Now Sun and Fujitsu have a horse for every course, so to speak. If I were HP trying to sell itanic boxes, and cranky old (soon to be exterminated) PA-RISC kit, I'd be very worried.

Re:What's actually going on here... (1, Informative)

Anonymous Coward | more than 10 years ago | (#9313249)

>If I were HP trying to sell itanic boxes, and
>cranky old (soon to be exterminated) PA-RISC
>kit, I'd be very worried.

I'm sorry, based on what you posted, you seem
to know something of Sparc hardware and
software, but even if what you say is true,
it's still just another crack pipe dream.

Why? Because business want platforms that
a) Aren't expensive
b) Can run their software today

There really aren't that many apps written
today that have a mandatory need for
"some sophisticated algorithms for migrating threads to the most appropriate processor based on things like memory locality and load"

I really don't think Oracle does; Microsoft's
software doesn't (doesn't even run on sparc);
I don't think OpenOffice needs it. What's left?
Apache? Apache runs just fine on commodity
hardware.

To use a simile, if your analysis is correct,
sun's os+hardware is like buying a $300,000
Feraris for a 5 mile daily commute
.
Only an idiot with more money than common
sense would spend that much money when
they could spend $10,000 on a cheap and reliable
commuter car for the 5 mile daily commute
and spend the rest of the money on a house/vacation/girlfriends/etc.

Re:What's actually going on here... (2, Interesting)

turgid (580780) | more than 10 years ago | (#9313281)

Apache runs just fine on commodity hardware.

So it does. There's more to life than apache though.

I dare you to look at this [sun.com] . Then, think for a minute about what sort of things you'd use it for.

Re:What's actually going on here... (0)

Anonymous Coward | more than 10 years ago | (#9313679)

Apache runs just fine on commodity hardware.

So it does.

Not if you bang on it with a few tens or hundreds of thousands of transactions a second....

Commodity hardware. You get what you pay for.

Re:What's actually going on here... (3, Interesting)

FatherOfONe (515801) | more than 10 years ago | (#9313355)

Oracle would absolutely take advantage of this. Any multi-threaded app would. Like say most of the mid-tier app servers. So in some cases it would be possible to have your database, app-server and web server on one box. Granted that box could be setup with different partitions, (similar to vmware in the low cost world, or perhaps user mode linux).

Solaris Zones (1)

d3xt3r (527989) | more than 10 years ago | (#9313854)

Say maybe like Solaris Zones [sun.com] due for release on Solaris 10 later this year?

From the article:

The Solaris Zones feature is based on the same basic concepts as FreeBSD Jails. In both FreeBSD Jails and Solaris Zones, each virtual view of the runtime environment is completely segregated, and processes from one environment cannot send signals to or even see processes in another. Both Jails and Zones share only one instance of the operating system, though, so multiple runtime environments can coexist on a machine with only one CPU.

I have been playing around with Zones on Solaris Express (Solaris 10 pre-release) and they deliver on their performance promise while easliy isolating applications.

Re:What's actually going on here... (0)

Anonymous Coward | more than 10 years ago | (#9313636)

BEGINQUOTE There really aren't that many apps written
today that have a mandatory need for
"some sophisticated algorithms for migrating threads to the most appropriate processor based on things like memory locality and load"

I really don't think Oracle does; Microsoft's
software doesn't (doesn't even run on sparc);
I don't think OpenOffice needs it. What's left?
Apache? Apache runs just fine on commodity
hardware. ENDQUOTE

This is to funny. It also proves that you have never seen
tyhe inside of a data center. Not a real one anyway.
Your parents basement full of linux boxen doesn't count either.

You're laboring under a misconception (0)

Anonymous Coward | more than 10 years ago | (#9313648)

There really aren't that many apps written
today that have a mandatory need for
"some sophisticated algorithms for migrating threads to the most appropriate processor based on things like memory locality and load"

Get a clue. Ever hear of "web servers"? OLTP? Real-time video processing?

I really don't think Oracle doesYou went two words too far.

Microsoft's
software doesn't (doesn't even run on sparc);
Microsoft's offerings are a joke in the world of high-performance computing. The fact that you even bring Microsoft into a discussion on HPC immediately puts you into the "clueless but still hyping my MCSE" corner.

