Sun To Use AMD Mobile Processor In Blade Servers 250
An anonymous reader writes "Looks like AMD is finally making some headway into supplying 1st tier business computer makers which the announcement that Sun will use their chips in upcoming blade servers. Apparently CNET can't help but speculate what this means for AMD's 64 bit Hammer."
Is it hot in here... (Score:1, Funny)
Re:Is it hot in here... (Score:5, Funny)
Nope, Its the smell of your Karma burning.
Re:Is it hot in here... (Score:3, Informative)
Re:Is it hot in here... (Score:3, Informative)
JOhn
Re:Is it hot in here... (Score:5, Insightful)
Yeah, no [sun.com] one [ibm.com] makes [mips.com] 64 bit chips that are ready to use.
Re:Is it hot in here... (Score:2)
Re:Is it hot in here... (Score:3, Funny)
What you mean is there's no real market yet for 64-bit Intel/AMD chips, sceptics don't think hammer will run 64-bit code as fast as Intel's offering and so there's no huge market. Itanium (or whatever they're calling it now) requires it's own nuclear power source so there's no market for that (who needs 64-but when you can cluster).
Re:Is it hot in here... (Score:2)
Also on Ars Technica (Score:5, Informative)
http://arstechnica.com/archive/news/1046147898.ht
A somewhat different interpretation of the meaning?
Re:Also on Ars Technica (Score:5, Funny)
Check it out! [w3c.org]
Re:Also on Ars Technica (Score:2, Funny)
Good news for Linux (Score:5, Insightful)
This is VERY interesting news since at this moment Sun is holding their Chip Conference where the future of Sparc is being discussed.
Re:Good news for Linux (Score:5, Interesting)
Fine. Don't take my money. Don't save on the lack of support calls you'll get. Save money on my lack of downloading your service packs. Sun is retarded for ignoring those who just want hardware.
BSD is DEAD (Score:5, Funny)
For instance, the other day I was making a little presentation to my boss and suddenly used the:
1.
2. . .
3. Profit!!
Step list . .
slashdot is going to get me unemployed and single.
Re:BSD is DEAD (Score:5, Funny)
1.
2. . .
3. Profit!!
Step list . .
That's from South Park (the 'Underpants Gnome' episode). It's not a Slashdot thing (although being unemployed and single probably is).
Re:BSD is DEAD (Score:2)
Re:BSD is DEAD (Score:2)
FreeBSD & OpenBSD are all over the place, and that's not even counting Apple's OS X, which is basically a BSD variant. BSD has not failed commercially any more than Linux has, and it's just as "standard" as Linux is.
Re:BSD is DEAD (Score:2)
It depends on what business wants to do.
If they just want to use open source code in their own products, then they would prefer BSD licensed code. eg Microsoft complaining about academic code being GPL licensed.
If they want to open up their own code eg to help the community, foster goodwill or commodotise something, then they would prefer to choose the GPL license to stop their competitors stealing it for use in closed source apps. for instance Sun with Open Office.
Re:Good news for Linux (Score:5, Informative)
If you can get assigned a rep, the best thing to do is call 1-800-iforgetsunsphonenumber and get a quote, their tracking system will automatically notify your rep that you got a quote and usually they'll call you to try to get a comission on an easy sale.
However, have you considered ebay or one of the MANY sun resellers?
Re:Good news for Linux (Score:2)
The main issue I had was with the occasional SE that was just a f***ing moron and tried to push an obviously incorrect over massively overpriced solution.
Re:Good news for Linux (Score:2)
All new Sun hardware comes by default with a Solaris right-to-use license. If you don't want that, the simplest thing for you to do is buy second-hand. There are tons of pretty darn inexpensive Sun equipment out there (Ultra 60s under $1,000, E10K around $50,000, etc.). Many vendors will even offer good warranties if you ask.
Why not? (Score:2, Interesting)
They are in business, not gambling, so yes, they need to think about what if, but Solaris is still the core of Sun (like Solaris is the core of N1).
