Beta
×

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!

Cray Co-Founder Joins Microsoft

CowboyNeal posted more than 8 years ago | from the switching-horses dept.

Microsoft 169

ergo98 writes "Burton Smith, co-founder and chief scientist at Cray (The Supercomputer Company), has jumped ship. He's joining Microsoft to help them with their clustered computer initiative. Burton joins Microsoft as a technical fellow."

cancel ×

169 comments

Sorry! There are no comments related to the filter you selected.

In other news (5, Funny)

Anonymous Coward | more than 8 years ago | (#14118702)

Microsoft also announced Windows Vista will require a Cray supercomputer to run.

Re:In other news (0, Redundant)

headkase (533448) | more than 8 years ago | (#14118736)

My old computer sitting next to me is about 3 times faster just in megahertz rating than a cray from the mid 80's (iirc ~300Mhz). And that's before you factor in architectural speed gains. What I would really love to have kicking around is the software that ran on those old Crays... 2D nuclear explosion sim's 'n stuff.. ;)

Re:In other news (3, Informative)

Alien Being (18488) | more than 8 years ago | (#14118813)

A 1985 Cray-2 could do about 4 GFLOPS. That's about the same as today's most powerful CPUs.

Hey Burton! (1)

pegr (46683) | more than 8 years ago | (#14118934)

So how's the Kool-aid?

Re:Hey Burton! (1)

Alien Being (18488) | more than 8 years ago | (#14119012)

huh?

Re:Hey Burton! (1)

patiodragon (920102) | more than 8 years ago | (#14119042)

Cult-of-personality reference. Jim Jones gets followers to drink poison kool-aid as he kills himself and all his followers...in the 80's(?)

http://jmm.aaa.net.au/articles/12589.htm [aaa.net.au]

Re:Hey Burton! (1)

pegr (46683) | more than 8 years ago | (#14119181)

Cult-of-personality reference. Jim Jones gets followers to drink poison kool-aid as he kills himself and all his followers...in the 80's(?)
 
While an excellent overview, I use the reference in a more generic fashion... to refer to one who ignores their own moral sense and agrees to further the goals of another, most often at their own peril. Useless Factoid: Jim Jones used Flav-r-aide, not Kool-aid. Grape, I believe...

Re:Hey Burton! (0)

Anonymous Coward | more than 8 years ago | (#14119133)

huh?

It's obviously working....

There's a difference between megahertz... (5, Insightful)

RodgerTheGreat (905510) | more than 8 years ago | (#14118831)

and computing power. Before I get on a rant about the megahertz myth and why I love PowerPC's, the real reason Crays were powerful was their massive parallelism and the use of path optimization (premeasured cables and careful curcuit designs that made the distance electrons had to travel equal between parts of the machine) was the real reason they were a Cray.

Just because your machine is *faster* doesn't mean it's anywhere near as powerful! How many CPU cores does your machine have? I bet the cray had more. Clockspeed means *nothing*. The reason those applications don't exist is because they would take an order of magnitude as long to calculate on your "old computer".

I recommend you do some reading on supercomputing-http://en.wikipedia.org/wiki/Superc omputing [wikipedia.org]

"Supercomputers traditionally gained their speed over conventional computers through the use of innovative designs that allow them to perform many tasks in parallel, as well as complex detail engineering. They tend to be specialized for certain types of computation, usually numerical calculations, and perform poorly at more general computing tasks. Their memory hierarchy is very carefully designed to ensure the processor is kept fed with data and instructions at all times--in fact, much of the performance difference between slower computers and supercomputers is due to the memory hierarchy design and componentry. Their I/O systems tend to be designed to support high bandwidth, with latency less of an issue, because supercomputers are not used for transaction processing."

Re:There's a difference between megahertz... (0)

Anonymous Coward | more than 8 years ago | (#14119126)

[block quote]Just because your machine is *faster* doesn't mean it's anywhere near as powerful! How many CPU cores does your machine have? I bet the cray had more.[/block quote]

You dive into an essay about the power of parallel computing and yet you know nothing about the Cray's from the 1980's??? What is wrong with you?

In the 1980's Cray was the champion of a fast single vector (AltiVec, SSE2) processor. It wasn't until the 1990's that limitations forced Cray to follow the multi-cpu path of other super computer manufacturers.

Re:There's a difference between megahertz... (1)

fingusernames (695699) | more than 8 years ago | (#14119261)

Uh... you simply don't know what you are talking about. EVERY Cray machine released in the 1980s was multi-CPU.

date model CPUs
1976 C1 1
1982 XMP 4
1985 C2 4/8
1988 YMP 8

You probably know the Cray-2 at least. C-shaped, transparent chassis with a cascading waterfall cooling tower. All computing components were submerged in the cooling liquid. Up to eight processors.

Larry

Re:There's a difference between megahertz... (1)

RodgerTheGreat (905510) | more than 8 years ago | (#14119368)

My point was that Cray supercomputers have a superior achitecture to a "modern PC" for what they were used for. Crays had a lot going for them, unrelated to their clockspeed. It's a far too common mistake to equate clockspeed with performance.

