Sun, Fujitsu launches entry quad-core Sparc box Fujitsu and server partner Sun Microsystems will today roll out an entry server based on the quad-core Sparc64 VII processor created by Fujitsu. The server, code-named "Ikkaku" (Japanese for "narwhal") and sold as the Sparc Enterprise M3000, is a single-socket box that will fill in a product gap in the companies' combined …
Oh dear, not satisified with bleating FUD and hot-air as ACs, it seems the Sunshiners have now worked out how to fool the Reg forum sign-up into allowing them to use my nom de plume, probably with just an extra character in the name. How childish, but then I'm not surprised. Since the Reg also requires an email address tied to each forum sign-up I assume it won't be past their capabillities to screen out the fake. Failing that, just send an email saying "Red Hat Linux is more cost effective and performant than Solaris x86 - discuss", and look for the frothing response.
In the meantime, I was actually going to say this looks like one of Sun's smarter decisions as Niagara just doesn't cut the mustard, and there are thousands of old Netras out there that will need replacing. But now I'll just laugh instead.
<quote>The server, code-named "Ikkaku" (Japanese for "narwhal") and sold as the Sparc Enterprise M3000, is a single-socket box that will fill in a product gap in the companies' combined Sparc T and Sparc64 VII product lines.</quote>
Glad to see that "Ikkaku" is the Japanese for "narwhal"... now wtf is "narwhal"? A city/place, possibly, but no capital letter? It's certainly not English (to my knowledge - I'm willing to bet a small amount of money), so "narwhal" is what for what? Someone please put me out of my misery.
Paris, because she once offered to show me her "narwhal" and I politely declined... not knowing what it was :-(
"Glad to see that "Ikkaku" is the Japanese for "narwhal"... now wtf is "narwhal"? A city/place, possibly, but no capital letter? It's certainly not English (to my knowledge - I'm willing to bet a small amount of money), so "narwhal" is what for what? Someone please put me out of my misery."
or, you could just google it AC.. it's not that hard
"Sun's smarter decisions as Niagara just doesn't cut the mustard"
You are a funny guy. Heres one for ya, T5220 running Oracle 11g, mostly OLTP with 200 concurrent internal users and > 100 concurrent external business clients and 2000+ per day end user clients.
1 $30K server with no complaints. It works for us and is about 1/3 the price as a replacement 490 last year; which would have been the natural upgrade to replacing a 480 but EOS'ed and not worth the investment. We did early this year look at the m4000 but we don't have the $$$ to suck up both $80K for the server and another $80k for additional Oracle database ransom.
For our purpose and budget it works fine; better than we expected, really. Don't get me wrong in a perfect world with a perfect budget this sysadmin would jump at the chance at running a Power6 monster but its not and we definitely don't have the budget.
Another note: T2 + JAVA + NIX or NUX = smokin!! Wintel can't even get into the game at the same price!! Yes, the NUX is UBUNTU, but dude still its not windows unless you run with Webster Phreaky. Na, you seem to know what you are talking about.
LOL
And being Danish, then Narwhal is translated to Narhval. Which directly translated would be Jester Whale, well it's funny if you are Danish.
This was a product that SUN needed, but where is the 2 socked server ?
And must admit that I think it is to expensive, it is about the same price as a p520 with equal cores, disk RAM. And the p520 will beat the M3000 to a pulp on every benchmark.
// Jesper
You can spot the fake Matt Bryant's posts by his limited grasp on reality, complete lack of technical knowledge, and the fact that he obviously doesn't work in computing. Keep trying, Sunshiners. If you're waiting for Rock I wouldn't hold your breath, and you could drive a truck through the holes in the limited Sun product range.
In the meantime, I'm just waiting for the posts accusing poor Jesper of being a paid IBM lackey, etc, for darng to say a Power system could be better than anything birthed by the Great Schwartz.
Why would anyone accuse Jesper of anything. He's commenting on a pretty impressive IBM product. It's his opinion... You just seem to think that HP can do no wrong, while constantly forgetting that Itanic is a dead CPU. When you are forced to port your applications to yet another CPU, will you come on here and admit that HP has no clue when it comes to high end computing?