> Wow -- Sun is boosting Linux in a BIG way now.
Why not? Though they were cutting work force dramatically, they are still one of the biggest players in server market and if you look back for the last 10 years, they have achieved quite a lot. 10 years ago, they were nowhere. They were pretty interesting 5 years ago, and now they are competing with players like IBM with head to head, toe to toe. They don't have a big share in low end server market, so they push Linux. Since they built their business around Solaris (Unix), their engineers can easily shift to Linux; training cost is insignificant. So why not?
The negative shift from dot com bubble was so dramatic that, many seem to believe that Sun is turning around the direction that they are going, but I (and probably many other) don't think so. They are in server business, and they are investing a lot there. They established themselves as one of the biggest players in high end server market, so now they are targeting low end as well. While they pursue the whole server market, they push, what they call, N1.
The point is "What's so surprising? What's so unpredictable?"
Re:Good news for Linux (Score:2, Interesting)
I've run Linux and Solaris on x86 boxes - Linux has a lot of neat bells and whistles, but Solaris seems to be a bit better thought out (have yet to try a BSD on x86). My biggest complaints with Solaris are the lack of an "smbmount" facility. and limited HW support My biggest complaint with Linux is that the desktops lack the refinement of CDE - CDE was designed, KDE and Gnome evolved.
Remember that Linux is just the kernel - a good portion of what you find in a typical distro can easily be ported to Solaris.
Re:Good news for Linux (Score:5, Insightful)
I see no reason for them to plan to phase Solaris out. It is arguably (and often measurably) better than Linux for the things where it wants to be better (dedicated servers), and I see no indication that is going to change. Linux has a lot of hardware drivers, and is great with system call overhead and other things which are nice to have on a single-user single CPU desktop system or small server, but I do not think Solaris has been worried about that kind of use for several years.
If Linux gets to a point where it is better than Solaris at the things Solaris is supposed to be good at, then I think Sun might think about using it instead, but I see no indication of things going in that direction. Not to mention that Solaris is extremely well documented.
Larry
Re:Good news for Linux (Score:2)
More seriously, I just downloaded Solaris 9 for x86 and am looking forward to using it. I am interested in opinions of where Solaris shines (sorry, once thought, had to say it). I have previously been told that its latency/multithreading support is superior. I will be looking at that.
I fear that simply experimenting with it on PC hardware will not really expose some of its strong points for the larger servers.
Re:Good news for Linux (Score:2)
Every new version of the Linux kernel shows more and more promise. 2.6 (probably next year) will have a really robust/optimised posix threading system, Better I/O and scale to far more CPU's in an smp configuration while still doing simple things simply fast. Solaris does scale better and contain other features that Linux does not have but Linux is catching up very fast without sacrificing performance on "smaller" machines. I am sure Sun is aware of these developments and Sun's top management is probably wondering how to shift their bussines model so that Linux will help them sell products and not the reverse.
Great (Score:4, Funny)
Re:Great (Score:3, Funny)
Re:Great (Score:2)
The weird part... (Score:5, Informative)
Re:The weird part... (Score:3, Funny)
They should have dropped in the noun 'synergy' in the announcement.
Re:The weird part... (Score:2, Funny)
Re:The weird part... (Score:4, Informative)
Sickle servers (Score:2, Funny)
my bad. mod me down.
Don't over look the real news. (Score:5, Insightful)
I *think* I know how the market will respond to this as far as AMD is conccernd, I'll be keeping an eye on what this does/means for sun.
But what about the end of Sun? (Score:5, Interesting)
Re:But what about the end of Sun? (Score:2, Interesting)
Re:But what about the end of Sun? (Score:3, Interesting)
True, linux on x86 is not big iron... yet... but do you relly mean to discount the possibility that it could become a cheaper solution to big iron? For one example, look at Oracle RAC on x86 blades. It's not exactly one megalythic server... it's really more like a beowulf cluster, actually... but what works works.
