Why is there always talk about cranking up the clock rate???
Homey hasn't played that card in years...
Software giant and server newbie Oracle and IT conglomerate and long-time Sparc partner Fujitsu said late Tuesday that they have extended their collaboration on Sparc platforms. The announcement was short on details, particularly any relating to the chips that would be used in the future Sparc Enterprise M machines. It also …
Homey hasn't played that card in years...
Anytime a vendor refuses to answer a direct question means they are hiding something
Obviously they are hurting on m-class servers and customers are questioning if they should buy into a dead end product. Either ways Fujitsu chip or SPARC CMT chip in the future m-class the current systems are end of life. I heard that directly from Oracle. I just doubt Oracle will be able to pull a rabbit out of their hat to make Oracle EE run well on a CMT system.
"The announcement was short on details, particularly any relating to the chips that would be used in the future Sparc Enterprise M machines. It also raises more questions than it answers."
BTW...I did the math on the Tukwila chip.....Mark Hurd put some serious hurtin on those poor BCS reps...can you imagine trying to sell a tukwila system that has the same per core performance and twice the licenses required?
There are three camps that run sparc. One is the ones who are running multithreaded java code and the T systems work fine great for them. The other is the fortune 100 companies that like to throw money at the problem and used to buy the SGI and Cray designed so called Sun kit. The rest are using it for security related computing and they want sparc for its unique architecture that has a habit of breaking lots of common malware techniques. They are looking for small 1RU servers that can hold cheap disks and aren't too far away from x86 stuff in performance. Oracle has been ignoring that entire class of customers but Apple's announcement about xserve implies there isn't any money in that area which is a shame since that is what built sun in the first place.
If they ditched the idea that you make java go faster by making the underlying clock speed faster then there wouldn't be a problem. In fact if they just ditched java and used something that was actually written to be parallel then they would get more bang from their buck out of the poxy sparc.
Honestly does anybody look at a UltraSparc processor these days and go "ooh cutting edge" I get more performance out of an OAMP 4 in my phone.
I knew that venus chip would be commercialized in some form, Oracle and Fujitsu were not about to let the billion odd quid the Japanese government sank into the funding for the Venus development go to waste.....that would just be silly.
If that potential roadmap turns out to be true, I have no reason to doubt it (all that much anyway....) then Oracle/Sun hardware looks to have a decent future. I look forward to the dust up between IBM and Oracle, true to old Larry's word, he is giving it a good go. Here we have two companies with great products competing fiercely, this can only be good for us, the consumer.
With Solaris 11 in prod grade not too far off, some interesting hardware developments, and of course with that DB and all that middleware and all those app's I say Oracle looks in pretty good shape.
Of course, as it's a story about Oracle/Sun, we can expect the resident militant HP fan boy to come along and start spewing his usual delusions...
Oh yes, the same old FUD "Venus is dead. SPARC is dead. ;igrate now to POWER7. And also Itanium is dead and our HP-UX servers are unstable and crashes all the time". Bull.
Well IMHO, the new M series machine won't be based upon SPARC64 processors.
If you look at the good old roadmaps from SUN, then the new M-Series servers won't be based upon the SPARC64 based machine, but rather the new 'beefier' CMT processors.
It looks like the CMT processors will branch into two different types, one with lots of cores and lot of threads, a kind of throughput computing cores, and then a more beefier one with better single threaded throughput.
If you look at this roadmap:
And compare it to the recent Oracle roadmap:
Then it actually fits with:
T-model in 2010 is Rainbow Falls based.
M-moel in 2010 is Jupiter-E based
T-model in 2011 is Yosimite falls based.
M-model in 2012 is Yellowstone falls based.
T-model in 2012/3 is Cascade falls based.
What just doesn't match is the number of sockets, but hey.. these are foils made by marketing so.
So IMHO SPARC64 is dead, and the future strategic sparc processors are the CMT.
It may well be CMT based, then again it may be SPARC 64 based. One thing is for sure is that some of that technology from Venus will be there in some form, if it wasn't, then why would Oracle bother with the tie up with Fujitsu? Fujitsu has to bring something to the table and the only thing they got is the Venus CPU architecture. I'm not saying it will be that exact Venus chip, but some of that tech will wind up in the future chip, Oracle ain't about to partner (hence share profits....) unless Fujitsu is pulling it's weight....
"....So IMHO SPARC64 is dead, and the future strategic sparc processors are the CMT...."