Re:There's a difference between megahertz... (4, Informative)

fingusernames (695699) | more than 8 years ago | (#14119186)

Back when I worked at Cray, one project I worked on was the Fortran 90 compiler. The Fortran 90 compiler was developed on Sun SPARC machines and it cross-compiled to the Cray. Crays, even the mighty C-90 back then, weren't that great interactively, and were pretty slow to compile code. Not to mention the fact that Cray CPU time was far more valuable than the Sun machine's. Pre SGI/Tera Cray machines came in two flavors, the original vector processors (C-90 up to 16 or 32 processors?), and the later massively parallel T3 series (with HUNDREDS of DEC Alpha processors). Both were specialized machines which excel at particular tasks. Wickedly fast at those tasks.

Too many people these days work only on PC architectures, and have no/little exposure to other, superior architectures. The PC was and is designed as a cheap, mass produced general purpose desktop device. It in no way compares to supercomputers, mainframes, or true server architectures. A computing environment is more than the sum of the raw megahertz and bandwidth claims of its disparate parts.

Larry

Re:There's a difference between megahertz... (0)

Anonymous Coward | more than 8 years ago | (#14119257)

Read the original post, moron. MID-Eighties

Cray had a single CPU computers until 1989. The C90 wasn't released until the early 1990's.

By any measure, MFLOP's, I/O's, or memory bandwidth, a typical desktop PC is more powerful than a 1985 Cray. The original post was insiteful. It would be fun to play with the 1980's code that was once only useable by supercomputers.

Re:There's a difference between megahertz... (2, Informative)

fingusernames (695699) | more than 8 years ago | (#14119289)

Oh my lord. You are calling me a moron, and then you make that completely bullshit statement?

The X-MP, the Cray-2, the Y-MP. All introduced in the 1980s, and all multi-CPU. The Cray-2 and Y-MP with up to eight processors. How about you try to learn at least a tiny amount about what you write?

Larry

Re:There's a difference between megahertz... (4, Interesting)

forkazoo (138186) | more than 8 years ago | (#14119424)

Well, the Cray-2 was released in 1985, so it only just barely qualifies for the OP's criteria, since it would not have instantly been in widespread use. The X-MP Was released in 1982, so it is probably a fairly good guide to what would have been a "common" supercomputer at the start of 1985.

Before the XMP/EA's came around, the XMP had a max memory capacity of 128 MB (stated at the time as 16 Megawords, as byte notation was not yet universal.) 4 Processors, and a theoretical peak of 200 MFLOPS per processor. Thus, about 800 MFLOPS theoretical aggregate peak.

I just looked up a few numbers real quick... Looks like a dual-proc, dual-core Opteron 270HE has a theoretical peak of over 17 GFLOPS. I'm not intimately familiar with the memory latency characteristics of a cray, but I really can't imagine there being much competition between the two, no matter how great the IO was in 1985.

Obviously, quad-core Opterons are fairly high end... dividing out, and a single core from the system I was looking at the numbers for would be about 4 GFLOPS. Of course, that's peak. Probably something like 2 GFLOPS easily sustained for a modern single desktop CPU. Any AthlonX2 should be able to run the old nuclear sim code quite a lot faster than the "average" cray at the start of 1985. Regardless of any verbal mis-steps, or name calling in this thread, I think the original point was well made. I'd love to get to play around with some of the old sim software. Let's break out the g77, bitches! Let's get a nuclear sim project on sourceforge. It'd be greatly educational, both from a retrocomputing perspective, and from a physics one.

Re:There's a difference between megahertz... (3, Insightful)

itsNothing (761293) | more than 8 years ago | (#14119351)

The real reason that early Crays were powerful was because they were very fast (high speed devices), and their main memory was SRAMs (very low latency, but smaller in size) instead of DRAMs (high latency, large size), so memory requests were serviced quickly. A friend once said that a Cray was a great lisp machine because it had a low latency memory.

The vector registers were interesting, but only of utility for linear algebra problems (Matrix operations), and then only when the vector sizes were fairly large. Their architectural contribution is overrated.

The parallelism you describe is a result of the attack of the killer micros . There was no way that an innovative architecture could compete against the relentless advances in device technology pursued by Intel and others. Most of the modern tera-flop systems use oodles and oodles of "stock" micros and a high performance interconnect network.

Today, the era of the killer micros is about over. Micro manufacturers can't just speed up their devices because they are already operating close to a limit of device technology. "Multi-core" processors are being built primarily because the manufacturers don't know what else to do. We're also about to start seeing the return of "architecture" to the realm of computing.

Re:There's a difference between megahertz... (1)

InnerParty (753801) | more than 8 years ago | (#14119394)

Clockspeed means *nothing*
I understand your argument, and you are correct, however take away the Hz and you don't have a computer! So clockspeed means everything if you look at it that way. So many people these days including G5 and AMD enthusisasts are making statements like "clockspeed means nothing", but I think it weakens their arguments because although you get the gist of what they are trying to say, it sounds ridiculous. Your arguments will have more gravitas if you avoid extreme statements such as this.

Irresistable (0, Redundant)

PunkOfLinux (870955) | more than 8 years ago | (#14118711)

Just a few things
First, didn't someone say that Cray was bought out, and it's only the name and reputation of Cray that survives, but some other company actually does it now?

second, Microsoft might as well not even bother with clustering - they're so far behind the game that there's almost no way they can catch up.

Third, the obligatory comment
A thousand BSODs a thousand times faster!