Anyway... it'll be intersting to see how this all plays out.
Re:But what about the end of Sun? (Score:5, Insightful)
Re:But what about the end of Sun? (Score:5, Insightful)
Truthfully, I don't think this will do much for AMD one or the other. Sun is just marketing these things to prevent current customers from looking elsewhere. You can be pretty sure the main emphasis will still be on Sparc.
Re:But what about the end of Sun? (Score:2)
He keeps telling that I should plan on porting my applications and web site to NT boxes and teach myself
Sometimes he seems to make sense. Other times, he sounds like a Redmond Fanatic.
I dunno. What I don't tell him is that I've had contingency plans to go to diffferent OS's and platforms for years. I like to hear him go on and on about how Mcneally is an idiot and how he's running through Sun's cash, and how Bill and co. are just waiting for Sun to squeeze the last bit of juice out of their orange.
"One day Bill's going to have a glass of OJ. From that day forward he'll never have to think about Java again".
Yeah, we come up with some weird stuff when we're supposed to be coding.
Re:But what about the end of Sun? (Score:2)
Does he follow IBM's financials too then?
Re:But what about the end of Sun? (Score:2)
'nuff said
Re:But what about the end of Sun? (Score:2)
Before anyone talks about the death of SPARC... (Score:5, Insightful)
- A.P.
Sun wants Solaris to be known as the 64 bit OS (Score:5, Interesting)
OTOH who is going to try to make a go of AMD/64? For sure not any of the system vendors who have commited to IA64. That means no Dell, no IBM, no HP. So there is an opportunity for Sun.
Re:Sun wants Solaris to be known as the 64 bit OS (Score:2)
Don't you just mean HP? I was under the impression that IBM has dropped Itanium, and Dell has decided to just wait and see if it ever amounts to anything.
I could be wrong though
Re:Sun wants Solaris to be known as the 64 bit OS (Score:5, Informative)
While there are no announcements out of Dell yet, Infoworld published this article [itworld.com] back in November, saying:
The Register published their take [theregister.co.uk] on the situation. It may never come to pass, but I'd be surprised if Dell wasn't at least looking at such a plan.
Re:Sun wants Solaris to be known as the 64 bit OS (Score:3, Interesting)
As for who will use AMD's x86-64 Opteron processors, I'd say that it actually makes most sense for Dell. Dell is now the only major server vendor that doesn't have their own processor. Sun has their Sparcs, IBM has their Power line, Fujitsu has their Sparc64 line, while HP essentially has the Itanium as their own processor.
Sure, Dell can buy Itanium's from Intel, but they end up with a the same processor that HP uses but lower quality chipsets and supporting architecture, and all 6+ months after HP gets their stuff. Any company selling Itanium based servers is going to be competing against HP at a serious disadvantage unless that company also puts the research and development money into developing their own chipsets and motherboards. IBM has made some motions in this direction, but research and development is definitaly NOT Dell's cup of tea.
Dell's strong point is slapping together systems that others have done almost all of the R&D for and most of the testing as well. Their strong point in servers is the Xeon market, and this is first and foremost where the Opteron is going to compete. What's more, a company called Newisys has made quite a bit of noise recently about their Opteron system designs. What this company proposes is to do all of the R&D work and most of the testing work in setting up Opteron servers and than selling these to big OEMs. The OEMs would than just need to slap all the parts together and sell them, ie right up Dell's alley.
Now, as for Sun, they're a bit of an odd case here. They're still kind of finding their feet in the x86 server world, so it's kind of tough to decide just where they're likely to go in the future. However, I would definitely guess that Opteron based x86-64 servers could offer them a reasonable solution for what they're after.
Re:Sun wants Solaris to be known as the 64 bit OS (Score:2)
However, Dell is by far Intel's biggest fanboy among the OEM's. I'd place the probability of them ever using something without an Intel processor somewhere between 0 and 0.5%.
another proof point that Sun is dying (Score:5, Informative)
Sun CPU engineers are way behind their competition. They're so far behind that their competition is litteraly lapping them in terms of price and performance.