I don't think OpenOffice needs it

Do you really think OpenOffice of all things defines what high-performance hardware needs to do? Earth is defintely calling, but I don't think the signal is being received....

To use a simile, if your analysis is correct,
sun's os+hardware is like buying a $300,000
Feraris for a 5 mile daily commute.
Only an idiot with more money than common
sense would spend that much money when
they could spend $10,000 on a cheap and reliable
commuter car for the 5 mile daily commute
and spend the rest of the money on a house/vacation/girlfriends/etc.

What kind of moron thinks he can show up at the Indy 500 in a fricken' Yugo?



You must think the desktop is where real computers are. Put you fricken' toy aside.

Re:What's actually going on here... (0)

Anonymous Coward | more than 10 years ago | (#9314396)

Solaris is highly multi-threaded from the ground up. It's extremely fine-grained. It also has some sophisticated algorithms for migrating threads to the most appropriate processor based on things like memory locality and load.

But what good does that do when you're up against Amdahl's law [wikipedia.org] ?

Re:What's actually going on here... (2, Interesting)

turgid (580780) | more than 10 years ago | (#9314675)

The new highly-multithreaded [sun.com] chips have much shorter pipelines unlike current headless-chicken designs like Pentium 4, which operate at obscene clock frequencies but take ages to refill after a pipeline stall hence spening a lot of their clock cycles doing nothing. The idea is that the chip has several simple low-latency cores with many "thread contexts" which can be switched in with a 0-cylce delay when the current thread blocks. So, going back to your Amdahl's Law, the "unimproved fraction" (1-P) on one of these processors is proportionally smaller in many cases where your clock frequency increase on your Pentium would buy you little benefit. Or something.

Witness intel's recent change of direction regarding the future of Pentium. They've all but EOL's the Pentium 4 Netburst architecture and are now going multi-core. It took an anouncement from their competitors though, and lengthy explanations and analysis in the industry press, before they did, once it was absolutely clear that the clock frequency wars were over. Intel is well behind, but they have an absolutely astronomical R&D budget.

No Clue Here (1)

turgid (580780) | more than 10 years ago | (#9313100)

Yet another self-styled expert seriously lacking in a clue.

My prediction: Sun will return, stronger than you could possibly imagine.

Re:No Clue Here (-1)

Anonymous Coward | more than 10 years ago | (#9313131)

Sigh. Yet another hardcore 80's Solaris zealot and/or Sun stock holder.

Re:No Clue Here (1)

grahamlee (522375) | more than 10 years ago | (#9313416)

Hahaha!!!! An 80's Solaris zealot...that's a good one! Solaris 1 (which was still SunOS 4.1) came out in November 1990, Solaris 2 (which was the SunOS 5 we all know and "love" today - why Solaris 9 isn't called 2.9 is beyond me) in July 1992.

why Solaris 9 isn't called 2.9 is beyond me (0)

Anonymous Coward | more than 10 years ago | (#9313703)

why Solaris 9 isn't called 2.9 is beyond me

It is, if you look under the hood:

bash-2.05$ uname -a

SunOS XXXXXX 5.9 Generic_112233-10 sun4u sparc SUNW,Ultra-Enterprise

bash-2.05$

Re:why Solaris 9 isn't called 2.9 is beyond me (1)

grahamlee (522375) | more than 10 years ago | (#9313984)

That's the SunOS version not the Solaris version though. Solaris has been SunOS 5 + Xsun + CDE + cruft + manky stuff for ages now, but the marketing types keep hiking up the version number that appears on the box. I expect the next version will be "Solaris X"...

Re:No Clue Here (0)

Anonymous Coward | more than 10 years ago | (#9313278)

Will they be radioactive and shoot laser beams from their eyes?

Re:No Clue Here (1)

turgid (580780) | more than 10 years ago | (#9313288)

Will they be radioactive and shoot laser beams from their eyes?

Probably. I'd say so. There will probably be aliens on flying-saucers too. And spacemonkies.

Re:What's actually going on here... (2, Interesting)

Anonymous Coward | more than 10 years ago | (#9313104)

You want 16 cores because servers (especially Sun ones) tend to run many process, with many threads. You want to distribute those threads across multiple CPUs so one doesn't bog down the whole system.

Regarding memory bandwidth: look at Sun's I/O bus architecture.