Re:Irresistable (4, Funny)

RenHoek (101570) | more than 8 years ago | (#14118725)

Third, the obligatory comment
A thousand BSODs a thousand times faster!


Looking at the new Xbox BSOD, I think they're now going for quality of quantity. So instead of a 1000 normal ones, you get one really good one.

Oh shit, my progra-- Ooooohh pretty....

Re:Irresistable (2, Informative)

TheRaven64 (641858) | more than 8 years ago | (#14119421)

I'mve not seen the XBox 360 BSoD, but the OS X equivalent fades the screen to grey and displays a translucent box (with rounded corners) in the middle of the screen telling you in four langauges that you should reboot your computer.

Re:Irresistable (2, Interesting)

in7ane (678796) | more than 8 years ago | (#14118753)

They were bought by SGI in 1996, then spun off and sold to somebody else, who then renamed themselves Cray once again - so Cray is indeed the supercomputer business. Somewhere along the way their not-so-super computer business was sold off to someone else. And no, it is more than name and reputation, they sell the Cray X1 and had some clustering product coming out, which could be hurt by this departure I guess.

And that's some very interesting logic - if you are not no1, just give up.

Re:Irresistable (2, Interesting)

Frumious Wombat (845680) | more than 8 years ago | (#14118801)

I think that "not so super" product you're referring to was the Sparc-based system, which became the Starfire E10K. SGI/Cray couldn't make money on it, but Sun used it to eat their lunch.

Like the old IBM, Microsoft is now big enough that various pieces are running their own projects, and it will be interesting to see how this plays out. Windows that seamlessly clusters, where you could just add machines transparently in a manner similar to a Condor flock, would be an interesting competitor. They may be a lumbering, http://www.eps.mcgill.ca/jargon/jargon.html#evil%2 0and%20rude/ [mcgill.ca] Evil and Rude corporation, but there are some really bright people in there working on more than Office.

Re:Irresistable (1)

SpinJaunt (847897) | more than 8 years ago | (#14118957)

And that's some very interesting logic - if you are not no1, just give up.
tell that to Microsoft who will happily throw millions away to just be no1(sic).

Re:Irresistable (1)

Sri Lumpa (147664) | more than 8 years ago | (#14119496)



        "And that's some very interesting logic - if you are not no1, just give up."

"tell that to Microsoft who will happily throw millions away to just be no1(sic)."

I thought it was to be #2... oops, wrong market. got confused with all the PS2=supercomputer of a few years back.

Re:Irresistable (2, Interesting)

geoffrobinson (109879) | more than 8 years ago | (#14118775)

With all their cash, they can catch up in a big hurry. Also, with their market position they can bide their time. How long did it take NT/2000/XP to become somewhat respectable?

Re:Irresistable (2, Funny)

FidelCatsro (861135) | more than 8 years ago | (#14118824)

"How long did it take NT/2000/XP to become somewhat respectable?"
I will tell you when it happens .

Re:Irresistable (0)

Anonymous Coward | more than 8 years ago | (#14118906)

I must have been too long on Antarctica watching penguins... I haven't noticed that those mentioned MS products have "become somewhat respectable"
While I was gone penguins became respectable...

Re:Irresistable (2, Interesting)

Analog Squirrel (547794) | more than 8 years ago | (#14119239)

I think the "current" incarnation of Cray started when they were bought by Tera Computing, whose primary contributions to supercomputing are in massivly multi-threaded computing. Not the wimpy hyperthread that intel has - 128 complete sets of registers per processing unit, data/control flow analysing compilers to automate the extraction of threads from a program, and a huge, proprietary flat (no cache) memory architecture to make sure that the processor always has instructions and data to compute with. I remember seeing Tera at the Supercomputing 1999 conference... and they've likely improved since then.

Re:Irresistable (1)

Glonoinha (587375) | more than 8 years ago | (#14119362)

128 full sets of registers per processor? Holy fuck, that's wet dream material.
The thought of being able to do context switching between 100+ threads without taking the performance hit of swapping in/out the registers - damn, that's nice.

What's the price of entry on a decently configured one of those?

I applied for that position... (0, Offtopic)

Qzukk (229616) | more than 8 years ago | (#14118720)

but I misunderstood the ad in the paper, and mistakenly applied for the position of "jolly good fellow".

That made me laugh (1)

lheal (86013) | more than 8 years ago | (#14119022)

Sorry, but it did. See, I'm still chuckling oddly to myself.

Reading "good" into a Microsoft ad -- how preposterous!

Crazy? (4, Funny)

HugePedlar (900427) | more than 8 years ago | (#14118723)

I read this as "Crazy co-founder joins MS"

I was thinking "How crazy do you have to be? Crazy enough to throw a chair?"

Re:Crazy? (1)

orbit86 (932209) | more than 8 years ago | (#14118738)

LOL, this will be like the Itanium...I doubt anyone will buy it

Re:Crazy? (1)

MasterPi (896501) | more than 8 years ago | (#14118821)

ur not the only one. must be some kind of common psycological reaction to microsoft

Re:Crazy? (1)

Flyboy Connor (741764) | more than 8 years ago | (#14119123)

Odd. I was reading "Crap co-founder joins MS".