So in your opinion SPARC64 is dead? What if Fujitsu releases SPARC64 as Venus, and Oracle releases CMT cpus? Then your opinion is just some of the FUD I talked about "yes, SPARC64 is dead, migrate now to POWER7 or you will go bankrupt". You said earlier that Venus was dead and never was going to be released as a commodity cpu. I said something like "bull shit, we both know that Larry will decide that when he buys Sun".
Your wish, is not the same thing as when IBM executives said that AIX will be phased out in favour of Linux. Now that is outspoken from IBM executives, and not something I made up. But it is not outspoken that SPARC64 will be killed, except in the posts from IBMers. AIX will be killed. IBM will migrate to Linux. It is officially said from IBM executives. That is more credible, than when IBMers say "SPARC64 is dead".
So, AIX will be killed off by IBM. That is true. There is no evidence of SPARC64 going to die. That is just more of the IBM FUD I talked about.
This is true: Larry has said he will increase investments on Solaris and SPARC. IBM has said that AIX will be killed off.
Look, if you aren't smart enough to see that I mean that replacing SPARC64+CMT with two flavours of CMT processors is actually a good idea, then perhaps you should try to take a deep breath and stand back a bit.
And your constant gibberish about Venus is.. well at best naive. Look, Venus would be outclassed by SPARC64 VII+ on commercial workloads.
SPARC64 VII+ uses SMT where as Venus has none.
SPARC64 VII+ has x4 the L1 cache compared to Venus per core.
SPARC64 VII+ has almost 5 times the L2 cache compared to Venus per core
SPARC64 VII+ clocks in a 3 GHz Venus clocks in at 2 Ghz.
So Venus might feature 8 cores but it would never measure up against SPARC64 VII+ on commercial workloads. So... stop your dreaming.
And your ramblings about AIX is .. well just uninformed, and I think that very few people actually take your ramblings serious.
I do not think that CMT is the one and only solution. Sun was clear with that. If you suggest that CMT should replace all other cpus, I think you are wrong.
CMT has high throughput. SPARC64 has good single threaded performance. I am not convinced yet that the new hybrid CMT cpus will have both advantages, it is not clear. It must be proved. That is the reason I am convinced it is a good idea to drop everything than CMT cpus. I dont see why "SPARC64 is dead". Maybe the new hybrid CMT cpus will suck?
Regarding the SPARC64 VII+ vs Venus. Sure, you say that Venus sucks in comparison. But Venus cpu reaches 128GFlops, whereas the SPARC64 VII+ cpu reaches something like 50GFlops. So, I am not convinced that Venus sucks in comparison, as you claim. Or maybe I might not be "smart enough" to see that Venus sucks.
Regarding my "ramblings about AIX" and that I am "uninformed":
"Steve Mills, senior vice president of IBM's Software Group, told CNET News.com at last week's LinuxWorld trade show. Asked whether IBM's eventual goal is to replace AIX with Linux, Steve Mills responded, "It's fairly obvious we're fine with that idea...It's the logical successor."
Steve Mill's view is really on a multidecade time frame," said Nick Bowen, vice president of Unix and Intel server software development at IBM."
IBM is killing AIX. It will happen. Not today, but in some time, as Nick Bowen says. But 10 years pass by fast. I am not "uninformed" on this, nor do I "ramble". It is true. AIX is going to die. By IBM's hand. It is not FUD. It comes directly from IBM. I suggest you better start to learn Linux.
You forgot to read what I wrote, commercial workloads... Sure Venus is better for floating point math, that was what it was made for. Hence it's commercial throughput is not as good as existing SPARC64 processors, which is why i said that arguing that Oracle would release a new fantastic Venus based chip is.. well a dream.
And your AIX story is just .... well mud throwing. It's from a different time before SCO with the help of SUN and microsoft tried to take out LINUX, a battle that SCO is dragging and dragging and dragging..
And sure a merger of LINUX and AIX is IMHO still a good idea.. but not going to happen. And looking at the IBM track record of keeping OS'es alive then we'll still run AIX in 2040.
I am not convinced that Venus is only good at floating point math, and sucks at everything else. I mean, POWER7 is used in supercomputers with good results. And we all also know that POWER7 is a good cpu for commercial workloads. That is not mutually exclusive. A new high end cpu is typically good at several things. Venus and POWER7 have more things in common, than say Venus and Niagara. I expect Venus be quite POWER7 like in performance. Venus and POWER7 are traditionally designed cpus, with 8-core with few threads. Large cache. etc etc. Niagara is something else, a unique and different design that does not suffer from cache misses. That is my reason to believe that Venus will be quite POWER7-esque in performance. Venus will be a good all-round cpu.