Re:What's actually going on here... (4, Insightful)

jschottm (317343) | more than 10 years ago | (#9313186)

> as Apple have shown its the system that matters, not the processor.

Yes, but remember, Apple was hurting for quite some time after Motorola stopped working on high end PPC chips. The stagnant G4 hurt Apple - I use encoding software that had started out on Macs but moved the focus of its development to Windows after the the G4 lost steam. The apple version still exists and is supported, but lacks some of the features of the Windows version. And while I've not had a chance to run it on a G5, a dual Athlon MP utterly spanks a dual G4.

The G5 certainly helps, but it still leaves Apple at the mercy of an outside supplier.

Re:What's actually going on here... (1)

nelsonal (549144) | more than 10 years ago | (#9314174)

Unfortunatly there will probably never be another integrated semi company formed, certainly not one tied to the PC market. Almost everyone (except Intel (and the analog guys) will be using an outside supplier at least some of the time. Not too many companies can afford a $3 billion fab.

Throughput Computing and the Transputer (4, Interesting)

dnnrly (120163) | more than 10 years ago | (#9313066)

Sun's description of Throughput Computing and their approach of putting multiple processor cores reminds me of what Inmos [inmos.com] tried to do with the Transputer before they became STMicroelectronics [st.com] . The idea was to have many small processors positioned close to each other, communicating between each other closely. I seem to recall seeing transputers on eBay a while back for huge amounts of money. By all accounts, a transputer board was a very useful piece of kit for the right appplications!

Re:Throughput Computing and the Transputer (0)

Anonymous Coward | more than 10 years ago | (#9313533)

Yes, it's a shmae they ended up running DVD layers as the ST20 without the comm's links.

Re:Throughput Computing and the Transputer (0)

Anonymous Coward | more than 10 years ago | (#9313935)

The Transputer also featured a special compiler (or even programming language?) to allow for "auto vectorization" of computational problems - or, call it "auto multi-threader"; because we know - writing correct/debugging MT-code is hard.


Let me also say, that the more fine-grained the locking is, the slower it gets on the non-target (eg. single or up to quad if you have >100 CPUs in mind) systems, because you have to acquire a lock for each subsystem within a subsystem.

Better is to use algorithms that are know to use less or even no locking or operate on seperate copies of data or on non-overlapping ones.

I know it - I wrote a small OS in C++ for my CS-classes at uni.

Re:Throughput Computing and the Transputer (1)

turgid (580780) | more than 10 years ago | (#9314442)

The Transputer also featured a special compiler (or even programming language?) to allow for "auto vectorization" of computational problems

That would be Occam [wikipedia.org] .

FreeBSD (-1, Offtopic)

Anonymous Coward | more than 10 years ago | (#9313070)

FreeBSD is not good at scaling at all. Even their development branch that has been focusing on SMP improvements for the past 4+ years cannot scale past one CPU on a dual Opteron (ie. a very scalable CPU and bus architecture). Seehere/a. [theaimsgroup.com]

Will this spark (2, Funny)

zBoD (86938) | more than 10 years ago | (#9313074)

> Will this spark

Ha ha ha, very funny.

Very punny... (-1, Troll)

blakespot (213991) | more than 10 years ago | (#9313082)

"Will this spark a new RISC renaissance for Sun and Fujitsu?"

Booooooo!!! Good lord.


blakespot

In related news (0, Troll)

mirko (198274) | more than 10 years ago | (#9313088)

Sony just announced [reuters.com] they'd stop distributing new Clie outside of Japan...
So, if they left the handheld market to join the Sparc community, is it in order to create servers, or what ?

Re:In related news (1)

Frit Mock (708952) | more than 10 years ago | (#9313103)


Incredible idea ... "handheld servers" ;)

Re:In related news (0)

NodeZero (49835) | more than 10 years ago | (#9313194)

"Is that a server in your pocket..."

provide the Throughput computing chips for the low (1, Interesting)

Anonymous Coward | more than 10 years ago | (#9313102)

provide the Throughput computing chips for the low end

It's more likely Sun will start using Opterons for the low-end. Why? Because (IIRC) Opterons scale much better than Intel chips in a multiple-CPU environment. And that multiple-CPU ability to scale damn near linearly is Sun's real strength in the computer market.

And they want to give that hardware away because they think people are clamoring to pay for the software they put out?!?!!??

