Samsung May Start Making ARM Server Chips 116
angry tapir writes "Samsung's recent licensing of 64-bit processor designs from ARM suggests that the chip maker may expand from smartphones and tablets into the server market, analysts believe. Samsung last week licensed ARM's first 64-bit Cortex-A57 and Cortex-A53 processors, a sign the chip maker is preparing the groundwork to develop 64-bit chips for low-power servers, analysts said. The faster 64-bit processors will appear in servers, high-end smartphones and tablets, and offer better performance-per-watt than ARM's current 32-bit processors, which haven't been able to expand beyond embedded and mobile devices. The first servers with 64-bit ARM processors are expected to become available in 2014."
Just what Apple needs... (Score:1)
Apple is busy switching to these chips for their laptops/desktops. Coincidence?
Re: (Score:2, Informative)
There's no technical reason why an ARM chip of comparable performance to x86 could not be made. There's also no reason to believe such a beast would use significantly less power than an x86 chip, either. In order for the entire exercise to make any sense, they would have to target a niche between current ARM and x86. If they can keep the design sufficiently simple, they should at least be able to beat current ARM designs in performance and x86 in price. It is not clear that they can beat future Intel CP
Re:Just what Apple needs... (Score:4, Insightful)
There is. The fact that ARM architechtule an order of magnitude or more behind the current x86 generation in terms of performance is a technical issue, and ARM is clearly having issues making its chips scale in speed without completely losing whatever advantage it has in low power. Hence all the talk about dark silicone in ARM world.
Re:Just what Apple needs... (Score:4, Interesting)
An order of magnitude behind? No. A15 is close to Pentium M in terms of IPC. It should be around half way to Ivy Bridge IPC, I would think. That's not an order of magnitude, unless you're counting in base 2.
Re: (Score:3)
You just compared a non-released chip from 2012 that is yet to be seen in any real life applications to a mobile x86 chip from 2003, and still didn't even get parity.
Half way to chip tech from 2012? Are you sure you want to lock that answer?
Re: (Score:2)
Re:Just what Apple needs... (Score:4, Insightful)
It depends entirely on the application. For heavy maths processing in games or Photoshop ARM is way behind, but for typical server applications it is fairly competitive. Being low power is a huge advantage in datacentres and you often get better performance by having more cores than you do by having fewer faster cores.
Look at graphics cards. Lots of small, simple and not even terribly fast cores (in terms of clock speed). For that application they blow any CPU away. Now look at a typical server and you will see that it already has lots of small, simple and relatively slow cores dedicated to things like TCP/IP offloading, RAID array control and SSD management.
Re: (Score:2)
So what we get is that GPUs outclass ARM in simple mathematics, x86 outclasses ARM in more complex things.
So, where is ARM supposed to actually fit in that grand scheme of server chip? That is a question answer to which big companies are yet to find in spite of a lot of very vocal looking.
Re: (Score:2)
At hightly paralelizable symbolic processing. Like the GP said, that is most of what servers do nowadays: webserver, database manager (to a lesser extent), network filtering and caching, and a lot of other things.
I guess the bigest question is: How well will those new chips handle cryptography?
Re: (Score:2)
GPUs mostly rule that roost (crypto, highly parallelizable simple tasks). ARM has nothing on them in that regard, it's about a decade behind just like it's about a decade behind in x86 in general computing.
Let's be serious here: ARM is something companies have explored for a while now. It just isn't up to par (yet?) If it were, we'd see a lot of applications as server market is very profitable. And considering both the GPU and x86 advancement, chances are ARM will never be able to catch up.
Re: (Score:2)
By all means, what do you understand by "symbolic processing"?
No, GPUs don't rule at that. (And crypto is not symbolic processin, thus it is an open question.)
Re: (Score:2)
https://en.wikipedia.org/wiki/Symbolic_computation [wikipedia.org]
Why is ARM better then x86 or GPU for this particular task, and for that matter, why is it so important and cost intensive that you would look to have gains after software rewrite to ARM? I honestly have no clue, enlighten me.
Re: (Score:2)
How to spot an article written by a matematician: That definition is perfectly correct. Altough, a lay-person will be misled by it, thinking that symbolic computation is just one of its applications (the one the author uses more).
The same way that a computer can only work with numbers, but we abstract those and think about an image or sound wave, we also often abstract the symbolic algebra, and think about text and data objects.
GPUs are built for numerical computation. They are just terrible at branching, a
Re: (Score:2)
Ah, you're talking about hypothetical applications. ARM seems to be the king of those.