Why do you always attack Sun for their CPU track record, yet never say a word about HP's horrendous record?
A limited grasp on reality huh HP Boy? :-) Pott, kettle, black, lets disect shall we?
Post from you, above : this looks like one of Sun's smarter decisions as Niagara just doesn't cut the mustard
Post from you, a few weeks ago : We did look at replacing the Xeon front end webservers with T2 kit due to performance gains.
OK, the second sentence is ad'libbed a bit to take out your usual HP marketing FUD/ anti-Sun dribble but you get the idea. I'm enjoying the fact it must actually pain you to have publicly admitted T2's have more performance than Xeons! Matt, your slipping...
To demonstrate, I've posted links on here for Xeon vs T2 performance, you must have seen them. Someone else posted links to "real benchmarks" which Oracle felt were real enough & showing T2 kit has the record for siebel transactions and so forth.
So who really has the limited grasp of reality? The person above who spotted how to mimic you or the person the with the poisin pen promoting HP cr@p all the time?
We can always spot you Matt so worry not, you generally go : "Take off your blindfold sunshiners and see your Ultraspanked CPU set is all doom doom doom but HP is so great, great great, ah, sh!t, someone made a valid point that undermines me! Superdumb might be dead, Itanic is going down! Might be dead soon!! No matter, I'll write a three page essay disparaging them with so much FUD that everyone dies of boredom in their seats before they can offer a response & I'll have the last comment! Yey!"
And to set the record straight IBM are offering reliable fast servers but at a price and not many people like AIX. I personally don't, it's never seemed user friendly once past the SVR3/4 stuff and into AIX specifics.
"....I'm enjoying the fact it must actually pain you to have publicly admitted T2's have more performance than Xeons! Matt, your slipping..." Actually, you very selectively misquoted me - the complete line said the T2 did give a slightly better performance with this specific webserving scenario, but cost almost twice as much. In this respect it was being such a poor return on investment that caused the T2 systems to be dropped from consideration. I suspect that little reminder will lessen your enjoyment.
"....Someone else posted links to "real benchmarks" which Oracle felt were real enough...." Real enough that Oracle slapped in a massive disclaimer saying they didn't stand by any of the results. Still, I'm sure every company out there with a non-Siebel application will be going "stuff comparing performance with standard benchmarks like TPC-H or any of that SPEC malarkey, that Niagara stuff must be good to do so well on an application I don't use". Yes, about as likely as T5220 somehow becoming the world's premier choice for Oracle databases (I'll give you a clue - it's not any Sun product holding that number one spot!).
"...We can always spot you Matt so worry not..." Don't tell me, posting with the name Matt Bryant wasn't a big enough clue to the author then? You Sunshiners are just going to confuse yourselves if you keep on posting under other peoples' names. It seems you have such a difficulty remebering your own, always posting under AC.
"....And to set the record straight IBM are offering reliable fast servers but at a price and not many people like AIX. I personally don't, it's never seemed user friendly once past the SVR3/4 stuff and into AIX specifics." Unluckily for you Sunshiners, whom all seem to have an endemic inabality to move to other platforms, AIX and Power seem to be eating up big chunks of the Slowaris market almost as fast as Integrity. DId it ever occur to you just because you can't make the switch from one OS to another that the majority of other people can and do just fine? Oh, sorry, I forgot there is only One Truth and it is spoken by the Great Sun! Nobody else need be considered, in fact they must be shouted down at all costs.
/still laughing, only harder.
ZzzzZzzz.... Zzzzz.... Oh bugger, I just woke up at my desk, Matt sent me to sleep again.
okeedokee Mr Sales dude, come and give us the loving again, you made us feel a bit shiny & special before when you DID admit Xeons had less performance than T2's, come on, do it again!! Do you want the link to the page to show you the loving?
I want that friday feeling Matt, even if the ackowledgment is a weeny one. Show us the love!