Re:provide the Throughput computing chips for the (0)

Anonymous Coward | more than 10 years ago | (#9313122)

Because (IIRC) Opterons scale much better than Intel chips in a multiple-CPU environment.

No they don't [lwn.net]

That looks like a cluster (0)

Anonymous Coward | more than 10 years ago | (#9313340)

And clusters only work on completely separable problems. If what process 12 is doing depends on what process 187 is doing, clusters suck, despite all their proponents in the academic world.

And how fast is a "shared memory" cluster when processor 34 updates a value that is cached by processor 91? Will processor 91 even know about the change to the value it's holding? This "cache coherency" issue is a huge problem in multiprocessor architecture, and Sun has solved it - and solved in so that it scales damn near linearly up to a few hundred processors at least.

They announced their partnership? (4, Funny)

farmhick (465391) | more than 10 years ago | (#9313111)

Did they have to drive from California to Boston for the ceremony?

And which one wore the dress? ;^)

Crush Fujitsu... maybe. (1)

dbirchall (191839) | more than 10 years ago | (#9313143)

Coincidentally, a Fujitsu PRIMEPOWER HPC2500 server ranked #11 on the last Top500 list. That system uses 2,304 SPARC64 V CPUs running at 1.3GHz, delivering an Rmax (tested maximum performance) of 5406 GFlops and an Rpeak (theoretical maximum performance) of 11980 GFlops. The highest all-Sun system on the list? A 672-CPU Fire 15K cluster, way down at #151. Sun does not build seriously big gear. Fujitsu does. That said, systems using competing processor architectures did finish above that Fujitsu. #10 used 1,920 2.4GHz Xeons, #7 used 2,304 2.4GHz Xeons, #6 used 2,816 2GHz Opterons, #5 used 1,936 1.5GHz Itanium 2s, #4 used 2,500 3.06GHz Xeons, and #3 used 2,200 2.0GHz PPC970 "G5" CPUs. (The other systems used Alpha, IBM SP3, or in the case of the Earth Simulator, NEC chips.) So... Fujitsu's big toys aren't going to drop off the bottom of the Top500 list right away, but it looks like other architectures deliver more bang-per-CPU than the 1.3GHz SPARC64 V. (Now, bang-per-CPU-per-GHz, on the other hand, I'm less sure about... I suspect GHz for GHz the SPARC64 V might outrun a Xeon or a PPC970, but might not quite catch an Itanium.) Anyway, Sun's idea about hardware being free should definitely be extended to Fujitsu's supercomputers, yup! :)

Re:Crush Fujitsu... maybe. (5, Informative)

thesupraman (179040) | more than 10 years ago | (#9313227)

Sigh.

Please try to remember that entry to the 'Top 500' list is as much about your interconnect topology and technology as the capabilities of the processors used.

It is a measure of one, and exactly one benchmark, LINPACK [top500.org]

Machines which are not well suited to this benchmark, or do not have network technologies/topologies well matching linpacks requirements will perform poorly at it, but possibly very well for their chosen purpose.

Good examples of this are the WETA digital clusters used in parts of the LOTR films, which are great for rendering, but hampered seriously in their linpack result by their 100MBit standard ethernet connections.

Another good example of this is the Virginia Tech G5 cluster, which gets a LARGE boost from it's infiniband interconnects (well, it will when Apple finish giving them the new machines... eventually..).

Not that I am defending SPARC's rather lackluster performance these days, just making a rather important point.

Those SPARC boxes better get a LOT cheaper VERY fast if they intend to find any real home in HPC.

Re:Crush Fujitsu... maybe. (1)

RevMike (632002) | more than 10 years ago | (#9313509)

Machines which are not well suited to this benchmark, or do not have network technologies/topologies well matching linpacks requirements will perform poorly at it, but possibly very well for their chosen purpose.

In my experience, Sun does a very good job building servers for medium to large scale corporate computing. Rendering farms and supercomputers are not its thing. But if I'm building a database for a typical corporate application, or even a data warehouse, Sun/Oracle are going to be at the top of the heap - at least until I need to go to Terradata or some other exotic solution.

Lots of corporate applications are not processor intensive, but need high quality I/O gear. Databases need lots of RAM and the fastest disk arrays one can afford. Processors are relatively minor considerations in comparison.