Try and find any decent Sun server benchmarks that prove that their gear is competitive.
You can actually find benchmarks that one can make the direct comparison of an 8 way UltraSPARC 3 to a 4 way Intel Xeon MP! And the Intel based solution is faster and costs 50% or less.
Sun by virtue of their ego is becoming a boutique server/workstation vendor. Think SGI, this is likely Sun's future or worse if they don't start laying more staff off.
Businesses are realizing this, and this is why Sun is taking such a beating.
Re:another proof point that Sun is dying (Score:2)
So, Sun is lagging behind in terms of technology, but can catch up by firing their staff?
Re:another proof point that Sun is dying (Score:2)
Then why does Sun have so many press releases about all the transaction throughput world records they break?
The SPEC cpu benchmarks are pretty damn useless when comparing general-purpose systems, which Sun systems most definitely are. If you wan't in-cache programs to run their best, perhaps Intel is better, but that alone is not sufficient basis for your argument.
Future of UltraSPARC (Score:2)
what about long term? (Score:2, Interesting)
Press (Score:5, Interesting)
Re:Press (Score:4, Funny)
Now we just need... (Score:2, Interesting)
Linux has had that for at least 5 years (Score:2)
Uhhm... (Score:2)
You can't have more than 4 gigs on x86 architecture. It's 32 bit, so it's limited to 4 gigs. I know, I know, Intel has some kind of 36-bit addressing hack, but it's just that -- a hack, like the XMS/EMS memory of the olde DOS days. It's either that or AMD's x86-64 which isn't out yet, but Linux is running quite nicely on the pre-release models. A few months ago, AMD even demoed x86-64 version of SuSE.
Re:Uhhm... (Score:2)
Re:Linux has had that for at least 5 years (Score:3, Informative)
Don't expect Linux to be any less ugly about something that works in a completely different way from how everything else does.
Re:Linux has had that for at least 5 years (Score:2)
The support was pretty much a byproduct of porting Linux to that arch.
I'm looking forward to the AA-64 as well since it fixes the 2 largest pains of the x86 world: The other problem being the lack of registers.
Lower cost overall? (Score:2, Interesting)
In any event, the Sun blades aren't in direct competition with commercial Linux offerings (yet), so I don't see how much this will help them. The inclusion of AMD CPUs will only marginally improve costs on the Blades.
Well, many researchers foretold Sun slowly to move to AMD as they enter the x86 market. You would expect that their next move will be low cost (low for Sun) Linux offerings with AMD chips to compete with IBM's $4,000 offerings.
Re:Lower cost overall? (Score:3, Interesting)
Linux tends to make huge leaps and bounds in a short time while Sun usually just tweaks a few interest points at a time.
This might be because Solaris is ahead of Linux in a lot of places (scalability and storage management are two areas that come to mind right away).
There are diminishing returns as an OS matures -- refinement becomes the goal rather than feature addition.
Watch MacOS X to see the same phenomenon in action...
Re:Lower cost overall? (Score:5, Informative)
Whaa? I recently bought a SunFire 480 (definitely the "low end") for work, came out to about $23K, just for shits and giggles I just went over to dell.com and priced out a similarly configured (more or less the same, the processors probably have a bit more horse power to them) PowerEdge 6650, which came out to $22,780.
Oh sure, I could've gotten a 2650 with considerably faster CPUs and 50% more RAM dirt cheap (and in fact, we just purchased a couple of those as well), but for some reason if I need it to be expandable beyond 2 processors and six gigs of RAM it's just nowhere as thrifty all of a sudden. Not to mention that with the 26XX's the thinking is pretty much: "If it breaks - we chuck it and get a new one." and you can't really afford that for all applications.
as Linux tends to make huge leaps and bounds in a short time while Sun usually just tweaks a few interest points at a time
You do realize that you've just made the case for Sun (hands down) for anyone who is actually in a position to make purchasing decisions for a company? Explain to me the difference between "improves daily" and "has a long way to go".