Regarding that AIX story, no, it is not "mud throwing". I have not made that up, nor have I cherry picked only some comments. Everything is there for you to read. IBM executives say that the long term IBM strategy is to phase out AIX and shift R&D to Linux. As I said earlier, x86 will soon be faster than POWER. Then you can run Linux on x86, both faster and cheaper than AIX on POWER. IBM executives foresee this. They know x86 will beat POWER very soon in terms of performance. Then there are no reasons to buy AIX.
AIX will have less and less R&D and eventually it will only be supported but not further developed. IBM will surely support AIX some decade more, but no new development. And no new cool tech will come. Everything will be Linux focused. IBM is investing heavily in Linux, even their cash-cow important mainframe business runs Linux. Linux is important to IBM even today.
As I said, the trend is clear. I see it, you see it, the IBM executive see it. Linux grows and gets more capable. x86 becomes faster and faster. And cheaper.
Even when I show links where IBM executives say AIX will be killed, I am FUDing and throwing mud, according to you. How much more credible can anyone be? Even if IBMs executives called you and repeated everything, you would deny that. But truth to be told: AIX has no future. Learn Linux instead.
With regards to Venus, you are absolutely wrong. The stuff you write is picked out of the blue, there is no truth to any of your statements. Sorry.
If you want to convince anyone, you should try to provide some documentation.
And with regards to AIX, your indsight is amazing. It is quite stunning what a Solaris/SPARC fanboi, can deduce with the of old quotes of the internet.
How about you provide some documentation to your claims:
a) Venus sucks
b) AIX is not going to be killed
At least I have shown some credible links from IBM executives. You have not shown any links at all.
"...With regards to Venus, you are absolutely wrong. The stuff you write is picked out of the blue, there is no truth to any of your statements. Sorry...." Dont you know that SPARC and POWER have always been considered as similar? Both are RISC, few cores, strong threaded performance, large cache, etc. So I would like you to show some documentation that disproves common knowledge. Or can you not? But you require that I prove things, but you need not to?
Once again, I am quite disappointed in TPM's arguments, analysis and misguidance regarding Oracles SPARC roadmap. First of all, Mr TPM, why aren't you just admitting that Oracles new SPARC roadmap is quite a milestone in the history of CPU and systems development being made by Oracle? Oracles reputation, and of course LJE's reputation, making this public disclosure on future product plans is quite aggressive to say the least. Customers can now use this roadmap for planning purposes and clearly hold this against Oracle should they not deliver to plan. There is an incredible amount of detail in the roadmap including performance gain expectations that neither Intel, IBM or even AMD have ever disclosed PUBLICLY. You can look at IBM's latest Power roadmap which is all about history. There no details about futures of Power beyond a Power8 placeholder. Same for Intel with Itanium. Sure, all CPU vendors have slipped on delivery dates and even made changes to CPU plans, but they never disclosed the details to hold it against them- so would you think that Oracle can afford to publish such amount of details without a certain level of certainty? So hold onto Oracles SPARC roadmap and over time, compare to whats released and then, comment on whether they’ve delivered to plan or not. So far, it looks like Oracle has delivered two milestones already on the roadmap (SPARC T3 and SPARC64VII+), on time and at performance specified. I for one, am looking forward to seeing the SPARC advancements, which look to be very competitive and take Oracle to new heights.
Aw, that was just so cute and naive, I couldn't resist the temptaion to do a little troll-bashing!
"......Oracles reputation, and of course LJE's reputation, making this public disclosure on future product plans is quite aggressive to say the least....." What reputation? You are right that this is about reputation, but the problem for Larry is us customers perceive Oracle as having a bad server rep. Oracle has zero previous server building experience, they are just a software company, all they did was inherit the big pile of fail from Sun's server bizz (and lost a large chunk of the skilled engineers in the process). That came with a history of broken Sun roadmap promises (and Sun rubbishing SPARC64 when they thought they had Rock coming), and many said that Larry needed to stand up on day one of the Sun buy and give a firm, believable roadmap to stand any chance of stemming the defection rate of those old and let-down Sun customers. He didn't, he dithered and waffled about Niagara which was already too weak for the enterprise, hence the need now to try and rebuild customer confidence in Oracle's enterprise server offerings. Larry really needs to have a new top-end offering to fill the hole left by the death of Rock as the CMT offerings have not been able to provide the type of server needed. He had four options - use Power; use Itanium; make a deal with Fudgeitso to extend the very dated SPARC64 design one more time; or just abandon all those Sun shops running old UltraSPARC and M-series to IBM and hp. Given his ego (and that the Japs have paid for most of the new SPARC64 development), it was no surprise that Larry is trying to push the SPARC64 option. Problem is it has taken soooooo long, probably because Fudgeitso weren't keen, and many of the old Sun base have started migrating off SPARC already.