As for real benchmarks, you failed to respond to someones post which stated your desired format, ie: TPC or "real" benchmarks (and other posts cited Java benchmarks, hmm, Java seems a real common thing so I assume specjb is valid as well? :
"Why only point at T2+? The comment was that HP is losing the performance battle with the poor choice of Itanic... Let's look at the SAP benchmark, where the Sun M9000 had 39100 users compared to HP SuperDomes 30000 users. The M9000 had 196570 SAPS, while the SuperDome only had 152530.
How about SPECfp2006 where Sun demonstrated a score of 28.8 SPECfp2006 (25.5base)... HP can't even beat Sun's base number...
There are too many records to enumerate here. You can find them yourself. TPC-C is a joke, and TPC-H is only slightly less so. Even HP doesn't use TPC-C anymore (though IBM keeps chugging along on this joke of a benchmark). However, let's look at those TPC-C numbers, shall we? Sun's 1000GB result is 118,573 qphh, which HP's result is only 69,999. Quite a difference..."
OK, onwards Matty boy., 3rd poin. Erm, I was answering your apparent earlier concern we wouldn't be able to differerentiate you, (add memory loss to bias, hmm, Bryant profile now updated).
And finally the 4th piece of trolling dribble, did you stop to consider that perhaps all the people using Solaris are doing it because it works and it has a lot of vendor support and until recently was Oracle's favoured platform (until Oracle turned into MIcroshite and want to own the world, including OS, middleware layers + the core database at the backend)
Bugger, I really am feeding the trolls today!
Ah, it's the magic Sun benchmarks again! Go to SPEC.org and search the results for M9000 and you get results for only two tests - SPECint_rate2006 and SPECfp_rate2006 - another case of Sun being very carefully only to bench on what they want and nothing that might threaten them. Then, look at the M9000 results are 2288 and 2005, whilst the Superdome's are 1648 and 1479 - but hold on a sec, that's 256 cores in the Sun (sorry, I meant FSC) system, compared to 128 cores in the Superdome. In fact, the 128 core Sun figures are only 1294 and 1225, which means the Sun kit got thrashed. In fact, for Sun to match the HP system, they would have to go to at least 200 cores and pay for an extra database licences over the HP system. A quick check of the SAP results shows an even worse case with Sun being out-perfromed core-for-core by over 40% when comparing to an HP test from 2006! Not even the latest Itanium cores and latest hp-ux, no wonder Sun wants to compare! Truth is Sun has to make very selective and dishonest comparisons with HP because they are so far behind on performance per core, and such a bad return on investment. I just can't wait for Tukzilla, which will really punish Sun.
As for the TPC results quoted, just got to www.tpc.org and click on the Top Ten Resulsts By Performance - Sun is not in the list. In fact, the highest SPARC entry is for the old FSC PRIMEQUEST 580 with a score of 2,196,268, whilst HP have the SD from last year (not even the latest release of hp-ux 11i v3!) at 4,092,799. I feel duty-bound to point out IBM still have the fastest result. In the meantime, the price-per-tpmC comparison is not good for the FSC either - $4.70 versus $2.93 for the HP system. Doesn't matter how much try and twist the results, the fact is M9000 result like the one quoted have not been submitted for TPC validation, which makes it highly questionable to quote. In fact, part of the TPC agreement that all vendors sign is that no vendor will quote any TPC test results without having them validated. I think you need to have words with your Sun salesgrunt about a little professional honesty....
But anyway, let's not laugh too much at these Sun results, but instead consider that, when asked for T2 or T2+ results for industry standard benchmarks, the Sunshiners again run for cover and try and deflect the conversation to SPARC64, a chip they used to disparage because it used to steal sales from UltraSPANKED. SPARC64 is a good chip, but it was never meant to be in Sun systems, and is only there becasue Sun screwed up UltraSPANKED and now can't get Rock out the door.
/still pointing, still laughing
Comparing core to core is a waste of time. It's about the system, no? HP can't scale as high as Sun, let alone IBM. The Sun systems are cheaper/perf. Get an Oracle site license, like we have, and you don't have to worry about core licensing. Also, when you buy SAP it comes with the Oracle license, which is not licensed per core! The per core argument is for those that are still working on a single core Intel laptop.