Mind you, I love Linux and use it extensively (at work and at home), but that is no reason to just make things up about Sun's software or hardware.
Re:Lower cost overall? (Score:2, Interesting)
Can the original contributor explain?
Re:Lower cost overall? (Score:2)
It goes over $20K very quickly. I did just notice that they add a 24-port switch in there, which no one asked them to, so that's a couple hundred bucks.
Re:Lower cost overall? (Score:3, Insightful)
Also, according to the Dell web page when I add 4 Xeon processors which only have 2MB cache, and 4 GB of RAM, the price is now over $25k.
The V480 uses 1.2Ghz UltraSparc III processors with a massive 8MB of onboard cache. I'm sorry, but your wimpy little Xeon will not keep up with these processors.
Also, keep in mind a major selling point of Sun servers: ECC across all data paths. Don't expect Dell to ever give you that. You might have ECC memory, but what about the memory bus that connects to that memory? No ECC error checking/correction. This is a major differentiator between Sun and Intel systems, and one that unfortunately the Slashdot crowd doesn't understand at all.
Re:Lower cost overall? (Score:2)
um, bzzzt, wrong answer.
obviously it depends on workload characteristics, but we find that 1.0 GHz P3's are equivalent to 900MHz US-III's (Yes, I have a Fire V480 to try this on). Those 2+ GHz P4's beat the pants off everything Sun makes. Don't believe me? Check SPEC [spec.org], our workload correlates nicely to SPECint results.
If you don't want to click-through, the Sun 1.015GHz US-III benchmarks at SPECint = 516 and a Dell 6650 (w/ 2.0 GHz Xeon) runs 816. Don't even try it with a reasonably current (i.e. 2.8GHz, 533 FSB) Xeon (SPECint = 1017), the Sun will just turn into a black hole.
Of course, the reason we have a V480 is because it is 64-bit -- it's for our largest-footprint computational tasks. But it costs a sh*tload, and is dog-slow. I think we can normally buy 5 dual-proc 2650's for the price of one V480. And these are fully tricked out 2650's. Just do the math and realize how screwed Sun is.
Bring on the freaking Itanium/Opteron solutions!! now!!
Re:Lower cost overall? (Score:2)
But there's the rub -- for my apps CPU performance really is the most important thing. #2, as you allude to, is memory bandwidth, but it's a distant second (and the L2->L1 cache fill bandwidth on any Intel processor is still pretty damn fast). You also will not see anywhere close to the numbers (9.6GB, 33.6GB/sec) you quote from a V480. No way -- those are aggregate marketing numbers (almost as bad as when people add MHz numbers together on dual-proc systems). Another guy later one set you straight on the PCI-bus issues on PC's so I won't do that here, but suffice it to say you are off the mark.
I have done all the app-level benchmarks, measured the real wall-clock times for apples-to-apples comparisons, trust me (when you are spending multi-$100k per year on servers, and millions per year on software licensing, you better get it right). The x86 boxen blow the doors off the Suns -- at 1/3 to 1/5 of the price.
As far as lack of education of complexities of enterprise systems, I think you are barking up the wrong tree. I do chip design work, used to do it at Cisco on high-end switches, now work on SAN switches (tangent: you will never get your claimed 512MByte/sec out of a Fibre Channel port -- it's good to 1/2 Gbit/sec -- i.e. 125/250 MByte/sec, assuming no protocol overhead -- crappy old PCI33/32-bit can almost drive a 1G FC HBA, and PCI66/64 or PCI-X certainly can handle a 2G HBA).