The problem is, even if the customers do decide to try Slowaris-SPARC64 one more time, what's next? A painful shift to a CMT design that has - so far - proven unsuitable to the enterprise apps they run? What if Oracle can't make the CMT option perform to the point where the CMT has some single-threaded performance? For many customers the simpler and safer route will be a switch to proven Power or Itanium (or Linux or Slowaris on Xeon) now.
All this has been predicted, discussed and rubbished by Sunshiners like yourself many times, and just as many times you all said "Niagara is sooooo good we won't need anything else", so you've just all been proven wrong yet again. If CMT was the answer, then Larry wouldn't need another extension to the SPARC64. The good news for you is that Larry has finally put some meat to the plan, but it may be too late. I said previously that the recession gave Larry some breathing space whilst customers delayed refreshing old enterprise kit, but that time is gone and hp and IBM are ramping up their latest enterprise server sales. TBH, IBM can probably afford to be a bit vague on their roadmaps for Power8 as they seem to have more standing with us customers, and Intel and hp have kept plugging the Itanium option many, many years after you Sunshiners repeatedly told us Itanium was dead (how many times have you been proven wrong on that alone!). Larry is the one with a reputation problem, and this deal with Fudgeitso may be too little, too late, to swing the buyers back behind the old Slowaris-SPARC combo again.
We understand that you hate various ethnicities, foreign companies, and their products - but can you please tone down the racism?
"....All this has been predicted, discussed and rubbished by Sunshiners like yourself many times, and just as many times you all said "Niagara is sooooo good we won't need anything else", so you've just all been proven wrong yet again...."
Sun has never claimed Niagara is a general all purpose cpu. Sun was always clear that single threaded performance is bad and never tried to hide it. Niagara is a high throughput cpu, Sun has said that.
So why do you claim that Sunshiners have said "we dont need anything else than Niagara"? That is not correct, and you know that. Sun,nor the Sun supporters, nor Oracle has said something like what you claim. Nobody has said that, except you.
Basically agree totally with the post except for the part of Itanium not being pathetic and dead as well (sadly at least SPARC actually had its heyday long ago, Itanium was a turd on arrival). SPARC has sucked for a very long time but at least at one time it was pretty common to see a few in different shops. Power I also see occasionally but have yet to see Itanium in any shops.
Dude you have a problem....seriously, why so aggressive all the time? I really do think you need a visit to the doc's mate, that obsession you have with slagging off anything and anyone that isn't HP is not normal and cannot be healthy.
I bounce around the city a fair bit on contracts, the Unix world is a fairly small one, with all honesty, I hope to god I never have to meet you...
"....Many years after you Sunshiners repeatedly told us Itanium was dead (how many times have you been proven wrong on that alone!)...."
Could you please quote where Sun supporters say that Itanium is dead? Ive never seen it. As far as I know, it is the IBMers that say things die: "SPARC is dead", "Solaris is dead" and of course, "Itanium is dead". Maybe you mistaken Sun supporters with IBM supporters? I mean, you read all the time that "XXX is dead, migrate to POWER now!". But you never see claims as "HP-UX is dead, migrate to SPARC now!". It is always "... migrate to POWER now!" - typical IBM trash talk.
Here are some examples of when IBM says "XXX will die now, migrate to POWER"
"The end of life for Itanium will occur in the next five years," IBM VP Scott Handy told us, during an interview here in Austin, Texas. "(HP) will have to announce some kind of transition. IBM bashing Itanium and HP hardly stands as a novel concept, although Handy's remarks come off as the most aggressive from Big Blue in quite some time. "We can beat HP or Sun with our previous chip the Power5+," he said.
"[Sun] are already signaling to customers the beginning of the end," Handy said. "Rock (Sun's next upcoming UltraSPARC chip family) is their last-ditch effort, and no matter what their volume is it's already too small to afford what comes after the first Rock chip."
Typical IBM trash talk.
