Two weeks ago, when Intel once again delayed its quad-core "Tukwila" Itanium processors until early 2010, the company did not give much insight into what the delay was about. It also said nothing about how the continuing delays with Tukwila would affect future Itanium processor rollouts. Like many of you, I have been trying to …
"Only the OEMs know for sure."
"Only the OEMs know for sure." ?
I don't think so.
You might have meant "Only HP know for sure" since they're the sole committed player in what's left of the Itanium game. But you can be reasonably sure that even HP management and HP customers no longer believe Intel's promised delivery dates for Itanium chips.
That leaves HP's Itanium-only HP/UX, Nonstop, and VMS customers with a bit of a problem if they want a plan that'll last more than a year or three, and with the amounts of money these folks spend, that'll be most of the big ones.
As for the rest of the server market, the vast majority of it, the lucky/sensible folks who have a hardware-independent choice of OS:
The future's bright. The future's... AMD64.
Intel is simply trying to kill Itanium by attrition.
"Sure, it will be out any day now. But while your waiting, why not examine our full range of Nehalem Xeons?"
HP is the real driving force behind Itanium and Intel just dances the dance to keep a major OEM happy. Itanium's death was sounded by x86-64 a long time ago.
Funny, this seems like the IBM/Apple PowerPC spat a few years ago doesn't it?
Power and SPARC both have the ability to snoop into other CPU's cache. I wouldn't doubt if Itanium already had this capability as well. No, I think the delay is that Tukwila is embarrassingly slow and Intel is tweaking the compilers.
Usually the vendors release a chip that gives them good performance and then they release a later version of the chip that has some simple fixes and tweaks, but not much performance improvement; they then tweak the compilers to give a performance increase. With Intel tweaking the compilers up front, there will be no mid-life performance boost from compiler tweaking. Tukwila is dead from the git-go.
Well, where's Matt?
Itanium is dead. Nehalem EX will outperform at half price.
Pls, Matt comments...
Re: Well, where's Matt?
Matt has no balls. He never show's up when he is proven wrong. Of course, if that were entirely true, he would never show up, as he's proven wrong just about every time he makes a comment here.
to all you armchair analysts...
go look at some usenet archives from 10-20 years ago - you'll find plenty of similar points of view replacing "itanium" with "mainframe" - mainframe was dead, had no future etc. etc.
now go look see how much money IBM still makes from mainframes...
the thing is most folks get so wrapped up in the "latest & greatest" mindset that x86 and M$ has foisted on us, they forget that most large enterprises can't and don't want to move at that speed.
maybe in your "all x86" 30-server machine rooms this might seem like reality, but step into any large enterprise data centre and you'll see a different story - despite how many consolidation and migration exercises they run, that legacy kit never really seems to go away.
so while there's money to be made, I'm sure HP/Intel will carry on, in the same way IBM carry on with Power and Oracle claim they will carry on with SPARC.
Itanium will lead a happy (if unexciting to the x86 gang) life in the datacentre for a good while yet
As for the article, well TPM as far as I could see it was all total conjecture, who knows if the reason Intel gave is correct or not, does it matter? It won't change the fact that the products delayed a little further and that HP is probably p*ssed about it. Articles bashing Intel on Itanium are ten-a-penny on this site... how about a new target for a change - maybe an article on what IBM will do with its loss-making chip division?
RE: Well, where's Matt?
Sorry, I was actually waiting for a Sunshiner with a comment that actually contaned some logical argument before posting a reply, but it looks like I'd be waiting a long time. Besides, Sun is dead so not much fun in pointing out their folly to the Sunshiners, I suppose I'll have to switch to baiting the AIX crowd soon.
Let's deal with the "hp is the only vendor wanting Itanium becasue it is totally reliant on Itanium" bit first. Posters using that "logic" manage to conveniently ignore the simple fact that hp is also the leading x64 vendor and Intel's and AMD's largest x64 customer. If hp just wanted to sell x64 then they'd be happy to let Itanium die and wouldn't be pushing Intel so hard. The vast majority of those Linux and Windows boxen that have been replacing SPARC Slowaris servers for years have been hp ProLiant systems. And now that Sun is dead and their customers faced with migrating to another OS, hp is perfectly placed to plunder those orphan Sun accounts, because, unlike Sun, hp engaged rather than opposed the Linux community and Microsoft. But it is not a one-punch strategy, hp also needs Itanium to squeeze the RISC base from above, including AIX Power, whilst ProLiant eats it from below. Without that pincer move, Slowaris refugees could move off SPARC and upwards to Power or mainframe, but Integrity gives both the performance and pricepoint to offer a superior deal. Throw in the easy transition from Slowaris to hp-ux, especially with the porting programs that hp run, and you see how hp is well set to eat up those old Slowaris shops. And seeing as those Slowaris shops are the targets likely to generate the largest areas of growth for hp-ux, Linux and AIX in the next few years, it is no surprise hp and IBM are gearing up to fight over them.