A big part of what I do is design the simulation and synthesis compute clusters, so system-level issues are all I think about. Further, I work with the guy who designed the Ultra60 SDRAM/system controller ASIC, a couple guys from the SGI high-end servers group, and one of the guys who ran the UltraSparc IIIi program at Sun. Our systems guys are from Sun, they're the ones who designed the Sun 280R,480 and Blade machines. They all agree (from feeling the performance) the x86 hardware is best, bang for the buck, and on absolute performance. Our modeling guys also tell us that Athlon's beat the snot out of UltraSparc III's for hspice circuit simulation (again, from head-to-head comparo).
As I mentioned, all of my points are true until you crack 4GB processes, then the 64-bit-ness of the Sun gives it an unbeatable advantage. Thankfully for us, that's a very small percentage of our workload, so we only need the one V480, and yeah it's a nice box. It's just overpriced and slow. An Itanium box is faster overall (even though everyone bitches how slow it is), and costs about the same right now in ultra-low volumes -- just wait till Intel turns on the faucet.
I appreciate your attempt to defend Sun's cost structure, but I think you'll find that it's not justified. Sure, they are solid boxes, but if you are willing to spend 5-6k on a decent rack-mount PC running Linux, it's going to be pretty damn solid as well. We have had many 100+ day uptimes on our x86 boxes, mostly terminated by building power episodes, or data center cooling failures. In our business (chip design),
Linux on x86 will completely supplant Sun in the next 3-5 years, I suspect.
One last thing -- the part about ECC. We design in ECC all over the place in the system we are building too, because people ask for it, and it's a check-box type of item for the buyers. The only place you ever actually see bit-flips is inside memories, at the bit cell -- either SDRAM or on-chip SRAM. So protecting those is covering 90+% of the problems. The rest is probably not worth it, since the probability of failure is so low.
Thanks for reading...
Re:Lower cost overall? (Score:2)
1) This comparison is pretty damn rediculous. At $250,000, that's the price of the entry-level Sun "midframes". These cater to the market segment where downtime is much more expensive than the added cost of very reliable hardware.
2) Thus, you must compare to IBM's "midframes"--the RS/6000 lineup or perhaps their genuine mainframes. Oh, they are just as expensive.
3) For $4,000, you get a rack-mount PC. A rack-mount PC you get.
4) To think otherwise is delusional.
Solaris less expensive? (Score:2, Troll)
Am I the only one that fails to see the logic here? Since when has solaris been less expensive? On hardware terms too, I would have thought linux is more suited to run on the lower-end boxes. Is this desperation from Sun we're seeing?
What of AMD? (Score:4, Informative)
After reading it, I felt a bit let-down, but then it's really no coup for AMD and no defeat for Intel, it's practically non-news.
As the cops say, nothing to see here, move along.
Re:What of AMD? (Score:3, Interesting)
Sun is using an AMD chip when they have traditionally used their chip, or intel's, for its low power use and ostensibly heat dissipation when the athlon in general has a bad name for power consumption, and this is non-news?
The article is one big, "no comment." (Score:5, Funny)
"However, Holman said Sun's decision to use AMD in the forthcoming blade server doesn't rule out Intel for future products. 'We're not completely wedded to either vendor,' she said."
"Asked if Sun planned to use AMD's 64-bit extensions, Holman said, 'There are no long-term implications based on this decision'""
"AMD declined to comment on Sun's move."
Now that's hard-hitting journalism!!
Sun ain't got the dullest knife in the drawer... (Score:2)
I just pieced together an AMD system for myself, an XP2400+, an Asus A7N8X Deluxe, 1Gb DDR333, and a 120Gb HDD. I'd like to see any current Sun workstation beat this combo considering I have OpenGL/Linux well in hand.
If you can't beat 'em... buy their shit and sell it as your own!
I've been watching Ebay for deals on Sun equipment and have never seen something that seems like a good deal. Like I might consider paying $100 for an Ultra10, but thats about it. If they go more mainstream and were to make some kick-ass motherboards for AMD systems they could probably go a long ways. Sun motherboards have mega-bandwidth which is exactly what AMD processors could use. Sun is also noted for scalability; i.e. add a second processor and your system will be nearly twice as fast.