Where is this Sun FUD you talk about? Can you link to it? Maybe you mistaken it with IBM FUD. According to wikipedia article on FUD, it was IBM that started to use FUD on a wider scale. IBM is famous for that.
And, you also say that "Sunshiners claim Niagara is the only cpu that is needed" - no one has said that. Can you quote this, or are you imagining this as well?
"....but can you please tone down the racism?" OK, I'm guessing that was just a depserate diversionary tactic, but what racism or ethnic slurs are you referring to?
"......why so aggressive....." Apologies if you mistake humour for aggression, but I would have thought people laughing at you would be a common occurence for you. But then it is you that immediately starts suggesting I need medical treatment just because I disagree with your faith, can I suggest a case of pot-meet-kettle?
".....I hope to god I never have to meet you..." If you really do "bounce around the city" then you probably already have. I've enjoyed many years of baiting Sunshiners in the UK, many parts of Continental Europe, and even as far afield as the States. Don't worry, I'm sure the rapidly shrinking Slowaris market means there's not much chance of you suffering my "aggression" for long. I would suggest you learn Linux - fast!
As usual with the Sunshiners, as soon as you try to suggest an alternative to their cherished beliefs, they stop all pretence at technical argument and quickly descend to petty insults. Please, try much harder. Would you like to make a technical response based on industry realities, maybe? For example, care to explain how you think that Venus SPARC64 VIIIfx, a one-task HPC core design, can be adapted to work as a general CPU without seriously lagging Pee7 and Tukzilla?
"Apologies if you mistake humour for aggression"
Right barrel of laughs you are, I'm sure everyone agrees. A bit sadistic like Frankie Boyle, only minus the funny bits...
".....I hope to god I never have to meet you..." If you really do "bounce around the city" then you probably already have. I've enjoyed many years of baiting Sunshiners in the UK, many parts of Continental Europe, and even as far afield as the States.
Woop-de fecking do, don't you work for some company called Ingram? In the shitehole of a place called Reading? I only do the City contract's you see, have been for 7 years, and will continue to cream the "Slowaris" money (Red Hat too these days) banks dish out for years to come. Never met you, likely never will.
"I would suggest you learn Linux - fast!"
And what makes you think I'm not already a Dab hand with Red Hat, and the various Debian's going back years? I know Solaris better than most, my Red Hat and AIX is as good as most, my HP-PHUX is non existent, wanna know why? In the banking sector, no one fecking use's it, that's why....
"....Right barrel of laughs you are...." Well, humour is subjective and also relative to your emotional state, and if you're overwhelmed with the Sunshine it's not surprising you're feeling a bit sensitive after the Sunset.
".....don't you work for some company called Ingram...." LOL, guess again! According to the posters on these forums alone, I work for hp and/or IBM, Oracle(!), Microsoft, RIM, BT, the Gubbermint, and the Greater London Authority! I've also been accused several times of being a Yank! Phew, I'm tired out by all that job-hopping, let alone the trans-Atlantic flights! I can't actually find a company called Ingram in Reading (did you by chance mean Clifton Ingram Solicitors, not heard if they have an IT department?). Whilst it is fun to watch you Sunshiners doing your e-stalking, before you start sending hatemail to some poor so-and-so you found on Facebook, please remember I post under a psedonym because of droollers like you.
"....Red Hat too these days...." Ah, a Sunshiner that at least saw the writing on the wall, even if they're not happy to admit it. After all, if your Slowaris contracting was so busy you wouldn't have bothered with Red Hat, Debian (in the City?) and AIX.
"....In the banking sector, no one fecking use's it....." Well, seeing as I personally know that's not true (not wanting to breach anyone's NDAs, but a friend tells me there's also plenty of hp-ux in the highstreet banks), that just goes to show you probably don't work as much in the City as you claim.
So, we've exposed the limits of your experience, would you like to expose the limits of your market knowledge with some equally revealing insights into the possibilities of success for Oracle's proposed servers? How about a brief on how you think Oracle will manage to maintain customer interest between now and the launch of the TNG M-series, when the current M-series are hampered by outdated tech like DDR2 memory and 10K internal drives (the competition are enjoying DDR3 and 15Ks)?
Dear Sunshiners. On second thoughts, I have decided to put my hand up and say I am that Matt Bryant working at Clifton Ingram Solicitors, County House, 17 Friar Street, Reading RG1 1DB, emails to firstname.lastname@example.org. Please, feel free to forward me all your carefully crafted justifications for your support for Snoreacle. You may even like to call in some time and persuade me of your technical genius. After all, I'm sure you're all too professional to use that info for e-stalking, and it's only a solicitors' office, what could go wrong?