Re:Crush Fujitsu... maybe. (1)

xose (219487) | more than 10 years ago | (#9314072)


Did you hear 'Barney and the Penguin' tale [earthlink.net] ?

sun problem (-1, Troll)

millahtime (710421) | more than 10 years ago | (#9313224)

I have a big problem with suns that drives me nuts. If they are turned off wrong you can break them. Why would I want to buy that?

I may have to pay a little more for another system but if you have brain dead people who break them so easily in the long run you make your money back.

No system should be so fragile.

Re:sun problem (4, Informative)

grigori (676336) | more than 10 years ago | (#9313279)

Baloney. I've had power drop out and kill Sun machines and they just come right back. Are you talking about file system check? Just turn on logging in /etc/vfstab and even that goes away, just like the same reason you use ext3 instead of ext2 on Linux.

Re:sun problem (0)

millahtime (710421) | more than 10 years ago | (#9313305)

No, I was talking about hardware failures because of power problems. Where I went to college and where I wonk now we have a problem with hardware breaking from power failures.

Re:sun problem (1)

confused one (671304) | more than 10 years ago | (#9313378)

That's true of a lot of computers, not just Sun. that's why they invented these amazing things called UPS'

Re:sun problem (2, Informative)

larien (5608) | more than 10 years ago | (#9313381)

I'm with grigori; never had a problem with power failures on a properly configured Sun box. The only server I know of which has a problem is the E150, which you can't power on from init 5 without either a keyboard or a screwdriver. The E150 is probably the worst put together piece of hardware I've ever seen and it astounds me that Sun released it.

Besides, power failures shouldn't happen; you should have UPS on all important servers so power failures shouldn't be a problem at all.

The problem is... (-1, Troll)

SQLz (564901) | more than 10 years ago | (#9313256)

Sun sucks a big fat one. I don't care who they partner with, MS, SCO, Fujitsu, they are going out of business.

Throughput computing. NOT! (1)

xyote (598794) | more than 10 years ago | (#9313285)

when yout go the multi-threaded, CMT, etc.. route then Amdahl's law trumps Moore's law.

Re:Throughput computing. NOT! (1)

grigori (676336) | more than 10 years ago | (#9313517)

No - That's for individual apps with both paralel and serial parts cos the serial part dominates execution and limits paralelisation. Throughput computing says if you're running a web or app server or OS with many independent threads then they all get to run in paralel. No problem with Amdahl's law - that's a different situation

Re:Throughput computing. NOT! (1)

xyote (598794) | more than 10 years ago | (#9313669)

That's only if the threads are completely independent. That's almost never the case. The problem is Amdahl's law has a bit of exponential bite to it. That's why you see all those scalabilty efforts do okay up to 8 or 16 way or so. When they start going to 32 or 64 or greater they start running into trouble. And that's with the highly tuned kernels. Major applications like web servers, databases haven't even started on this. It's only in the discussion stages right now, if at all. I'm supposedly involved with such a project and as far as I know it's only a theoretical possiblity that someone might actually do something about it.

Re:Throughput computing. NOT! (1)

jsavit (701307) | more than 10 years ago | (#9313975)

For Java, individual JVMs have been seen to run happily with good scaling at 16 CPUs now, and maybe more. For database applications like Oracle and DB2 there have been reports of linear scale at 72 CPUs. So, Amdahl's law (and I met him - he's a great man hardly given the credit due him!) really applies to a particular application or algorithm with both serial and parallel components. As the number of CPUs rises, the serial portion tends to dominate - but that's not relevant for *separate* applications!

Re:Throughput computing. NOT! (1)

joib (70841) | more than 10 years ago | (#9314000)

In the HPC world, 1000 cpu jobs are not that uncommon. Of course, these apps run on nodes having relatively few cpu:s and communicate using message passing, so various OS imposed scalability limits doesn't really affect them.

Also, the message passing paradigm tends to lead to programs that replicate as much state as practical on each node, so there is usually less time spent waiting on locks compared to typical multithreaded designs.

Re:Throughput computing. NOT! (0)

Anonymous Coward | more than 10 years ago | (#9314421)

Only if Amdahl's law prevents any SMP system from running (:-))

Joking aside, the throughput chips are not for parallellized scientific computing, they're for squishing a SMP onto a chip.