This should be really interesting...
Re:Sun ain't got the dullest knife in the drawer.. (Score:3, Insightful)
I guess it all depends on what your terms are. Three years ago at work I was working with a simulation that took about 5GB of ram to run (1 process). All of the 2 year old Sun workstations we have now could run this. Sun had equipment, what, 7 or 8 years ago that could. Your PC still can't.
Your PC could no doubt render a beautify, a kick-ass Quake 3 scene. But it would probably suck wind trying to do certain types of CAD displays. It can be very different 3D work from what a PC graphics card is good at (textures & shading). Of course, for what its worth, Sun's new XVR-4000 graphics card can take up to 1GB of memory!
Your PC will be a lot cheaper, and kick-butt. However there are some things a Sun could do that it just couldn't, or would do poorly.
I've been watching Ebay for deals on Sun equipment and have never seen something that seems like a good deal.
It all depends what you are looking for.
Re:Sun ain't got the dullest knife in the drawer.. (Score:2)
Wait, no I don't. Maybe that's because they are using mobile processors with low wattage!
Dooh! Dang they're onto me. Blow up the planet.
Funny dat (Score:3, Interesting)
What does this mean for Sun? No one knows for sure. Is it the beginning of the end or a stop gap measure until their new processors come out in 2004. The ones all the analysts are so hyper over, not the USIV or USV but the Afara procs.
But what does this mean for AMD? Now every enterprise can ask the question, why not go with AMD? Sun uses their procs... why shouldn't we use them also.
This is just good news for AMD and may be a kick in the groin for Intel to wake up to the 64 bit to the desktop question.
In other news (Score:2)
To: "The TREK NOW is the CUT ME PRO tm"
~ that is all...move along.
joke explained (Score:2)
What about the Cobalt line? (Score:2)
> Sun last year bowed to market realities and accepted general-purpose Intel-compatible computers into its server line. Its first model, the LX50, uses Intel processors.
What about their Cobalt [sun.com] line of RaQ servers. Seems to me they "bowed to market realities" when they acquired Cobalt Systems back in 2000. The LX50 [sun.com] is just a Cobalt RaQ with a faster processor [sun.com].
I think Cobalt servers make great low-end web servers, and they even run Sun's Brand of Linux (as does the LX50), which I believe is based on RedHat 7.2 (which they also acquired from Cobalt Systems).
Sun should buy AMD (Score:5, Insightful)
1) Sun can still afford it.
2) They gain instant credibility in the x86 market.
3) AMD gains credibility in the enterprise (luring really big enterprise customers with real service)
4) Sun gets 2 of the leading 64-bit processor platforms, plus some control over the Windows hardware platform.
5) Sun gets to own their chip manufacturer (rather than rely on stinky TI and Fujitsu for the Sparc line).
6) Sun can control the cost of its Linux platform.
Do, it Sun. . . you know you want to. . . buy them.
Say Goodbye to 64 bit windows (Score:5, Insightful)
Re:Say Goodbye to 64 bit windows (Score:5, Insightful)
I find this real hard to understand from a strategic viewpoint. (Maybe they are just late and do not want to hold up 2003). If indeed they have been strongarm'ed (bad joke) or something by Intel. It seems to me they are forcing a Linux / Opteron attack precisely where they want to go themselves. The middle tier server market.
With no immediate support from Windows what other choice is there for AMD than to embrace the only credible OS for their chip, Linux. They want to position Opteron against Xeon but the volume is not there initially so what else can they do than make special deals for Linux based servers. Now, this will hurt Dell as a Intel only supplier. Dell can not afford to loose momentum so either they have to get huge discounts from Intel, or embrace AMD. Either way it's bad long term for both Intel and Microsoft.
Once the middle tier market is gone to linux, they can kiss .Net goodbye. Just look at the Webserver market. No "innovations" from MS, since forever. Why?, because of Apache. They can't find traction for an embrace and extend strategy with 26% share. Same for .Net once the middle tier market is gone.