Re:Crazy? (1)

3-State Bit (225583) | more than 8 years ago | (#14119138)

When I read "Cray Co-Founder Joins Microsoft" I immediately thought, "don't you mean joins Google" -- and anyway so what, it's not like they need him, I bet it's just for the business connections. Anyone else have this first reaction to the headline?

Great News (4, Funny)

Essef (12025) | more than 8 years ago | (#14118744)

Windows Cluster Edition System Requirements:

    - 128 CPUs
    - 100 GB RAM
    - 30 square metres of floorspace
    - Liquid Nitrogen cooling system ... and they will still claim it has lower TCO then Linux!

--
Don't read between the lines, the real interesting stuff
is below the line you just read.

Grammar nazism... (1)

Yaa 101 (664725) | more than 8 years ago | (#14118933)

Sorry couldn't leave it...

Quote: "and they will still claim it has lower TCO then Linux!"

"then" is time based comparison. "than" is a subject based comparison.

So the proper usage is:

"and they will still claim it has lower TCO than Linux!"

Re:Grammar nazism... (1)

fatphil (181876) | more than 8 years ago | (#14118999)

Utterly offtopic, but were you aware that the etymology of
then and then is identical. They were, in early English, the
same word. It's only chance that they ended up being clearly
distinct in more recent times.

Re:Grammar nazism... (2, Funny)

fatphil (181876) | more than 8 years ago | (#14119010)

Excellent place for a typo, grand-dad.

Very low memory requirement (1)

Flying pig (925874) | more than 8 years ago | (#14119180)

Only 100G of RAM to 128 CPUs? That's less per CPU than we specify for development boxes today. Or is that L2 cache?
And if you had 30 sq metres of floorspace, you wouldn't need the liquid nitrogen cooling. You could use blown air.

By the time Windows Cluster System Edition comes out, your spec will be considered on the low side for a PDA.

Gone to the Microsoft Side... (4, Funny)

Red Samurai (893134) | more than 8 years ago | (#14118749)

Bill Gates: The Microsoft Side is a pathway to many abilities some consider to be unnatural... Burton Smith: Is it possible to learn this power? Bill Gates: Not if you stay at Cray...

Re:Gone to the Microsoft Side... (4, Funny)

kesuki (321456) | more than 8 years ago | (#14119107)

So now the race is on, who can build skynet first? google? [slashdot.org] microsoft? or linux users? [wikipedia.org]

I think humanities last best hope is that it's microsoft.. humanity is saved by a BSOD (or perhaps by a gaping security hole that allows users to set terminators to target skynet)... of course google will never take skynet out of beta, and linux users would make skynet overly complicated, and abandon the project half way to completion.. when the lead developer gets a real job.

Clarification of "co-founder" (5, Informative)

Durinia (72612) | more than 8 years ago | (#14118752)

Burton was the co-founder of "Tera", the supercomputer company that purchased the old Cray division away from SGI in their 1999 restructuring.

Tera was founded to develop massively multithreaded machines. After their big purchase, they took the Cray name for continuity with Cray's old customers and products, along with the fact that it's a much more viable "commercial" supercomputing name.

Re:Clarification of "co-founder" (5, Interesting)

mpg (220657) | more than 8 years ago | (#14119386)

Burton Smith responsible for architecture of the Tera MTA series and, much earlier, the Denelcor HEP -- both of which were ahead of their times technically but complete failures commercially. (Indeed, Tera Computer had significant financial problems and some corporate governance issues in the years leading up to the Cray purchase. I don't know the financials of Cray today, however.)

Some thoughts, in no particular order:

* The MTA and the HEP, together with Multiflow, represent the commercial roots of the multithreading (MT) work still going on in academia today. Note, however, that the "real" MT work is different by an order of magnitude from what we see in the threaded commericial chips emerging now from Intel, etc.

* The rumor as of a year or so ago was that Burton and a few of the Tera old guard had been pretty much sidelined from the larger Cray operation into unfunded R&D projects being pitched to organizations like ARPA, etc. It would be nice to believe that someone in the commercial arena is going to fund traditional MT ideals, but I'm skpetical.

* What is Microsft doing hiring him? Is this a largely PR move, to improve their HPC image? I have a hard time believing Microsoft is going to spend any money doing parallel architecture work; the list of companies that have tried and failed is long and impressive. Supercomputing today is either custom stuff, or high-end-but-nonetheless-stock hardware running Linux clusters. What's their angle?

* Back in the day, Tera had one of the hottest compilers on the planet; indeed, their compiler IP was pretty much the only valuable stuff left from the MTA project. [Ditto for Multiflow, whose compiler served as the base for Intel's compiler, way back when.] It would be interesting to see who else from the original Tera team follows him over to Redmond -- compiler folk? Architecture folk? Surely not hardware folk?

* If Microsoft wanted Burton, did Google make a play for him too? Now that would have been interesting -- one could have a fun time speculating about masive parallelism and large-grained work tasks across Google's distributed network...

[disclaimer: I briefly worked at Tera in the late 90's.]

Mr. Proprietary, meet Mr. Proprietary... (3, Interesting)

Nigel_Powers (880000) | more than 8 years ago | (#14118755)

Isn't Cray hardware and software completely proprietary? If so, no wonder MS is interested in teaming up with Burton Smith. However, as this article [slashdot.org] suggests, Linux is way ahead of the curve in this arena.