So, will being stuck with the current Integrity servers for another year hurt hp in that battle? In a way, yes, because customers have been led to expect and have planned for quad-cores. To avoid customer disappointment I expect there to be a few more points off deals to convince some customers to take the current servers instead (well, that's what I'll be beating our hp salesgrunt up with anyway). Will it hurt hp because Integrity will somehow be behind in performance? The answer there is probably not. SPARC hasn't managed to match Itanium for years and is now zombified. Rock, even if it does escape Larry's obsession with rehashing the network computer, is going to be comprehensively outperformed by Nehalem and the current Itaniums, and Niagara is struggling to get out of its webserving niche before the boys at Oracle realise just how limited it is. AIX is still waiting on Power7 as we have now seen Power6+ as such a non-event that IBM didn't even make a noise when they slipped it into their range. IBM's gamble on extreme clock speeds hasn't worked out, it is still the surrounding architecture that keeps the cores spinning that is vital, and hp seems able to do that well enough now to match Power6+. Unless IBM manage to pull Power7 forward and also fit it with a radically better surrounding architecture, Intel have time to tune Tukzilla to meet and beat Power7. Then there are Kitson and Poulsen to come, and what does IBM have planned for after Power7?
So are Nehalem and Istanbul the big threats to current Integrity? Yes, just as Xeon and Opteron have been to RISC for years. But according to all the Sunshiners, quad-core x64 was supposed to have killed Itanium by several years ago, but the reality is Itanium (especially in Integrity and with hp-ux) still does some jobs that x64 can't and still does a lot of jobs better than x64. There are even cases where Itanium with Windows beats Xeon and Windows, especially large M$ SQL instances. And it still will even with eight-core x64 CPUs are available. There are plenty of heavy-threaded apps out there that require the grunt of Itanium for best performance and hp-ux for superior RAS and scaling.
And in a way Nehalem is Itanium's best allie, as they allow hp to use the economies of scale of the ProLiant bizz to benefit Integrity as the two ranges now share more and more parts, much more than i/pSeries and xSeries or M-series and Galaxy (just mentioned the Sun kit for the humour value). And tehn there are the continuing worries about IBM's commitment to x64 - will they sell the xSeries bizz to Lenovo like they did the PC bizz? Every account hp gets ProLiant into makes it easier to push Integrity into as they share the same comprehensive centralised management tools and support, and hp can deliver the whole deal with better storage options. There are even hp Integrity blades and NonStop blades that fit into the ProLiant blade chassis - yes, that hp blade range being the dominant blade vendor offering too. So Nehalem and Istanbul will actually help Itanium as far as hp are concerned.
In fact, if we want to talk about reliance on a single CPU design and any subsequent vulnerability, then IBM should be the target. Sun has demonstarted the folly of relying on one range - UltraSPARC - to keep the revenue rolling in. After all, IBM's revenue stream is much more dependent on Power than hp's is on Itanium. The vast majority, I think it is 60+%, is tied to Power. All those mainframe sales, services and licensing streams are largely tied to Power - what happens if Power7 slips some more? And yes, IBM trolls, Power has been late before, simply moving the deadline is slippage, it's not delivering on time. With the majority of hp's revenue streams related to x64, it is sitting pretty with Nehalem and Istanbul, and Itanium is the bonus that allows hp to own the high-end and squeeze AIX in between and attack upwards at the mainframe base. A slip of another year on Tukzilla isn't a massive problem for hp, but a slip of another year on Power7 could see IBM taking a big hit in revenue. But then I wouldn't expect TPM to highlight that.
/going to be so disappointing replacing the Sunshiners, the AIX boys are so grey and boring, they just don't froth and rant like the Slowaris fanbois. Ah well, SP&L whilst I can!
Re: RE: Well, where's Matt?