Shame no one ever managed to get those to work at levels needed for actual production so far.
Re: (Score:1)
you can fit more ARM cores at the same space and same price. If the performance is comparable (what we don't know yet, but isn't an unreasonable assumption)
Isn't it unreasonable? Let's see.
Let us assume that an ARM core occupying less space, consuming less power, and cheaper has comparable performance to an x86 core. This would mean that large server farms (facebook, Google, Amazon and others) have an advantage by switching over to ARM. None have switched even though they are very concerned with space, power and cost.
Hence our original assumption was wrong. Which means that an ARM core does not have comparable performance to an x86 core.
QED
Re: (Score:2)
Samsung didn't start to produce this chip yet, how do you expect Facebook, Google, Amazon and others to use it?
Re: (Score:1)
So your comment was specific to Samsung processors? Do you think Samsung will do something no ARM processor manufacturer has been able to do? By a significant margin? Why?
Re: (Score:2)
Did you notice that TFA is about a new architecture from ARM?
The comment was not only about Samsung, there are other manufacturers tooling their fabs for this new architecture. But nobody is producing it yet.
Re: (Score:1)
Yes but the new architecture is only an evolutionary one. There is nothing to suggest it will suddenly make ARM "comparable" to x86 in any sense. If new architecture ARM is comparable to x86, old one is as well because the new in in turn comparable with the old.
Re: (Score:2)
Re: (Score:2)
I don't think MIPS per CPU is the biggest concern in datacenters, it's MIPS per Watt. In that sense, ARM may outclass x86.
Re: (Score:2)
That's the problem. At the moment, it's not outclassing x86 nor GPUs due to severely lacking in terms of raw calculating power. The word is that "there's potential if ARM can increase its performance while keeping the low power requirements." That doesn't mean "it's happening" or even "it's going to happen".
And intel isn't exactly sleeping, so while ARM needs to get to increase it's workload per time, intel is working on increasing workload per energy. ARM may potentially hit the "sweet spot" at some time b
Re: (Score:2)
I'm not planning to install a datacenter in the near future, so I haven't studied it in-depth. But I'm sure the big players will do just that, and if they do make the switch, it won't be for fanboy reasons, but for hard economic facts. So I'll let that be the proof, and postpone any poor judgement from my part until later notice.
The only thing I can say is that from my experience with ARM programming (including assembly), the architecture is much cleaner than x86. And a clean design has a tendency to be mor
Re: (Score:2)
The issue isn't about how "clean" architecture is, but how hard it will be to rewrite and/or recompile all your software for ARM. That is, assuming there are actual advantages to ARM.
So far, no one seems to have bothered in spite of a lot of noise about the issue. This strongly suggests that this is in fact just noise, and ARM is either not yet ready, or is generally unsuitable for server applications.
Re: (Score:2)
I was just addressing the issue of power consumption. I assume that an architecture that's basically horrible in terms of design will have some implementation and power issues (as a rule of thumb).
The recompilation issue is entirely different, but an interesting point to bring up. Is it really that hard? From my experience, it isn't. The major difficulty in cross-compiling is with different environments, not the CPU architecture (except for the very lowest levels). But if you're dealing with server farms, e
Re:Just what Apple needs... (Score:5, Interesting)
It is not clear that they can beat future Intel CPUs on power usage, especially since Intel's manufacturing process leads the industry by a significant margin.
Everybody says that, but it's only true for the high performance / high power consumption process variant. It's not true for the lower power variant(s), which have some differences and are more tricky than the high perf ones (I'm not an expert on this but one issue for example is that LP needs larger wires to reduce resistance and power consumption. This requires in turn more precision to avoid shorts between wires. People who know more on this topic, please share. It's important to understand how the race can turn in the low power area). For low power Atom chips Intel is right now on 32 nm, while TSMC has been on 28 nm for a while now. It's a one year and half-node advantage for TSMC clients. And Samsung is also now on 32 nm (par). Intel announced they will speed up the availability of new finer processes for low power in the future, but based on their respective announcements Intel and TSMC would be on par for LP (we'll have to see how this turns out in practice...). This means that ARM clients can have a competitive process in the low power space today, and possibly tomorrow. It's likely that ARM clients would focus on many cores / low power servers for I/O bounds loads. They can be competitive there, and gain a foothold. Going to higher single thread performance can come later, it would be hard to attack Intel there in the short / medium term anyway. If you pick a fight, pick one you can win. And the ARM world has more experience in LP.