Linux may not ever truly catch on in the desktop environment, but in high-end computing, it's a proven winner.

Not exactly right (5, Informative)

Anonymous Coward | more than 8 years ago | (#14118850)

The Cray XD1 uses Opteron processors and runs a variant of SUSE Linux, but uses a custom interconnect. The Cray XT3 uses Opterons and runs Linux on service nodes, and the Catamount lightweight OS on compute nodes. The Cray X1 series has proprietary CPUs, interconnect, and OS. So you're only partly right. Cray does not hesitate to use Linux where it is appropriate. However, when you are doing something like designing your own vector processor from scratch, porting Linux to it just doesn't make sense.

Linux has certainly proven itself to be a winner in lots of HPC computing applications, and Microsoft has a tough uphill battle to fight if they want to break into this market.

You do seem to be implying that Linux-based computers running commodity hardware always makes more sense than using things like proprietary interconnects. It can certainly be more cost effective, but if performance is your main goal (this is "high performance computing" after all), custom-designed hardware like the interconnect on the XT3 is always going to smoke the off-the-shelf stuff which does not exclusively target the high end.

Re:Not exactly right (2, Insightful)

sluke (26350) | more than 8 years ago | (#14119288)

I agree very much with your post, but would just like to point out that all of this really depends on your application. As an example, many high performance applications use the metropolis method to do Monte Carlo, and in that case (as in many other "embarrasingly parallel" applications) the interconnect hardly matters at all.

Re:Mr. Proprietary, meet Mr. Proprietary... (1)

SpinJaunt (847897) | more than 8 years ago | (#14118946)

Are you suggesting that the beloved Linux is proprietary?

Shame on you.

<Flame-On>

Under training... (4, Funny)

Skiron (735617) | more than 8 years ago | (#14118773)

Burton Smith took a two week training course in several stages for this:

1. The mouse - what is it? 2. How to use the mouse. 3. Learn to click [OK] without thinking. 4. Timing - measure your bogomips with the mouse hourglass icon spinning after you click [Cancel] 5. How to reboot when the mouse hourglass icon is still there after 45 minutes.

In other news (1, Funny)

Anonymous Coward | more than 8 years ago | (#14118778)

Imagine a Beowulf cluster of Microsoft Cray supercomputers... Wait!

No, please don't (0)

Anonymous Coward | more than 8 years ago | (#14118781)

Imagine a Beowulf cluster ... of BSOD's, glowing in the shadows.

    On the other hand, I'd rather not.

    Hm, could that be the (non-O).S. in Darth and the Emperor's 'meditation eggs' ? That would explain why they spend so much time there. Probably trying to recover the files on immortality from the last heuristic sync crash^W^H 8-lane pile-up.

   

Tera Computer Company (3, Informative)

CSHARP123 (904951) | more than 8 years ago | (#14118798)

Burton Smith was co-founder of Tera Computer Company not Cray Inc. He could help MS in improving their thread architecture as well.

Re:Tera Computer Company (3, Informative)

Logger (9214) | more than 8 years ago | (#14119145)

I was going to make this point as well. He does not represent the Cray you are probably familiar with. The brains of the Cray you all know and love still lives on in Chippewa Falls, WI. Although Seymore Cray has long since left and unfortunately died, they still retain their lead vector computing architects.

They've fallen on some hard times as of late. When Terra acquired the remenants of Cray from SGI, they continued Terra's parallel processing work. Which never turned out to be much of a business success. Rumor has it that they are putting their efforts back into vector processing.

Seeing that a Terra co-founder is leaving, this would seem to confirm the shift away from parallel processing (Terra's heritage) and back to vector processing (Cray's heritage.) It has to been tough to compete using the parallel processing business model. It may be a more scalable approach, but everyone and their dog is trying to build these types of systems. Including colleges which whip them together using off the shelf computers. The Terra/Cray advantage was interconnect and memory access speed.

There still are specialized applications that work best on a vector processor such as weather simulations and atomic simulations.

Microsoft is probably a better home for Burton Smith given his approach to supercomputing.

Practical impact on Cray probably nil (0)

Anonymous Coward | more than 8 years ago | (#14118802)

Burton has done some very interesting things in HPC, but I very much doubt that this move will have any practical effect on Cray. Burton's interests seem to have diverged from Cray's recently, and, anyhow, the real mind behind their recent architectural innovations is Steve Scott, their CTO and Chief Architect for the Cray X1 series. It will be interesting to see if Burton continues work on the "Chapel" parallel computing language he has been championing... maybe it will show up in the next Visual Studio. =)

BTW, Burton is only a "co-founder" of Cray in a technical sense. He was a co-founder of Tera, which bought Cray from SGI after SGI bought out Cray.

Well, if you were given the chance... (4, Insightful)

Dread_ed (260158) | more than 8 years ago | (#14118840)

...wouldn't you just love to spend Bill's seemingly ulimited resources to fund your pet project?

The guy is in the business of developing the biggest/fastest/floppiest computers he can. Having the deep-as-the-Pacific pockets of Microsoft to dig into can't hurt his chances of implementing all his pie-in-the-sky ideas.

Smart move if you ask me.

Re:Well, if you were given the chance... (1)

Flyboy Connor (741764) | more than 8 years ago | (#14119095)

...wouldn't you just love to spend Bill's seemingly ulimited resources to fund your pet project?