Not supporting AMD's x86-64 is like trying to corner an amimal thinking it wil not strike back. Strange.
Re:Say Goodbye to 64 bit windows (Score:2)
Re:Sun should buy AMD (Score:2)
Re:Sun should buy AMD (Score:4, Insightful)
Alternative scenario:
Having joined themselves together like some sort of financial Siamese twins, one of them gets struck down by competitors. Maybe Intel releases a good 64-bit processor; maybe they just market a 32-bit Pentium V really hard. Maybe linux continues to eat Sun's lunch from the low-end up, and destroys their core business. Maybe some other random thing happens, but the point is that it's certainly not clear that both Sun and AMD have rosy futures forever.
Now one of your Siamese twins is limping around attached to a corpse. And that's not going to do it any good.
Not saying that's what's going to happen, but "we'll both break into new ground" is precisely the reasoning behind the AOL-TW merger, and look how well that's worked. AOL is, to some extent, sinking, and TW will not be able to carry them forever.
I think I'd prefer them to stay seperate, and sink or swim on their own merits, because as it is, despite the synergy they might or might not have, if they did join, then the risk that either of them faces becomes a risk for both of them. And any one of those risks could drive them both straight into the ground.
not_cub
Re:Sun should buy AMD (Score:2)
If Sun didn't suffer from foolish pride (Score:3, Interesting)
This isn't the first time AMD has been here... (Score:5, Interesting)
Sun has used AMD CPU's before, although not in the primetime in their servers. They did use them in the SunPCi cards for workstations. I still have one.
The reason that Sun used AMD (the K6-2, I believe) instead of a Pentium, like they did with the SunPCi 2, is that at the time it made more sense price-wise. I see no difference here.
Finally a server from sun.... (Score:4, Funny)
Bothered to read? (Score:2, Interesting)
These are the notebook AMD XP-M CPU's.
That means low power and heat.
It also means no 64bit support.
Java crushed SPARC (Score:2)
1) Sun SPARC. Buy a Fire 280R for 7999$
2) IBM x86. Netfinity XSERIES 305 for about 1500$ with 2.67GHz P4.
Ok, the IBM one don't have Fibre Channel hard disks, but so what? I don't need them. For running Java, x86 is THE choice. Sun will still be the choice for running Oracle, but for how long?
Failproof Get Rich Never Business Plan! (Score:2)
2) commoditize your software! (Linux, free software)
3) $$$!!!!
I had a tough decision to make (Score:2, Interesting)
Moderate this thread or comment on it....hmmmm
I had to comment because I saw quite a few posts on the ability of Sun's slaes staff to reduce you too feeling like a non-human, loser who isn't worthy of their products because you are only spending 25, 50 or 75K worth of gear.
I work for an MSP and we do a lot of business with Sun (although we have sold more Dell/Linux solutions that Sun Solaris at the 3:1 ratio in the last 9 months). I am really tired of dealing with them. I even get attitude fromt heir teir 1 support! When a tier 1 peon asks me if I am sure that the drive is broken 3 times, and then tells me to get someone else to check it I get very angry and feel like cramming that drive down his stupid throat!
I mean really....I was supporting this stuff since before he was even a twinkle in his father's eyes. Am I not a repeat and well paying customer? Did we not spend several million dollars with Sun in the past? Do they not want to continue this relationship? I ask my sales rep these questions everytime I call....and he promptly hangs up on me.....BASTARDS!
Thats no ordinary blade (Score:2)
Re:E-Cold War (Score:2, Funny)
Re:What do we need sun for really? (Score:2)
That said, the UltraSPARC is still probably a weakness and so are JVMs (although the are getting better). To provide the solutions people really need, they need to get better at offering cheap x86 Linux that are well tested, Sun solid and integrate into their other systems well. Sun's on the edge, but be prepared for a strong recovery when corporate spending rises and IT guys get what they need instead of having to buy the cheapest thing that could possibly work.