Posts by tpm
125 posts • joined Monday 1st November 2010 20:09 GMT
Re: Glue?
I think you open the glue, sniff it a few times, and then it makes perfect sense. You do get all wet, in any event.
Re: I still want a couple of these to play with --
Oh, man. That hurt my head too when I looked at it! Sorry, that....
Re: Really? "Smashes?"
They had nearly the same number of threads. That was 8,192 physical for the Microsoft server setup and 8,396 virtual threads in the Google cloud. It is not clear how many physical nodes it took to make the Google setup, of course.
Re: some wrong figure there?
Yup. It was 59 seconds, not 29 seconds. Not enough coffee.
Re: Re: Deliberately disingenuous?
I was merely trying to describe what is. I actually admire both ARM and Linaro. You are reading tone that is not there.
To have made that more clear, had I not been rushed, I could have added this:
"This stands in stark contrast to the totalitarian hardware model of Intel, where you get what they make and like it, and Microsoft, where you get what they make and sometimes don't like it."
Now THAT would have been a snarky comment. No snarks intended at either ARM or Linaro. One makes money, one distributes money. Both are collectives and I think good ecosystem players.
Re: it is really simple
That is precisely why I put all of those numbers in there. To show how silly it is.
Re: Puppet Labs
You Win!
Nice one....
Re: Re: > Except this doesn't help when it's the Hypervisor or guest kernel that crashes. :(
See page 4 here:
http://www.stratus.com/Products/ftServerSystems/~/media/Stratus/Files/Library/Collateral/AutomatedUptimeLayerBrochure.pdf
I also contacted Stratus and triple-checked it and they confirmed that you only need one software license for the OS or hypervisor on a pair of machines.
Re: One reason for 5.3...
Good point.
Re: Re: > Except this doesn't help when it's the Hypervisor or guest kernel that crashes. :(
Not true. Both Microsoft and VMware view this as a single system and only charge for one license on the mirrors.
Re: shoot the proof-reader
Shooting seems a bit extreme. As the writer, I can tell you I have a bit of word poisoning after a year of this, so you might as well shoot me, too. I think perhaps some coffee would work better than bullets.
I mean, we don't shoot programmers when their code has a bug. Not yet, anyway.
Re: Support for 512 tape drives?
Sounds like the NSA or Amazon Glacier
I did not know that. Tweaked the story to reflect the change. Thanks.
Re: Re: Stampede
Actually, I put the most recent data into the Top500 story here:
http://www.theregister.co.uk/2012/11/12/top_500_supercomputers_nov_2012/
Dell and TACC said Stampede would be around 9 petaflops, but as you can see in more current documents I cited at https://www.xsede.org/documents/234989/378230/XSEDE12_Stampede_and+MIC_Overview.pdf, the plan is to reach around 10 petaflops peak with a 6 megawatt power draw.
Re: A request for Tim
Hey Marcus
Here's a great place to start with how Nvidia got here:
http://www.theregister.co.uk/2011/11/15/sc11_huang_keynote_exascale/
Re: Where do we get our money back for Tukwila systems?
Well, there is another option. That there was no Sandy Bridge-EX because Ivy Bridge-EX was too close and that Ivy Bridge-EX and Maybe even Haswell-EX will go into what we would have called an Itanium socket.
I am not saying this is the case--Intel has not said. But putting Xeon E7 in an Itanium socket is just as plausible as the reverse.
I think I said game over, or maybe not. And I agree that there are interesting possibilities, which I will be talking to Imagination about to see what they think.
Re: Dell has a higher density per rack U than HP
Absolutely correct. Read my own story wrong as noted elsewhere. Dell has the advantage density wise, packing 5 sleds in 4Us compared to HP's 4 sleds in 4Us
Nope. It was supposed to say "each Copper enclosure has room for a dozen sleds." Apologies.
Re: It's a shame, we owe Intel x64 (not IA64) to AMD
No question about it.
Re: So let me get this straight....
K10 prices were not announced by Nvidia, but buy.com has one listed for $4,000. Which sounds about right based on the Fermi M2090 prices I have seen at server makers.
It must be tempting for Nvidia to think they can charge $10,000 for the K20. Three times the flops for three times the price is not a price/performance improvement. So I am thinking maybe $6,000 is a reasonable price if it can hit the performance levels El Reg is estimating.
We'll see. And a lot, of course, depends on Xeon Phi prices, which no doubt will be lower per flops than whatever Nvidia charges.
Re: The Virtual AI Terrain Team Solution to ITs Real Human and Surreal Practical Resource Problem
Ah, Man from Mars! It is good to see from you. But you are making less, or rather more, sense than usual. I think....
Re: Re: 2013??
Guys. It is a fiscal year. As the story says.
And thanks. Not saying I don't do bloopers. HA! But this ain't one of them.
Re: Now we need good design.
That will happen. It will have to.
And maybe we will have to go back to compiling our code, too, instead of using so many interpreted languages. HA!
Yup. I meant Exalogic.
Re: HP needs a database?
That one is tuned for big data chewing, not transaction processing
Re: In comparison....
Everybody gets their turn in this business.
Mainframes did. Proprietary minis did. Unix did. Windows and Linux may or may not before we all retire, and Intel has so much on its side. But ARM is a very, very serious threat.
Or so I hope lest I die of boredom.
Yup. Not enough coffee.
Re: And have you tried turning it off and on again?
I believe Mother Nature turned it off and on.... HA!
Re: More Nationalistic
TSMC fabs the Sparc64s, and it also does Nvidia GPUs. That would work.
Re: How on earth ..
Discovery from the trial. The real question is how it is that either HP or Oracle can let these internal documents out in public with no consequences.
Re: Re: 37 / 1350 mln
Last graph last sentence was completed screwed up. Fixed now.
Re: SPARC
Yup. Wrote it up here earlier this week:
http://www.theregister.co.uk/2012/06/11/hot_chips_24_preview/
Re: Errata
The revenue streams from NonStop and VMS are what again?
Re: Re: accounts for 70 per cent of data center
Bravo!
Re: So, how exactly is this even a threat to hp?
The threat to HP is merely that it is the first and only real supplier of ARM-based servers up until now. Hence my subhead.
Re: RedSleeve
Thanks Gordan. I told Reg readers about this separately at http://www.theregister.co.uk/2012/05/29/redsleeve_enterprise_linux_arm/
Re: Bubble
Right after everyone installs big data combines and years later figure out their users are mostly doing random crap.
Re: The Cloud Formerly Known As Azure
Was it coffee or cola?
Re: Re: what on earth...
In the old days before these Web 2.5 guys took over the world, I guess it was called database partitioning.
Re: Between the company's name and the headline
You're welcome.
Re: Re: Re: Linux-only mainframes
Just like the AS/400 shops paid for IBM to attack Sun and HP in the Unix racket.
Re: Linux-only mainframes
Yes, but these "official" Linux only mainframes had much lower prices, just like these "official" Power-Linux boxes do.
Re: That's the first time...
I was just amusing myself on a late Friday afternoon because a half dozen people jokingly asked me what scale-in was.
I know what IBM was trying to say, but it was a silly way to say it.
Shadowman is the trademarked name of the Red Hat logo.
http://www.redhat.com/f/pdf/corp/RH-3573_284204_TM_Gd.pdf
Re: Gluster fsck
Yeah, I had it in the subhead. But then I changed my mind to let you guys finish the joke.