Indeed. I have sometimes wondered what it would take for me to become a Microsoftie. Despite my loathing for the company, when Bill would offer me my own lab and a serious budget to hire staff, to do my own research until my retirement, I probably would get over my aversion quickly.

Re:Well, if you were given the chance... (1)

Cylix (55374) | more than 8 years ago | (#14119183)

Yes, the Devil is quite good at temptation isn't he?

The good news is, you are quite safe as your soul isn't worth a lab and assistants.

Re:Well, if you were given the chance... (1)

l3v1 (787564) | more than 8 years ago | (#14119124)

I just hope this day will be the one remembered as the day MS started to loose money and drop in red ink below Cray's numbers :P

:P

Quote 11.10.2004... 'One More Thing' (3, Insightful)

djupedal (584558) | more than 8 years ago | (#14118856)

Smith: "One more thing" [taborcommunications.com] is that the uniprocessor has pretty well run out of steam. Parallelism to date has been a nice strategy for HPC users and an afterthought for microprocessor vendors. Now, it is becoming a matter of business survival for all processor vendors. Parallelism is going to be taken more seriously, starting with the idea of exploiting multi-threading and multiple cores on a single problem. This is a major change. Imagine if Microsoft wanted to write Office in a parallel language. What would that language be, and what would be the architecture to support it? We don't have good answers to these questions yet'

Imagine if you got paid to answer that question? Which, by the way comes out as 'parallel' and 'parallel language' (don't mix them up) ...the other shoe drops.

Re:Quote 11.10.2004... 'One More Thing' (3, Informative)

Richard Mills (17522) | more than 8 years ago | (#14118984)

A good guess might be that that parallel language will be something like the in-development "Chapel" language that Burton has been championing. And Burton certainly has a lot of experience working with threading (google Tera's MTA "Multithreaded Architecture" supercomputer). This hire may turn out to make sense for Microsoft.

Re:Quote 11.10.2004... 'One More Thing' (1)

Alien Being (18488) | more than 8 years ago | (#14119094)

"What would that language be?"

Ada. /ducks

Re:Quote 11.10.2004... 'One More Thing' (1)

demachina (71715) | more than 8 years ago | (#14119103)

I more burning question is why would you want to expend the massive R&D effort to make a parallel version of Office or any of the basic desktop apps.

I imagine most of this new work this guy was hired for is targeted at servers, not the desktop. Excel yes I guess I could maybe see an advantage if its a really monster spreadsheet, though I imagine you would be better off just compiling it for starters. Word and Powerpoint just aren't CPU intensive enough that a parallel version would yield enough benefit to counteract the serious pain of threaded software development. It would be especially bad to try to redesign a massive legacy code base that wasn't designed for threading.

Desktop apps, browsing, email and office just aren't screaming out for major leaps in performance at this point other than Microsoft will find new ways in Vista to bloat them up so they require more CPU power to accomplish basically the same tasks people are doing now and have been doing for years. The computer is idle most of the time waiting on the human already unless you just waste it.

Now games, there is an arena in which you will never have enough power. In creating virtual worlds there is no limit to the computing power you can consume and it will always be the driver for performance on the desktop. To a lesser extent multimedia also, if you are running VoIP, movies, music, cameras, vector graphics all at once.

Wodehouse (3, Funny)

IainMH (176964) | more than 8 years ago | (#14118864)

"Burton joins Microsoft as a technical fellow."

Was this article submitted by Bertie Wooster?

Re:Wodehouse (2, Funny)

Skiron (735617) | more than 8 years ago | (#14119004)

No, it would have been "chappie" in that case.

Re:Wodehouse (1)

AndroidCat (229562) | more than 8 years ago | (#14119051)

Do they have many women joining as technical fellows?

Re:Wodehouse (1)

Usquebaugh (230216) | more than 8 years ago | (#14119202)

Prefer PG Tips myself.

Re:Wodehouse (0)

Anonymous Coward | more than 8 years ago | (#14119477)

Took a moment to register. Damn good

GOOD NEWS For Microsoft (in Clustering) (0)

Anonymous Coward | more than 8 years ago | (#14118866)

No doubt, good news!

This man will doubtless be an asset to them in quite a few capacities...

(Especially as the voice of experience in the CCS (clustering edition of Windows Server 2003) area)

After all: Clustering's the last place for MS to completely CRUSH & DOMINATE the "Pro-Linux Penguins" in ultimately is the niche arena of "Super-Computing"/clustering offerings, & to scale as well.

(Nothing's undoable for MS, they just hire on the best talent & give them unlimited research funding & equipment, so expect this to happen imo)!

APK

microsoft penis gets injection (-1, Troll)

Anonymous Coward | more than 8 years ago | (#14118875)

Quit beating a dead horse. Seymour Cray has been dead for quite a while and SGI hasn't owned cray for years and mips sold cray centuries ago so who cares what some nobody from nowhere who leaves a company that has been dead forever and goes to work at microsoft penis. Hey cowboy neal, post another microsoft penis story please so we can all worshop bill gates.

I mean... (0)

Anonymous Coward | more than 8 years ago | (#14118883)

I know they've got a problem to work on, and all, but isn't it a bit much for MS to be bring'n this guy in so soon, just because new xboxen are crashin' & being a turkey and all...?