Turn that finger around and point it at yourself Mr. "I'm so smart I can't stand it" Bryant.
Also, as has been pointed out before, what makes you think that Tukwila will ever come out? Intel's canceled better chips before. My guess is that Itanic is Xeon bound, which will reduce HP's scalability even more, and cause another porting effort for all the HP faithful. Will HP port HPUX over to X86? I doubt it. Then what will they do? Linux maybe? Perhaps Solaris? If I were a HPUX user, I would start converting over to Linux or Solaris now. Why stay on an obviously dead OS like HPUX?
"Comparing core to core is a waste of time...." No, most enterprise software is billed per core, so unless you can build your stack from free software you will pay more to get the same performance with Sun kit as you will with Integrity. And even if you do get a fully free stack, you still have to pay someone to support it and - guess what - most software support costs are per core. So the Sun solution - sorry, I mean the FSC solution in drag - would still cost you more than the Integrity solution.
"....Get an Oracle site license..." Another bit of distortion - there is no such thing as an Oracle site licence, each one is actually a carefully calculated individual licence based on how many users and/or how many cores Oracle expects you to use. Oracle site licences are subject to revue and audit, so simply pretending that there is a one-fee-buys-all fixed licence is not true - if Oracle think you are going to use more sockets they will want to charge you more.
"....Also, as has been pointed out before, what makes you think that Tukwila will ever come out?...." And I give the usual reply - what sustainable argument do you have against it coming out? None. Both HP and Intel make a profit off Itanium so they both have an interest in bringing out Tukzilla. Compare this to Sun, whom are losing money faster than they can make it, and although Sun need Rock you suddenly realise they may not be able to afford it by the time it is ready.
"....My guess is that Itanic is Xeon bound, which will reduce HP's scalability even more...." Well, Bill, your guess just goes to show your lack of technical and industry knowledge. Xeon can already scale to more than Niagara, and using grid technology has scaled to greater size than any SPARC installation in existance. That didn't stop Itanium being produced. What you should consider with real fear is that CSI (aka Quickpath) will allow Xeon to scale to similar reaches as Itanium without needing grid technology, which will just about kill any chance Niagara has, especially with the low-power tech from Atom in the mix. A future low-power Xeon using CSI and HP's cell-based technology could scale to 256 cores, and I bet it will come in a nice blades chassis too. Users will choose Xeon blades with Windows and/or Linux for normal tasks, and Itanium blades with hp-ux and/or Linux for heavy thread tasks, and maybe Atom blades for low-powered tasks like virtual desktops. I'm sure Sun will try and follow behind IBM and HP as they get their offerings out first, but I doubt Sun's hardware division will last that long. By then, Sun will just be a software shop flogging support for Slowaris on Xeon, and no-doubt still losing market share to Red Hat.
Hi Salesboy,
"256 cores in the Sun (sorry, I meant FSC) system, compared to 128 cores in the Superdome"
Er, perhaps thats because Itanium has only managed to get to a dual core model. Why the hell would Sun benchmark dual core Sparc64's when they are selling quad core Sparc64vii that can have 256 cores in a 64 socket frame. Itanium can only hold 128 cores in a 64 socket frame, your problem (or HP's it would seem). Sorry it beat your beloved.
If/when quad core Tukwilla comes out do you not wonder that the Sparc64 might be onto 8 cores, hell, 16core Rock CPU's could be out before then, there still scheduled. Quad core Itanic's, 16 core Rock, this could be a call to Hollywood for a new film :
"Itanic 2, sunk by Rock instead of Icebergs". I want the lead role!
Anyway, onwards : "Xeon can already scale to more than Niagara"
Come on Matt, show me the love, I'm begging!!! Lets do some link exchanging again shall we? OK, here goes mine again : http://blogs.sun.com/mrbenchmark/
Like before, yes, this is a slower frequency than the latest but look at the curves HP boy, 8 threads and BOOM!! Bye bye Itanium performance.
Isn't this what led you in the first place to state T2's were faster than Xeons?
Go on Matt, do it again, show me the love....