--dave

Cunning writers (1, Funny)

dj245 (732906) | more than 10 years ago | (#9313306)

...and takes up the Fujitsu provided SPARC64 chips for the high end and workstation market. Will this spark a new RISC renaissance for Sun and Fujitsu?...

Stop it, you're punning me to death. But really though, will the benchmarks from the new systems be fiery or all wet? How heavy are the servers, are they any lighter? And will the chips light your boxes afire or will they be different from the flaming Xeon? Will it be a match for Opteron?

Re:Cunning writers (0)

Anonymous Coward | more than 10 years ago | (#9313414)

hot cross puns, hot cross puns. one a penny two ain't fenny hot cross puns. lost on american ear drums, hot cross puns. "math" is what they call sums. those americans are dumb.

A: I think the bakery that made those hot cross puns just started the flamewar of london.

B: Well at least it'll kill the rats.

A: And we burnt down the white house, didn't we?

B: like I said, at least it'll kill the rats.

thank you.

Re:Cunning writers (1)

johnhennessy (94737) | more than 10 years ago | (#9313597)

A renaissance .... probably not.

I think Sun are due a bit of credit here. They are in the space of 3-6 months after dropping an architecture they have developed and fathered since the late 80s. Would you abandon your own teenager?

Management have obviously faced the cold hard truth - the UltraSparc has been solidly beaten. A lot of companies are very slow to pull the plug on something with as a long a history as this, and usually that delay leads to their downfall - Sun, just maybe have caught this before it was too late, and I personally don't think it's too late yet: Intel have pretty substantial power issues - throwing registers at the problem has finally reached the end of the line for Intel.

Sun are clearly and intelligently hedging here - support the low end with Opteron, support the midrange with SPARC64 - all while waiting and seeing what their Throughput Computing brings out.

Its the same for their software - They're hedging Linux and Solaris.

It's all boiling back to Darwin again - Natural Selection.

May the best OS/Chip Architecture win.

Re:Cunning writers (2, Insightful)

christophersaul (127003) | more than 10 years ago | (#9313677)

They're not dropping an architecture - the architecture's still the same - Sparc.

UltraSparc has not been solidly beaten - UIV is out there now and doing well in the market. It's what follows it that will be jointly developed with Fujitsu, which will operate alongside the forthcoming Niagara and Rock multicore CPUs. Hardly a case of abandoing anything.

The fact that there's another company investing in and developing their own Sparc CPUs validates the whole architecture in the first place.

I agree with you that the strategy makes sense - low end with the 'i' range and Opteron Solaris/Solaris x86/Linux, with Solaris/Sparc for the mid to highend.

Did Sun.... (3, Funny)

wpiman (739077) | more than 10 years ago | (#9313347)

happen to mention that their business model includes free hardware? (see yesterdays article)

That is a slick move- offer free hardware- and then team up with a hardware company to pay for it. Brilliant.

Confusing and mixed messages (3, Insightful)

Anonymous Coward | more than 10 years ago | (#9313516)

So yesterday there was the post about hardware being free and today there's news about Sun partnership for UltraSparc. Make up your freaking mind SUN. I still like SUN hardware for dense deployments where you got tons of racks, since Intel and AMD both run considerably hotter than UltraSparc. Sun needs to make up its mind about whether they believe UltraSparc has a future and stick to it. PC hardware is still isn't as reliable as high end Unix, so it's stupid to drop their R&D for high end systems. Some things simply scale better vertically than horizontally.

Re:Confusing and mixed messages (1)

grigori (676336) | more than 10 years ago | (#9313541)

Thats what this announcement does - it says 'more high end SPARC chips with faster clocks are coming' in addition to the throughput computing chips they previously announced. What's so confusing about that? Agree totally about what you said about vertical scale and reliability and heat

Open-source platform for games (2, Interesting)

Anonymous Coward | more than 10 years ago | (#9313594)

I wonder if funding a kind of open-sourced game development platform wouldn't help the hardware manufacturers (e.g. Sun in this case for the processors and ATI etc. for the graphics) sell their wares. All 3D-engine stuff wide open and free, so that a prospective game maker would not have to buy an engine license.