Non-compete (2, Funny)

Anonymous Coward | more than 8 years ago | (#14118895)

Due to Burton's non-compete agreement with Cray, for his first year as a Microsoft Fellow, he's going to read Cryptonomicon over the company intercom and fix broken chairs in the CEO's office.

Meow (0)

Anonymous Coward | more than 8 years ago | (#14118905)

I remember that microsoft was complaining, because of the conflict of interests, about a former employee joining google. Assuming Cray computers is still in business (last that I knew, they were) wouldn't that potentially be a conflict of interest with the shareholders of Cray?

Microsoft (1)

NoMorePoints.com (930644) | more than 8 years ago | (#14118910)

Burton, [huh, hew] You are my son! [huh, hew] Come to the Dark Side my son! [huh, hew] (Bill Gates during the Interview with Burton Smith) (Comming soon, Bill Gates in "The Matrix") NoMorePoints.com

Edwardian Microsoft (1)

Michael_Burton (608237) | more than 8 years ago | (#14118913)

Burton joins Microsoft as a technical fellow.

What an oddly old-fashioned way to say he's a tech guy.

Re:Edwardian Microsoft (2, Informative)

Flyboy Connor (741764) | more than 8 years ago | (#14119113)

What an oddly old-fashioned way to say he's a tech guy.

If you did not know, a "fellow" is someone who is funded in a particular way. Usually a fellow is someone whose salary is guaranteed and who is allowed a certain budget for research, and has no obligations to produce anything. The idea is that fellowships are awarded to people who will produce the most valuable stuff if you give them free reign. Although I know of an IBM fellow who after receiving the fellowship went to lie on a beach for the rest of his days.

And not google (0)

Anonymous Coward | more than 8 years ago | (#14118926)

Not being a troll, but why Google couldn't allure him to join their team. I would say it is Google's loss.

Re:And not google (1)

Skiron (735617) | more than 8 years ago | (#14118935)

Google already have clustering on Linux. Why would they need to get help to do it?

Re:And not google (0)

Anonymous Coward | more than 8 years ago | (#14119038)

I think you are missing the point. They didn't hire the Firefox guy just to make a browser. So if you have a smart guy/gal, you hire him/her. Good companies invest on person, not skills. I agree with parent-parent. Smith has lot of experiences with high performance computing. Hiring him doesn't mean Google has to switch to Cray or something.

CRAY using Linux (1)

Foofoobar (318279) | more than 8 years ago | (#14118953)

Don't know what he is going to do for them. Have a friend that used to work for them and the new CRAY up here in Seattle is working on clustered super computers running Linux. Don't think that's going to translate.

Re:CRAY using Linux (1)

quarkscat (697644) | more than 8 years ago | (#14119154)

Q:
What do you call the conjunction of Cray/GNU/linux with Wine and ActiveX and MSIE and MS Windows For Clusters(TM)?

A:
It's called a "cluster-fuck".

Q:
How will this be different from the original MS Windows For Clusters(TM)?

A:
No difference, except that the BSODs will also be available on the SSH terminals.

Ohh..., and the MS "Shared Source(TM)" will require not only a soul-snatching NDA, but also with an implanted RFID-protected DRM scheme.

one vote for easy (1)

pigwiggle (882643) | more than 8 years ago | (#14119174)

I would like to see a more user friendly and stable super-computing environment. All the SC I use are remarkably opaque and extremely unstable, including the new Cray XT3. Likely the worst are the Army and DOD computers. Adding to the difficulty of dealing with their esoteric security procedures they insist on running an in house batch scheduler. My research is difficult enough without spending hours debugging scripts.

No doubt... (3, Funny)

mtec (572168) | more than 8 years ago | (#14118956)

...to help develop a supercomputer version of the BSOD.

Inevitable, really... (3, Interesting)

Anonymous Coward | more than 8 years ago | (#14118962)

I think it was a foregone conclusion that Smith would eventually leave Tera^H^H^H^HCray once they dropped the MTA as a product.

Some people have acted as if Burton Smith is the second coming of Seymour Cray. To be blunt, I just don't see it. The MTA was Smith's baby, and by most accounts it was a failure. The first version of machine was based on gallium arsenide technology and was very problematic to manufacture; less than 5 were built. Tera bought Cray largely for their CMOS design experience because they wanted to convert the MTA from GaAs to CMOS, but even that wasn't enough to fix its performance problems. While the massive multithreading capability is cute in theory, the MTA architecture simply doesn't have enough memory bandwidth to handle the scientific codes that cause people to spend 7-8 figures on a supercomputer.

It does seem weird that Burton would go to a software company like Microsoft, though. OTOH, Microsoft Research also employs Jim Gray and Gordon Bell...

Where is the Cluster? (3, Insightful)

deadline (14171) | more than 8 years ago | (#14118966)

This is kind of odd. Burton Smith is not really a cluster guy, although he probably knows his way around HPC (High Performance Computing). Cray is not really a cluster company [newsforge.com] (except for the system they bought from Octiga Bay [technewsworld.com] deal). If you want to read a review of what Bill Gates said at the recent Supercomputing conference, check out Where is the Cluster? [clustermonkey.net] at Cluster Monkey.