Once again, Matt is trying to obfuscate the article by attacking Sun and Sun users and now unsurprisingly IBM. No real comment on the article though. Come on Matt. What's your take on the fact that Itanium is pushing out further and further for no other reason than it's performance sucks. You have all this internal information from Intel and HP that you are so blessed with because they "trust" you. Come on what's really up?
Explain to us why "A slip of another year on Tukzilla isn't a massive problem for hp, but a slip of another year on Power7 could see IBM taking a big hit in revenue." This seems to be pure bluster. IBM is the number one server vendor again, which implies that HP is losing share. How does that show that HP can stand another year of selling old and dying Itanic? Gartner and IDC both say that Superdome _was_ only growing at the expense of EOL HP boxen, so again, how is HP going to survive better than IBM
with another Itanium delay?
Your nonsense and FUD just proves further that you must really work for HP, no matter what you say to the contrary.
RE: Re: RE: Well, where's Matt?
"Once again, Matt is trying to obfuscate the article by attacking Sun and Sun users and now unsurprisingly IBM....." And why not? I merely highlighted the fact that the current crop of Itaniums are doing fine, and the folly of IBM having so much tied up in one CPU range when that is what arguably killed Sun. Care to contest either? I doubt it.
"....What's your take on the fact that Itanium is pushing out further and further for no other reason than it's performance sucks....." So you have perfromance figures then? You have any proof to your conjecture? No, none at all, just like the majority of the article. When will you Sunshiners start to realise just becasue you fantasise about something it doesn't make it true?
".....This seems to be pure bluster....." So you don't think it would be a serious issue for IBM if Power7 slips any later, especially when 60+% of the IBM bizz revolves around Power? I'm betting you're not in managment, unless that's Sun management.
"....How does that show that HP can stand another year of selling old and dying Itanic?...." Well, seeing as hp make a profit from Integrity whilst IBM are losing money on their chip business, and that sales for Integrity are not just holding up but increasing, it would seem that hp don't have as much to worry about as you wishfully rant.
"....Your nonsense and FUD just proves further that you must really work for HP, no matter what you say to the contrary." Your continual insistance that I must work for hp is just illustrative of your inability to grasp the fact that customers don't want the Sunshine you peddle. Just because I don't agree with your Sun FUD doesn't mean I work for another vendor. Wake up and smell the Java - Sun is dead. Just for you Sunshiners, I'll say it again - I don't work for hp, I don't get paid by hp to do marketting for hp products, I don't work for an hp reseller and I don't get paid to do marketting for an hp reseller. Sorry, you'll just have to find something else to obsess about.
Increasing commonality between IA64 and x64 at HP
You say yourself that IA64 and AMD64 systems will, courtesy of CSI/QuickPath, have increasingly common hardware, therefore common features. And you make the same argument for HP's common management software. Let's assume these are valid points and ignore how you get the frequently claimed but never explained "superior RAS" out of largely similar hardware and software.
So, under what circumstances would an end user pick an IA64 over an AMD64? It may happen from time to time, but in any given sale it will only happen when the end user is happy with IA64, the reseller is happy with IA64, the system integrator is happy with IA64, the app developer is happy with IA64, and so on.
Every one of those organisations, every link in that chain, needs to be onside with IA64. If any one of them isn't happy with IA64, the sale goes elsewhere (if not to IBM, then probably to AMD64, and if the team are somehow happy with HP as a supplier, quite possibly to AMD64 in Proliant, as you rightly point out). So that leaves IA64 with a tiny tiny tiny market segment in terms of units, though maybe not quite so tiny in terms of value.
The IA64 development and support costs are substantially independent of the size of the IA64 market, so as those costs increase (which they inevitability will, despite the increased commonality due to QPI and blades and so on - enterprise class "qualification" doesn't come cheap), the overhead per system sold increases too. This is the same "death spiral" which was used to justify the termination of the Alpha chip despite DEC's tales of a twentyfive year lifecycle commitment.
IA64 is irrelevant. The only thing that matters in this picture is the OS (and apps etc) that IA64 (and only IA64) runs - the HP/UX, the NonStop, the VMS. As soon as it costs HP more to keep those OSes exclusively on IA64 than it costs to port them to AMD64 or to give them up altogether in favour of chip-independent "industry standard" OSes on "industry standard" hardware, that's the end for IA64. Shall we say 2012, I'm feeling generous?
Matt = the definition of irony......
1: This really rich coming from HP's PR machine Fanboy himself!