Problems of course:
- need an installed base to sell enough games
- state of the art engine does not grow on trees
- willingness of hardware types to work together

Possible Pros:
- open standard encourages performance improvements for the next generation that don't break older applications
- massively distributed bug fixing

Re:Open-source platform for games (0)

Anonymous Coward | more than 10 years ago | (#9314915)

Yeah, it'd be kind of like the Fujitsu FM Towns Marty! [roarvgm.com] [assembler.roarvgm.com] That would be awesome... that was such a cool system, and the FM Towns computers in Japan were quite interesting and powerful for their time.

In two years SPARC won't exist (3, Insightful)

Anonymous Coward | more than 10 years ago | (#9313657)

With the Millenium project dead and buried Sun is relying on Ultra SPARC III to carry the comapny until "Mid 2006" when Fujitsu's and Sun's products will be shared between them. The current Niagra design (from Afara) is so low end that Sun will be luck to sell a few hundred systems based on it. If they didn't need a throughput computing product on the market RIGHT NOW they would have killed Niagra already.

When the inevitable schedule slips on Niagra II and Rock come to light (the original Niagra from Afara was "almost done" when Sun bought them two years ago, it's only just taped out) Sun will have no choice but to fall on it's sword and admit defeat. The company might survive if it can convince enough customers to recompile and move to Opteron based systems while sticking with Solaris, but that's going to be a hard sell when they can recompile for linux and not be locked into Sun's software/services stack.

Re:In two years SPARC won't exist (0)

Anonymous Coward | more than 10 years ago | (#9314632)

Not likely, look at SGI, they've been making worse mistakes for years and they are still around. I've been watching SGI shrink for a long time but they're still hanging on by their fingernails. Given how long SGI has held on and how little they seem to have to offer these days, I don't think Sun has all that much to worry about unless they grossly mismanage the company well beyond the sins committed by SGI.

Smart move by SUN (1)

adam872 (652411) | more than 10 years ago | (#9313954)

IMHO this is a wise move by Sun. They can not only share their (considerable) R&D costs with Fujitsu, but they can take advantage of some of the nice performance gains FS have been able to make with SPARC64 (FS machines are big in HPC environments, where Sun doesn't have much traction). This will help their margins and maybe finally they can be profitable again. The other thing is that it gives the SPARC platform a united front and potentially greater market coverage (especially in Europe, where FS are very strong). Maybe there is life in the old dog yet. I hope so, the server market needs companies like Sun. Leaving it to Intel and Microsoft would be a backward step for the industry.

Itanium crushing something? (3, Insightful)

invisik (227250) | more than 10 years ago | (#9314283)

I don't think the Itanium is going to be crushing anything in it's short lifetime. However, the PowerPC/Opteron chips are putting the smack down quite nicely about now. We need them to bring back that Open spec for PPC hardware so we can get some serious speed and off of Intel..... !

-m

Worst intro paragraph ever! (3, Insightful)

oldmanmtn (33675) | more than 10 years ago | (#9314460)

Sun and Fujitsu just announced a 20-year partnership to jointly develop SPARC based technology and systems.

They have had a partnership for 20 years - they aren't announcing a new one.

My guess: Sun drops Ultrasparc III

Sun is already shipping the Ultrasparc IV. Nice guess!

to provide the Throughput computing chips for the low end / web / network stuff,

They have already announced that this is exactly what they are going to do. Again: nice guess!

and takes up the Fujitsu provided SPARC64 chips for the high end and workstation market.

Yesterday's announcement was all about using SPARC64 on the high end. Usually the trick is reading between the lines - not reading the lines themselves.

Sun also announced that they will be using Opterons in their new workstation line - not SPARC64.

Will this spark a new RISC renaissance for Sun and Fujitsu? Or is it a last gasp before Opteron / PowerPC / Itanium crush them?

Itanium has gone white dwarf. The only thing it will be crushing is itself.

Opteron is not going to crush Sun. They have announced that they are shipping multiple Opteron boxes (1-8 way servers and 1-2 way workstations).

This could really revitalize the SPARC system market, especially if Sun's work on Throughput computing proves out.

This doesn't even make sense. The Fujitsu/Sun machines are not the Throughput Computing systems that Sun has been talking about for months. Throughput compututing is Niagara/Rock - the Sun-only CPUs.

And I, for one... (2, Funny)

the_olo (160789) | more than 10 years ago | (#9314769)

...welcome our new Sun&Fujitsu overlords!

8Ep!!? (-1, Offtopic)

Anonymous Coward | more than 10 years ago | (#9314940)

are abouRT 7000/5
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...