Re: (Score:2)
You make some great points here about process size, however one thing to remember is the Atom line processors are already 64 bit with very good performance to power draw ratios. Paired along side of Intel's graphics offers this allows for extremely low power / reasonably good performance devices to be produced in house.
I tend to agree with the others here who suggest this is a solution looking for a problem, that said, I'm always excited to see innovations which push Intel's glass prices down :)
Re: (Score:2)
Re:Just what Apple needs... (Score:5, Insightful)
I seriously doubt Apple will ever switch to ARM chips in OS X (not iOS) machines. They don't provide enough performance to run at the level of current OS X machines, not to mention that ARM64 is immature as hell.
No, but the threat of switching will provide that extra minute push to ensure Intel's continued refinement of Atom chips, and perhaps force them to release subsequent generations a year or two sooner than otherwise. Now that MS is actively promoting ARM-based tablets, Intel should be worried if not outright scared.
Re: (Score:1)
Indeed, with AMD's recent moves into the ARM ecosystem, I think Intel is pretty much the only one that isn't in on ARM. It remains to be seen what AMD's APUs are going to look like with an integrated ARM core, but I like the idea. I just hope they can pull it off.
Re: (Score:2)
Given the fact that Microsoft will probably sell no more than a few thousand of those tablets (to all tech review sites) I'd say Intel is probably safe.
Your point stands though.
Re: (Score:1)
Re: (Score:1)
Re: (Score:1)
Re: (Score:2)
Eh actually sorry, Samsung denied reports it decided to stop selling LCDs to Apple [forbes.com].
Re: (Score:1)
Re: (Score:2)
Apple is busy switching to these chips for their laptops/desktops. Coincidence?
Yes. Because when I'm looking for a server, I need to be able to RUN THINGS ON IT! You know, like exchange and our autocad plugin licensing program and our fax controller and our voicemail control program and active directory. I can't even think of anything an arm chip would help with other than being slow and not running anything. It wouldn't even work as a file server because then it'd have to run some RT-style version of server 2012 and Linux probably won't run on it either. What a pointless device.
Re: (Score:2)
Re: (Score:2)
Game servers may be problematic because afaict they are usually propietary.
Re: (Score:2)
Arm seems to be pretty strongly pushing linux support for 64-bit arm devices and I imagine the opensource server apps will pretty quickly follow. Samba4 will probablly run too if you want to host an AD tree.
It will be insteresting to see what MS does and whether they gimp the 64-bit arm version of windows in the same way they gimp the 32-bit one but even if they don't I wouldn't expect specialist propietry server apps to be ported any time soon. So for those uses arm is probablly out of the running for now.
What are these low power servers good for? (Score:4, Insightful)
I understand the implications of lower power for infrastructure reasons. Lower power means lower cost for power, lower cooling needs, etc. I get that. But what is the "Killer app" for these low power servers? Is it data warehousing? Simple web hosting? I can see these being useful for odds-and-ends servers in data centers with bigger iron for more heavy duty apps, but why is everyone jumping on this bandwagon?
Re:What are these low power servers good for? (Score:5, Insightful)
I/O bound servers, where a more powerful CPU would be mostly idle anyway.
Web hosting, data warehousing, networking infrastructure, and the like do fall that way pretty often, though obviously there are exceptions.
Re:What are these low power servers good for? (Score:5, Interesting)
I/O bound servers, where a more powerful CPU would be mostly idle anyway.
Didn't we invent SSDs to fix that...?
Re: (Score:3)
Re: (Score:2)
Re:What are these low power servers good for? (Score:4, Interesting)
The I/O limit could be on memory. Servers can have >1000 times more RAM than there is cache on a CPU chip. With enough threads and/or processor cores the cache hit rate drops, so that the memory bus is 100% busy. At that point a faster CPU gives no benefit, may as well us a low-power one.
Re:What are these low power servers good for? (Score:4, Insightful)
No, we invented SSDs to alleviate that. Even an SSD is much, much slower than the CPU. Hell, your *RAM* is much slower than the CPU; that's why CPUs have memory caches. Even with SSDs, there's a lot of load profiles where the CPU is not the bottleneck. A slower CPU that's cheaper, uses less power and generates less heat looks good to anybody with that kind of load profile.
Re: (Score:2)
I/O bound servers, where a more powerful CPU would be mostly idle anyway.
Didn't we invent SSDs to fix that...?
Even if the system is not bottlenecked by a HDD, you wouldn't need much any CPU power if the server is doing a lot of plain I/O, which is just copying bits around.
Re: (Score:2)
I/O bound servers, where a more powerful CPU would be mostly idle anyway.