(Hey, if they fell for the Sunshine there's a chance they'll fall for that too!)
/gets popcorn in and waits for the show to start..... where's my "sweet'n'innocent" icon?
X86/64 economics and wider scale virtualization adoption will be the end game for all other CPU product (not involving mobile that is).
Anything else is just wasting time, or covering your own butt until you retire. Let's make this really complicated design and arch, that will keep me employed for a while.
Speaking from within the borg....
... Nice work!
Where's that Larry icon I ask for long ago?
Anybody else skip most of article just to come to the comments to read Matty's rant. Still have to say SPARC is garbage has been since 2000 and every SUN shop I have been in, the developers loathe having to work on the SPARC boxes due to the sluggishness. Quite a bit of work can be found migrating apps from SPARC to x86-64 as nobody in their right mind or still having a job gave the go ahead to deploy any business critical apps on SPARC in about the last five years or so.
Bah posted literally one minute before I wrote this so bitten by moderator delay once again. Still have good rips on the garbage that SPARC is so won't withdrawl.
'Nuff said. Hey, I have to do some work every now and again!
Matt Bryant was wrong about dead architectures, let us count the ways!!!
Matt Bryant ~~~ Intel and hp have kept plugging the Itanium option many, many years after you Sunshiners repeatedly told us Itanium was dead (how many times have you been proven wrong on that alone!)
Remove the beam from thine own eye, hypocrite
Matt wrongly predicted ~~~ SPARC is dead
http://forums.theregister.co.uk/post/163212 - 02/2008
http://forums.theregister.co.uk/post/420488 - 02/2009
http://forums.theregister.co.uk/post/458903 - 03/2009
http://forums.theregister.co.uk/post/475800 - 04/2009
http://forums.theregister.co.uk/post/482308 - 04/2009
http://forums.theregister.co.uk/post/503118 - 05/2009
http://forums.theregister.co.uk/post/503434 - 05/2009
http://forums.theregister.co.uk/post/652492 - 12/2009
http://forums.theregister.co.uk/post/687197 - 02/2010
Matt Bryant wrong again with ~~~ SPARC bizz is dead
http://forums.theregister.co.uk/post/244292 - 06/2008
Wrongly suggested ~~~ Niagara is dead in anything other than the webserving niche
http://forums.theregister.co.uk/post/437736 - 02/2009
Matt wrongly said ~~~ SPARC is as good as dead
http://forums.theregister.co.uk/post/499533 - 05/2009
Matt wrongly stated Sun was not prepping processors in the 8 &16 core cpu's ~~~ for sure
http://forums.theregister.co.uk/post/503118 - 05/2009
Matt wrong again with ~~~ SPARC, which is dead
http://forums.theregister.co.uk/post/751048 - 04/2010
If there is ANYTHING to be SURE ABOUT, when Matt Bryant makes a prediction about the future in technology, it will be WRONG, based upon his poor track record.
!!! EPIC FAIL !!!
P.S. Matt Bryant is not the only individual with the poor track record - Allison Park also wrongly said ~~~ SPARC64 is dead
http://forums.theregister.co.uk/post/693070 - 12/2010
Whilst it is amusing to point out that you have simply regurgitated a number of posts, you haven't actually proven the "error" in any of them, you have missed the most obvious fact that Sun did fail with their SPARC plans, and that only Oracle's money has allowed the disaster to roll on a bit longer. Please try and deny that whole Sunset thing happened, just for laughs!
".....Matt wrongly predicted ~~~ SPARC is dead...." I suggest you go read the quotes you linked to, you may notice a few chickens coming home to roost. As I predicted, Rock stalled and was killed and Sun had to switch to Fudgeitso's SPARC64 for their top-end servers. Sun sales had to make the embarrassing switch from rubbishing SPARC64 and urging customers to wait for Rock to instead pushing SPARC64. Also as predicted, Niagara was useless at replacing many of the low-end UltraSPARC servers in the market, to the point where Sun were forced to bring out the one-socket, SPARC64-powered M3000. Please try and deny the original Sun plan was that Niagara would face Xeon in the webserving heartland that used to make up 80+% of Sun's Slowaris base, whilst Rock was supposed to slug it out with Itanium and Power in the enterprise arena. Niagara hasn't moved out of the webserving niche because the single-threaded perfromance is still pants, and most of Oracle's existing Slowaris customers are still using apps that require good single-threaded performance. Nothing illustrates the unsuitability of the CMT design for the current industry apps like the fact that Oracle still needs Fudgeitso to produce another generation of SPARC64s.