"...froth and rant like the Slowaris fanbois"
# wc -w /var/tmp/matts_waffle.txt
Matt, you've excelled again, lets see if we can get you toward 2'000 word rants sometime soon please!
Re: Matt the HP droid.
"So you have perfomance figures then? You have any proof to your conjecture? No, none at all, just like the majority of the article."
No proof, just conjecture based upon the stated claims by Intel that they are delaying the release - again - to make additional performance improvements. I didn't make that up, it's in Intel's public statements. Also, Intel's doubling the core count, yet only "approaching double the performance of previous Itaniums." They double the core count and only approaching double the performance? With such a major upgrade, requiring a forklift upgrade, all they can do is double the perf? Not very exciting if you ask me.
Are you telling me that if Tukwilla met the 2x performance goal they would not have released the chip and added additional performance features in a follow on version? Intel is either lying (probable) or they have another serious issue with their overly complex chip. They're just to using performance as an excuse.
All of my conjecture is based on public information provided by Intel. What's your hatred of everything non-HP based on?
RE yawn-provoking Sunshiners posting exactly the same drivel for the umpteenth time!
RE: Increasing commonality between IA64 and x64 at HP
"....So, under what circumstances would an end user pick an IA64 over an AMD64?...." That's a bit like saying when would a customer pick a Xeon over a Celeron. Whilst a Celeron can do a lot of what a Xeon can, you're not going to pretend that every user should drop Nehalem and go back to Celerons, are you? Itanium is designed as a "heavy-lift" CPU, it has much larger cache, a far greater number of registers, and a lot wider pipeline than Xeon or Opteron. Sure, if you have a lighter weight thread, and you just need CPU scale to say eight cores, then Nehalem (or Istanbul) makes sense over Itanium. But, if you have a heavy-thread app, like a lot of the enterprise commercial apps (e.g., SAP or Oracle), and you need wide memory and cache bandwidth to keep the data flowing, and the ability to scale for example above 32 cores, then Itanium is the better choice. You may disagree, but then a lot smarter people than you have done the benchmarks and gone for Itanium in hp Integrity (hp Itanium Superdomes are just about the de facto choice for telecom billing systems, for example, as they are the only platform that delivers the scale, sheer grunt and RAS at the best price point). I'm not expecting you to take my word for it seeing as you have already shown both your bias and your intent to immediately label anyone that disagrees with you as a liar or competitor and liar, so I'll just suggest you go talk to some of the companies on this list http://h20341.www2.hp.com/integrity/cache/405502-0-0-0-121.html and ask them why they picked Itanium over AMD64, Power or SPARC. Don't hurry back, you won't be missed.
"....It may happen from time to time, but in any given sale it will only happen when the end user is happy with IA64, the reseller is happy with IA64, the system integrator is happy with IA64, the app developer is happy with IA64, and so on...." Gawd, what a mind-numbingly innaccurate pile of male bovine manure. I'm a customer, tbh I don't give two hoots about whether the reseller is happy as he'd better be worrying about my happiness first and foremost (or at least making a damn good pretence)! Here's the big news you missed - Itanium has a massive number of applications, so I don't have to worry about the developer being as brain-dead as you either. Please name a major enterprise application that doesn't currently run on Itanium on either Windows, Linux, hp-ux or VMS. And as for integratrors should we make use of one, then you may be surprised to find all the major VARs are also hp resellers/integrators. So, to summarise, stop talking testicles!
"....IA64 is irrelevant...." Sales figures say otherwise, and the list of customers using hp Integrity for business critical solutions says it doubley so. The only thing irrellevant here is the continued mindless posting of repeated and boring nonsense. Please try some new FUD.
RE: Matt = the definition of irony......
"....Matt, you've excelled again, lets see if we can get you toward 2'000 word rants sometime soon please." Two things for you to consider - first, I only post in repsonse to the repeated FUD of you Sunshiners, so if you stop your drivel then there would be no need for me to show you up for the morons and liars you are; second, try a word-count on the amount all you Sunshiners post and you'll see I don't even come close.
RE: Re: Matt the HP droid.
"No proof, just conjecture based upon the stated claims by Intel that they are delaying the release...." So at least a Sunshiner admits their FUD has no basis in reality, but am I surprised you continue FUDing? Not really, it's the Sun way.
"....I didn't make that up, it's in Intel's public statements. ...." No you didn't, you just delved into fantasy for the rest of your post.