How about distributed databases with high throughput and complex commit protocols?
Don't we need fast CPU's for that?
Re: (Score:2)
Hence the GP said, "though obviously there are exceptions."
He wasn't claiming that these chips would be perfect for everyone, just that there are *some* areas where they would be.
Re: (Score:2)
Re:What are these low power servers good for? (Score:5, Funny)
Think of the colourful charts - a new vision of fast ssd's, new ARM, new streamlined code and huge drops in power costs* when doing some types of math and not using HD's.
Find some art of a smiling admin and photoshop it all together.
Invite managers to lunch and sell them the low power, always on, expandable, low cost, union free remote admin upgrade, effortless cloud future - now at a super low price if you sign up today.
Then up sell the users on your green server, green power supply and find some art of a happy polar bear.
Its like selling powerpc to the young and dumb all over again.
Re: (Score:2)
These ARM servers are not for the general public. A lot of servers now go to the Facebook, Google and Amazons. These guys run their own stacks based on open source, so are not much tied to any ISA. Linux based software run fine on ARM. And they have a lot of loads that are I/O bounds (network mostly), so no need for huge CPU. And costs are critical, both in term of cost of hardware and power consumption (direct and cooling)
Re:What are these low power servers good for? (Score:5, Informative)
* DNS servers (if you aren't virtualizing stuff)
* email servers (if your spam scanning is external)
* some database servers (generally io bound not cpu bound, tho it of course depends on the nature of the queries)
* simple web hosting (stuff like a CDN serving static files needs almost no CPU)
* monitoring servers
* Camera/surveillance servers (video processing is mostly done by dedicated chips on capture cards)
Really, most servers are not CPU bound these days and would probably benefit from many low-clocked cores than few high-clocked ones. They are exceptions of course, that is why we have super-computers at the other extreme.
Re: (Score:2)
* email servers (if your spam scanning is external)
* some database servers (generally io bound not cpu bound, tho it of course depends on the nature of the queries)
Where are these servers not CPU intensive. Even in a small business your most CPU intensive servers will be mail and database.
Things that ARM chips would be ideal for.
* File server appliances
* Security appliances
* Web server appliances
* Networking appliances (DNS, DHCP, Directory Services)
You might notice the word "appliances" comes up a lot, well ARM/Linux is already used in a lot of these appliances.
The one that ARM would be ideal for I havent seen (so it probably exists and I havent seen it)
Re: (Score:3, Interesting)
95-98% idle
Anti-Spam server:
70-45% idle
These are both ISP servers, with many thousands of active accounts.
In both cases having more, slower cores would be better than a few faster cores.
Re: (Score:2)
I dunno, I'm having trouble seeing what gap they fill. In terms of low powered units, well we have those already. They often do use ARM CPUs (or MIPS), with other bits integrated on them, and they work fine for consumer shit. When you start to talk higher end, you need bigger systems.
Like if you want a simple little home NAS type of thing, it might ship with a BCM4718 and do just fine. However when you start stepping up to enterprise filers, you need more power. You find NetApps use Intel and AMD CPUs as an
Re: (Score:1)
It's actually the byte size that matters. Chomping 64 bits per cycle means more data per instruction. You really don't need any of the fancy intel instruction set or construction set for just plain raw processing.
Re: (Score:3, Informative)
Pedantic: yes the GP probably meant wordsize, but byte is not by definition 8 bits. Of course you're unlikely to encounter different byte sizes these days, but still. See http://en.wikipedia.org/wiki/Byte [wikipedia.org]
Re: (Score:1)
Yes you are both right. Word size was what I was after. And I did know of funky byte sizes, but my memory is getting old and crackly.
Re: (Score:1)
Who cares about ARM!
From previous slashdot CPU circle jerk articles the Cell processor should be in everything now! RIP x86!
Re: (Score:2)
I'd love to replace my server with a low-power ARM type one (Debian runs on ARM, right?). First of all, remember that there are many many more uses and installations of servers than in server farms and data centres.
My server is not doing much work, though it has many different jobs. It's running a web site that has a couple dozen hits a day maybe. It's a file server (NFS - for the home directories, and handling backups), Kerberos authenticaion, e-mail/SMTP, LDAP, etc. And it's for just two workstations, and
Re: (Score:2)
Re: (Score:2)
And the indexing for quick searching. That's what takes quite some effort, too.