Matt, you spelled Solaris, and various other words incorrectly again. Please use spell check, to at least appear to be credible.
Matt Bryant posts, "Oracle has zero previous server building experience, they are just a software company"
It seems Oracle has released several refreshed several lines of their own servers since the Sun acquisition, and after dumping former HP boxes in some integrated system lines.
The Oracle T3 platform over doubles performance over Sun T2 platforms... 400% throughput improvement comes at a cost uplift, but 100% performance increase is a actually a discount from the old platforms.
Matt Bryant posts, "Larry really needs to have a new top-end offering to fill the hole left by the death of Rock"
SPARC64 M systems provided Oracle a "top-end offering"... suggesting otherwise logically suggests HP has no "top-end offering", because HP stopped making systems with Alpha processors. It has been this way for years.
The T4, which is already in the lab, to be released later this year, offers aggregate throughput boost and substantial strand performance, placing it squarely between the former CoolThreads systems and M systems.
"SPARC64 M systems provided Oracle a "top-end offering"."
These top end systems comes with an almost decade old memory technology. When will Oracle finally equip them with DDR3 memory?
I see Oracle spec sheets tries to hide this embarrassing fact by not telling what type of memory the M-servers can be fitted with.
"The Oracle T3 platform over doubles performance over Sun T2 platforms... 400% throughput improvement comes at a cost uplift, but 100% performance increase is a actually a discount from the old platforms."
I guess you mean "The Oracle T3 platform over doubles the price/performance..." right :)=
With regards to T4 (Yosemity falls), then I think you might be wrong, I don't think it is a sure thing that the T4 will offer an aggregated throughput boost.
Now the clock frequency will be 1,5 times faster.
It will have half the number of cores.
The single thread throughput will be up to 3 times faster, which dictates a factor of 2 from something other than clock.
Now that will give the chip a 'best case' throughput of clock increase x other increase / factor of fewer cores = 1,5 x 2 /2= 1.5 times the throughput. But this dictates that the x2 'other increase' is attainable for all cores at the same time. I don't think that will be the case.
But lets see, what actually happens.
Now personally I think it's a great move, if Oracle Fujitsu kind of agree to merge SPARC64 and the CMT processor lines. IMHO it's terrible to have several processor lines running at the same time.
Specially when those processor lines are actually overlapping in products. For example if you look at the tuning settings on the more or less straight forward specintrate2006 benchmark then for the T3-4 and the M8000 the compiler settings are actually quite different, if you look at the compiler settings, and it's also true for the base settings. And these two machines both have 64 cores and are within the same performance range.
Which basically means that if you have to compile code that have to run as good as possible on both platforms, you have to aim somewhat in the middle. That is not an optimal situation. So if Oracle and Fujitsu somehow agrees on merging development teams and start to use one platform, then I think it would be a advantage for them in the long run.
Looks like Novatose has forgotten about the Sunset too! In case he's forgotten, he got the "Novatose" moniker for his continual hyping of the long-anticipated Rock server lines, even after it became obvious to the rest of us that Rock was a zombie just waiting for a mercy killing.
"....you spelled Solaris, and various other words incorrectly again....." As I have previously reminded you many times, the moniker "Slowaris" was given to Solaris by Sun's own customers due to our unhappiness with SPARC-Solaris's performance. Pretend all you like, that's a simple fact.
"....at least appear to be credible...." Given your previous and hilarious outbursts of Sunshine (e.g., "Rock will not be killed", "Sun is not up for sale"), I'm sure there is no way I can appear credible to such a self-certified Sunshiner! You carry on keeping The Faith, don't let that little old Sunset event or the loss of Prophet Ponytail deflect you, just don't expect the rest of us to suffer from such delusions.
"....It seems Oracle has released several refreshed several lines of their own servers since the Sun acquisition....." Hmmmm, you mentioned a spell-checker, ever think of using the grammar-checker? All Oracle have done is slap new badges on old Sun designs that were already available or already in the works. Oracle has released no server truly of Oracle's own making yet, and it looks like the next gen top-end servers are just going to be more badged Fudgeitso kit.
"....after dumping former HP boxes in some integrated system lines...." Well, Larry did inherit a whole stack of servers no-one wanted to buy, I'm not surprised he'd want to burn through that old Sun stock, especially after hp had done all the tricky engineering and integration for him. It obviously didn't register with you that hp shrugged and carried on being the leading server vendor, whilst Snoreacle is still third tier at best.