"....Intel is either lying (probable) or they have another serious issue with their overly complex chip...." From what I've read, the chip core is done, the additions like the DDR3 memory controllers are all peripherals, same goes with anything like the "hypercache" idea. Sorry to remind you, but Itanium isn't struggling with the basics like Rock, which can't even get scout threads and transactional memory working. And Intel can afford to take the time to get Tukwila right because it will be competitive, whereas Rock is already behind the curve and falling further behind every day. Power7? Who knows, has the core design even been cut to silicon yet? Looks like Tukwila is ahead of the potential rivals.
"....What's your hatred of everything non-HP based on?" I don't have a "hatred" for anything, just a profound distaste for the unethical approach of you Sunshiners and your FUD habit. What should worry you more is the profound liking for hp that the customers have developed as it means less options for neanderthals like you.
/SP&L, especially at the Sunshine re-runs - has Sun fired all their FUD merchants, can't they think of anything new?
Re: matt the king of FUD
"I only post in repsonse to the repeated FUD of you Sunshiners"
Matt, if that were true, then we would only see you commenting on HP specific articles. The fact is that there are a lot more Sun articles than HP articles, so you are constantly commenting on Sun articles with your FUD. No one says anything about HP on those articles until you come along and state that HP does everything better than everyone else.
"...but am I surprised you continue FUDing? Not really, it's the Sun way."
Again, Matt, nothing you say is based on fact. Let me remind you what FUD stands for. Fear, Uncertainty and Doubt. That is exactly what you throw at Sun, always. You have no proof that Oracle will drop SPARC, as a matter of fact, Larry states the opposite, yet you spread the FUD that Oracle has already made the decision to do so. Again, you have always stated that Sun cannot compete because their financials are not good enough - you throw this in on articles that are talking about the technical merits of a Sun product. How is talking about financial merits in a technical discussion not FUD?
You make incorrect comments about IBM and Sun technology, yet state that noone understands HP's tech (except you). You are a FUDster and a hypocrite. I'm not sure which is worse.
Oh yeah, you are the king of rants and frothing. I would bet that you must hold the record for word count on El Reg. You may even have more words here than the actual columnists. You must be so proud.
RE: Re: matt the king of FUD
Oh yeah, because I invented FUD, didn't I - not! Here's the results of a simple straw poll I did a while ago amongst City admins I know, who work with a variety of server vendors. On the simple question of which vendor talked the most FUD, the answer was predominantly Sun by a massive margin. Here in the UK Sun is synonymous with FUD. The one good thing you could say about Sun is they aren't prejudiced, they FUD everyone! Micosoft, RedHat, Novell, IBM, Fujitsu, SGI, hp, even partner companies like Oracle when they do stuff like the Oracle Database Machine work with hp or RAC on Linux.
"....You have no proof that Oracle will drop SPARC, as a matter of fact, Larry states the opposite..." Wrong! Larry can't commit to SPARC and his public statements in no way commit to a roadmap for any SPARC product, they're just vague "intention" statements designed to keep Sunshiners like you happy so you don't all start dumping Sun for hp, IBM or Dell. Please point us to a public roadmap which states exactly which SPARC CPUs will be definately produced under Oracle's control. Oh, you can't. And it's not me saying SPARC has no future under Oracle ownership, it is industry analysts. Your selective hearing tunes out the nasty bits but the customers have already got the message.
".....You make incorrect comments about IBM and Sun technology...." So which comments then? Please let us know where I have gone wrong in your eyes if only for the comedy value. I'm betting my "incorrect comments about IBM and Sun" just turn out to really be what are for you just painful realities about Sun.
"....Again, you have always stated that Sun cannot compete because their financials are not good enough...." And there we have the perfect case in point of just how happily blind to reality Sunshiners are. Sun has nose-dived from a $200bn company to a sub-$4bn market cap, with continual losses draining the reserves, and yet you Sunshiners try and pretend this doesn't have any impact on Sun's abaility to deliver. Even Schwartz eventually folded and made the announcement of cuts - do you think he did that for fun? It was because the Sun board realised they needed to cut costs drastically. Even if it was just people being lost if would affect Sun's ability to deliver, but we also hear tales of budget cuts and slashed development budgets, and those are coming from people in Sun. So Larry buys Sun and all you Sunshiners start bleating about how Larry is just going to pour Oracle profits into the same moneypit that was Sun without asking for any changes - do you realise just how stupid you sound? Larry and Co are going to go through every bit of Sun with a fine toothcomb and a scalpel, and I doubt if even 50% of the current Sun will still be in Oracle hands in three years time.