"....Why the hell would Sun benchmark dual core Sparc64's when they are selling quad core Sparc64vii that can have 256 cores in a 64 socket frame...." True, but then Sun have to have twice as many cores to beat Itanium, and that means it will be more expensive - much more expensive. Which is one of the reasons why more customers buy Itanium in Integrity servers. Other reasons would be a better support structure, better designs, and management tools that actually integrate and work. You also forgot to mention that when Sun populates FSC's frames to capacity they lose expansion options, which doesn't happen with the HP Integrity range. Which is why the market is beating your beloved Sun down to a delisting.
"....If/when quad core Tukwilla comes out do you not wonder that the Sparc64 might be onto 8 cores...." Well, you should check the rather vague FSC roadmaps, then. FSC don't plan on having the speedbumped Jupiter+ until mid-2009, which means in Sun servers about Q1 2010 at the earliest. There is no date for FSC eight-core parts, they seem have to have caught the vapourware bug from Sun. Which means Intel have until forever to get Tukzilla out the door, but instead they have a solid roadmap showing Tukzilla due Q1 2009. The 32nm process for Tukzilla and the CSI aka Quickpath has already been demonstrated in the latest Xeon CPUs, so the last technical hurdles have been cleared, whereas FSC haven't shown they can shrink their process or make a working four-core. So, in short - again - you just showed your lack of industry knowledge.
"....16core Rock CPU's could be out before then...." LOL! Which roadmap are you looking at, because not one analyst (Gartner, IDC, etc) thinks that. If Sun do release a Rock chip next year it will be a crippled design because they still haven't sorted the technical issues bedevilling it. And given Sun's long history of slippage to the n-th degree, Rock is much more likely to just get canned. Remember UltraSPARC V? Denial is not a river in Egypt, it's running through your head.
"Itanic 2, sunk by Rock instead of Icebergs".... I think you're much more likely to see the headline "Sun sunk by Schwartz". Just take a look at the relative market positions of HP, Intel and Sun, and the share prices for the three, and it is blatantly obvious which one is dying. Better polish up your resume and learn some Linux!
"....Lets do some link exchanging again shall we?...." What, Sun trying to talk about blades!?!?! Don't make me laugh. Sun's blade strategy is as flawed as the rest of their product lines, which is why they have less marketshare than Dell. Oh, by the way, the market leader BECAUSE THE CUSTOMERS RATE THEIR KIT THE BEST is hp, not Sun. IBM sell more blades than Sun, Dell do too (well, now they have copied the hp c-class design). And the chip that powers the most popular blade design is Xeon, not any Niagara. You seriously believe Niagara blades will rule the market? Dream on. They have no chance, which is why Sun have been forced to make Xeon x86 servers. But, seeing as you want a link, I won't go and get an hp blog link or anything that might be construed as vendor biassed, I'll just post the Gratner article here at the Reg (http://www.theregister.co.uk/2008/08/22/gartner_server_q2_2008/ ) - see the tiny little green slice compared to the big blue and red slices? Yup, Sun is the minnow, HP and IBM are the big fish. Read it and weep.
"....Like before, yes, this is a slower frequency than the latest but look at the curves HP boy, 8 threads and BOOM!! Bye bye Itanium performance...." What, Sun trying to benchmark someone else's kit? Yeah, I'm sure that was an unbiased experiment! LOL! How about another real world example, but seeing as you don't like mine I'll borrow one from AMDOCS, the guys that run just about all the telco billing systems in Europe. The AMDOCS ClarifyCRM app was originally written on Slowaris for SPARC. Nowadays it gets implemented on hp-ux on Itanium on Superdome at just about every major telco. The reasons are simple - Itanium scales better than any SPARC, with better performance, with simpler implementation and better management, and with a better return on investment. Telcos used to be Sun's happy hunting ground, now they are losing share to Itanium and Power to the point where a telco deploying any billing app on Sun is an exception. Go read the AMDOCS case studies. Face it, you ask for my love but you really need to give some love back to your customers becasue - as the market figure show - they don't love Sun anymore.
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2024