".......The Oracle T3 platform over doubles performance over Sun T2 platforms...." Just not in the way customers want. Stop talking the "throughput" drivel, that only matters to webserving, it's irrellevant to the single-threaded apps most customers want to run. A three-year old Xeon server can thrash a T3 server with real applications and real data.
".....suggesting otherwise logically suggests HP has no "top-end offering", because HP stopped making systems with Alpha processors...." Oh dear, just showing your lack of knowledge again! You forgot PA-RISC, which was caning UltraSPANKed for years before Sun finally went to SPARC64. It had already been agreed between Compaq and Intel that Itanium would replace Alpha before hp bought Compaq. Unlike Sun, Compaq and hp saw the fact that traditional RISC CPUs were reaching their design limits and both moved on before they destroyed themselves. Sun presisted with UltraSPARC, failed with Rock, stumbled with Niagara, and saw their company value crash from a 2000 peak market cap of $200bn to less than $4bn. If Oracle hadn't saved them (after IBM and hp both turned down the opportunity), then that would have been the end of SPARC right then. Even then, even Larry admitted his original intent was to buy just Sun's software business but he got stuck with the hardware failure as well.
".....The T4, which is already in the lab...." So, more unproven vapourware arguments. Hey, didn't the Sunshiners assure us Rock was "taped out" right up until it got killed? And if all T4 does is place itself "between the former CoolThreads systems and M systems" then I'm not impressed, it will be slower than current Power or Itanium and probably x64 with the apps us customers actually might want to run on it. It may be finally suitable for replacing the old UltarSPARC IIIi kit still out there on a like-for-like basis, but seeing as I can already consolidate old UltraSPARC onto Lintel blades, at a better than one-to-one ratio and for a lot less money, I'm just not impressed.
'Oracle has zero previous server building experience, they are just a software company'
Hang on... wasn't HP just a printer company until it bough Compaq?
Just as HP's purchase of Compaq shows, you can go far reaching into new territories and make a real success of it. Given his Ahab-like desire to see IBM on a spike and everyone else smashed to bits at the roadside he *might* actually do it.
"......wasn't HP just a printer company until it bough Compaq?...." I suggest you remove the Sunshiner Blinkers (TM) and read a little industry history. There were server and storage products from hp long before the Compaq buy, using Intel's and AMD's x86 chips and hp's own PA-RISC CPUs. They also had a storage line before Sun, management software (in fact, Sun had to resell hp Openview as they didn't have their own management software), PCs, networking products, and of course the printers biz (which continues to make more profit in a quarter than Snoreacle makes from all server products in a year!).
But, this forum is about the refresh of Oracle's server roadmap, do you have anything even mildly related and vaguely technical to post? Go on, have a try, you may surprise yourself.
Hi have to agree with Matt on this one.
HP has a long history of IT technology innovations. The explosion of printer revenue came from IBM's spin-off of printers and creation of Lexmark. But today HP has transformed into a balanced company with services and hardware. We still use HP for x86 and were HP before the compaq acquisition. We have looked at moving but never justified the change.
There have been stumbles along the way. 1) forced migration from pa-risc to Itanic 2) CEO's getting fired
If they get a software business they will prosper but right now all I see is partnering with Ballmer and pissing off Larry.
As far as the sunshiners......face it scott screwed it up, jonny pissed on it and all that is left is Oracle's mean spirited extortion of Sun customers. The basturds came in last month and found some failover serves which were "not licensed correctly" and tried to get us to buy Exadata so we would not get charged retroactively. We called their bluff
".....CEO's getting fired....." I've often wondered if hp's exec hiring scheme wasn't an attempt to branch out into comedy! Apatheticker hasn't really dismissed that belief yet.
..we have to remember that the amount of Oracle Friends is actually shrinking quickly. I don't really think that the new HP CEO Apotheker (which btw means pharmacist in Danish) have much love for Oracle. And just before he joined HP they bought Stratavia and recently they bought Vertica Systems, so they aren't just buying up software companies, but also software companies that are entrenching on Oracle Business.
And the rather strange upping of the license cost of Oracle software on Itanium 93XX processors haven't helped either.
".....strange upping of the license cost of Oracle software....." It will be interesting to see what Larry does when the octo-core Poulsen Itaniums hit town.
Biting the hand that feeds IT © 1998–2017