".....yet state that noone understands HP's tech (except you)...." Actually, I state the complete opposite. The fact that Integrity sales are growing share means that customers understand that hp tech just fine. Also, the fact that Sun has tanked like the proverbial brick just goes to show the customers also get exactly what you Sunshiners just can't face - SPARC and Slowaris are dead on their feet.
"....You are a FUDster and a hypocrite. I'm not sure which is worse....." Sticks and stones, Sunshiner. And who says I give two hoots about your opinion? It likely to be just as comic as your poor grasp of both technolgy and the market.
"....Oh yeah, you are the king of rants and frothing. I would bet that you must hold the record for word count on El Reg. You may even have more words here than the actual columnists. You must be so proud." More like laughing my face off at how much it winds you Sunshiners up! I am so enjoying watching you guys squirm whilst Sun goes down.
Re: matt the king of FUD
Ah... Leave poor Matt alone. He's a bit slow, but he has his place.
Matt meet Kettle
"Here's the results of a simple straw poll I did a while ago amongst City admins I know, who work with a variety of server vendors. On the simple question of which vendor talked the most FUD, the answer was predominantly Sun by a massive margin."
Matt, I took a straw poll of my ass and it said you're a douche bag. I would actually take that opinion over your so called "straw poll".
Seriously though, Matt, give me a break. I just walked over to a rather large group of admins and asked the simple question "out of the top four server vendors, who has created more for the IT industry as a whole?" The answer, in order?
1. IBM (with some votes for Sun).
2. Sun (no votes for HP or Dell here)
3. HP (a couple of votes for Dell)
It was pretty overwhelming that no one thought that HP or Dell have actually had any kind of technical advance that benefits the industry. Of course, this is a total bullshit poll and used only to show how full of crap you are Matt.
Wait, I just took a straw poll of a dirty diaper and it says Matt's full of crap.
RE: Matt meet Kettle
When you've finished talking to your ass and your diaper, I suggest you go have a nap and leave the discussion to the adults.
Re: RE: Matt meet Kettle
Now that's funny. I don't care who you are...
Some other straw polls
So I kinda' like Matt's straw poll idea. So I took one of my own:
I showed some of Matt's comments to non-technical people and asked what they thought of this Matt person. The overwhelming response was that this person needed to get a grip (to paraphrase). When I asked what they meant, most stated that this Matt person had way too much time on his/her hands and an unhealthy dislike for everything non-Sun. But, I argued he dislikes Sun, but he seems to really really like HP. I showed them some of Matt's more embarrassingly pro-HP comments. They just rolled their eyes. This was a rather large group of non-technical people.
I asked if they thought that Matt should get a girlfriend/boyfriend. They all shook their heads yes as if they were a bunch of bobble heads being shaken by a 2 year old.
I think you should take this Straw Poll seriously Matt. I know how much credence you put in them.
I chose non-technical people, cause I've already seen what technical people think of you on these boards and thought the poll would be repetitive.
Heart... well, 'cuz you know why...
RE: Some other straw polls
Aaaaaannnnnnd..... still waiting for any form of technical argument from the Sunshiners. At least in between talking to or through his ass and examinng his diaper, our AC Kettle at least tried to form a discussion around Sun's prior achievements. Unfortunately, that's the problem with Sunshiners - all looking back at the Golden Days of the pre-dotbomb and desperately clinging to the belief that someone will be able to make Sun great again. Problem is, our Kettle should have asked his group; "Which of the top four vendors do you think will make a profit this year?" After putting hp and IBM and probably Dell in the profit group, they'd probably be scratching their head trying to think of a fourth vendor. I'm betting not one would say Sun would make a profit.
As for your poll of non-technical people, the eye-rolling was probably more to do with your rabidly forcing them to read a forum they have no interest in, then having you bark at them; "See? He's a loon! He hates us! Hates us!" I'm sure that same group spend a lot of time avoiding you from now on, that is if they don't already.
You've been provided lot's of technical arguments. When you are hit with it, you tend to get very quiet, and ignore it. If you are provided benchmarks, you call them cherry picking, and then provide your own cherry picked benchmarks. I for one have given up trying to have a civil discussion with you Matt. Your lies and FUD are laughable. You say that noone else uses technical arguments, but then attack on financial terms (how's that a technical argument?) You throw enough FUD into the world and some of it is bound to be right. You are the definition of the infinite monkey theorem, Matt.