A golden age of Fellows (5, Funny)

Anonymous Coward | more than 8 years ago | (#14118989)

The new supercomputing fellow position will be a great complement to Microsoft's existing technology fellowships:
  • Menu drop shadow fellow
  • Tail-recursive Windows-Update/reboot dependency cycle fellow
  • Cartoon balloon notification fellow
  • CD-ROM executable file autorun fellow
  • Animated dog search technology fellow
  • Cool full screen color effect fade fellow
  • File replacement/deletion semantics fellow
  • Marketshare defensive game theory fellow

Truly exciting research and development is in store at Microsoft!.

Re:A golden age of Fellows (1)

ViaNRG (892147) | more than 8 years ago | (#14119248)

You forgot

- Clippy, the "looks like you wanna print an envelope" I wont leave you alone fellow.

It will be interesting to see if Microsoft will use their entrance to the HPC market as a second chance to utilize true open XML, and play well with the others. To survive this market takes a lot of teamwork with proprietary vendors. This could be Microsoft's attempt at saving face.

Unix (2, Interesting)

Dollyknot (216765) | more than 8 years ago | (#14119080)

Perhaps he is going to teach Billy boy Unix, the defacto clustering OS. It could be said, the internet is Unix based, Google is Unix, Apple is Unix, Amazon is Unix, I could go on - Beowolf anyone? 'Tiz a shame Billy boy did not complete his computer science education.

Re:Unix (3, Informative)

CharlesEGrant (465919) | more than 8 years ago | (#14119168)

Umm, perhaps this was before your time, or perhaps you're just going for the wry comment, but back in the day Microsoft had it's own version of UNIX: XENIX. They originally sold it on the Tandy and later ported it to the 386. They gradually sold their UNIX business off to *shudder* SCO. In fact I believe at one point AT&T had to by the rights to sell UNIX on the Intel x86 architecture back from Microsoft. Whatever Bill Gates' many sins, not knowing UNIX is not one of them.

Re:Unix (0)

Anonymous Coward | more than 8 years ago | (#14119342)

Thanks, I think that makes it even funnier. How come he did not know that Unix was far more evolved and stress tested than his cobbled together OS, that evolved from CPM, an 8 bit operating system. Unix evolved on main frames.

BTW I have been around for quite a while, but computers are my hobby, I am not a professional - so there are vast gaps in my knowledge

What's he gonna do? (1)

penguin-collective (932038) | more than 8 years ago | (#14119086)

Hiring big names is good PR. But what else is this guy gonna do? It's not like Cray has been spectacularly successful. Mostly, they made a name with their quirky special purpose hardware before most college students were even born. How is that a good preparation for doing anything reasonable for Microsoft?

Re:What's he gonna do? (1)

NineNine (235196) | more than 8 years ago | (#14119125)

Well, I imagine that there are still plenty of uses for super-high end computing hardware setups. Believe it or not, Pee-Cee's can't do *everything*.

Re:What's he gonna do? (1)

penguin-collective (932038) | more than 8 years ago | (#14119295)

Oh, sure, there are uses for super-high end computing hardware. But, in case you didn't notice, Microsoft is a Pee-Cee company that is working on clustering Pee-Cee hardware. So, again, what sense does this hire make?

Dr. Evil says... (0)

Sfing_ter (99478) | more than 8 years ago | (#14119128)

The Devil's first batch of payments is very lucrative...
Then come the details... is it thursday yet?

Cray must protect itself (2, Informative)

icepick72 (834363) | more than 8 years ago | (#14119185)

Now all Cray has to do is sue Microsoft because the guy is bringing over trade secrets.

A Windows Cluster.... (2, Funny)

Chris Bradshaw (933608) | more than 8 years ago | (#14119204)

Did you say, "Windows Cluster"? I've already got several in my data-center. In fact, every dekstop in my network that runs windows can be considered a "Cluster", "Cluster F#%$^" that is.... HA HA HA HA, I SO FUNNY!

I don't know what Burton will do at Microsoft.... (5, Informative)

computerDr (226122) | more than 8 years ago | (#14119329)

but whatever it is, it will be interesting. Burton Smith is a very bright guy who pioneered multithreading computing first at Denelcor, and then Tera, which bought Cray from SGI and adopted its name. He is the founder of the company which is today called Cray, but the original Cray company was, of course, founded by Seymore Cray.

        Burton always reads broadly and thinks broadly. When designing a supercomputer he deals with every issue, from VLSI technology, Architecture, Operating Systems, and Compilers and Applications. He enthusiastically interacts with many experts, in many areas, and attains a very deep understanding of the issues.

          Burton, best of luck at Microsoft.

Jon Solworth

has to be said (1)

rd4tech (711615) | more than 8 years ago | (#14119420)

1. create a supercomputer
2. ...
3. profit

Burton Smith... (4, Informative)

eXtro (258933) | more than 8 years ago | (#14119422)

isn't a founder of CRAY. He's a founder of TERA Computer who aquired CRAY in the late 90's. He's a proponent of their multithreadhed architecture - an architecture which has abysmally failed commercially. Since 1988 they've had only one actual cash sale of their system. What this probably means is that CRAY is returning to it's strength of vector supercomputers, such as the CRAY1, CRAY2, XMP, YMP, J90, SV1 and SV2 or possibly massively parallel systems such as the T3E and T3F.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?

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>