Re: (Score:2)
What do you do for SPAM? Running a small (less than 10 users) email system over the years, I've had to upgrade from a dual PII to a dual PIII and most recently just got an i7. To be fair I didn't need to get the i7, but the entire system was cheap and the dual PIII had problems that I didn't want to investigate (most likely bad RAM).
Postfix+mailscanner+spamassassin are not cheap to run! Dspam is maybe a lot lighter than spamassassin. But once you have an active mailserver on the internet you get signifi
Re: (Score:2)
The first 90% or so of spam is stopped by greylisting on SMTP level. Yes it delays mails from new senders a bit, but in 99.9% of those cases I'm not expecting it, and am not waiting for it, so that doesn't really matter. And by far most of the mails that I receive are from regular contacts anyway which are accepted instantly.
The last 10% that does come through amounts to some 30-40 spam per day on my account, and far less on my staff's account (which is not plastered all over the place). The number of e-mai
Re: (Score:2)
Remember now (Score:5, Insightful)
The new Google Nexus phones are shipping with 2GB of ram, and its conceivable that tablets will being shipping with > 4GB of ram within a few years. It just looks like Samsung is covering their bases for the future.
Re:Remember now (Score:5, Informative)
The recent 32-bit ARMs supports LPAE, so you can have over 4GB no problem. That's still running a 32-bit address space per app, which would probably still work fine for a mobile environment.
Re:Remember now (Score:4, Insightful)
Re: (Score:2)
Re: (Score:3, Informative)
Umm, you're still processing a single item of data per cycle, but it's now 64-bit long instead of 32. Performance increases if you can process 64 bit as a vector of 2x32/4x16/8x8 bit values, which you could do before with NEON for ARM or MMX/SSE for x86.
Extra addressable space doesn't matter for most tasks, some, like DBMS, do benefit from it though.
Biggest performance increase from new 64-bit architectures, applicable both for x86_64 and ARM64, is bigger register set - you don't need as much memory accesse
Re: (Score:2)
It's not that simple. 64bit instructions can handle more data per cycle than 32bit ones, so there is an increase in performance whenever you handle large amounts of data and/or large numbers
The first is that the size of the address space corresponds to data size. NEON, the ARM vector instruction set, can already perform operations on 64-bit integer or floating point values[1]. This is even true on x86, where you have 64-bit operations that work on a pair of registers. The advantage is that you have 64-bit registers, so you don't need to use two for each 64-bit operation (6 of your 14 GPRs on ARMv7 if you want two source and one destination, comp
Somewhat off-topic, but... (Score:1)
Address extensions are a pain (Score:2, Insightful)
While it is a workable hack to support more than 4GB of RAM without expanding the virtual address space, it is a hack. Much better to just g 64-bit and call it good. Hence I imagine that's what you'll see with mobile devices. When they start to need more RAM, they'll shift to 64-bit.
Same shit with desktops and many Intel servers. Intel supported PAE, and Windows implemented it as AWE, with 32-bit chips. Was never very popular though, due to the limitations and performance issues with paging. Now, with actua
Re: (Score:2)
PAE is a hack. It works, but you should avoid it if you damn-well can. And it sounds like we all can avoid it.
Re: (Score:3)
It's that they're missing ethernet ports and are low on storage, but a modern phone is more than powerful enough to serve as a simple server.
Re: (Score:3)
Re: (Score:2)
Re: (Score:3)
..and sammy would probably license any chip arm makes anyhow, if only to just check it out.
Re: (Score:2)
Did you notice that the website has not been touched since 2010?
I am not sure how the design may progress with the current status. Is there any forks or active contributors?
Commodity ARM 64 bit server motherboards (Score:3)
Re: (Score:2)
Perhaps if Linaro's work bears fruit, that will be a realistic vision. Right now support for ARM-based devices is all over the place and is only now being unified in the kernel, let alone boot loaders etc.
Re: (Score:2)
If this thing does crypto well, I could use a quad-core ARM chip at home.
But I doubt those chips are targeted at home or small business. They'll probably have much more than 4 cores, to achieve similar throughput to the current x86 offerings.
MIPS was doing it 12 years ago (Score:2)
MIPS and ARM are very similar Instruction Set Architectures. While I've only taking a cursory look at the new ARM64, it doesn't seem as clean as MIPS64. So with the same level of optimization, MIPS should be able to get a better performance per watt and higher IPC. SiByte had working MIPS64 CPUs 12 years ago. MIPS used to dominate the TOP500, but recently Intel has left them in the dust. So I don't see how Samsung is going to do any better with ARM.
Then again, if x86 can become the IPC leader, any ISA has
I can confirm they are (Score:3)
Re:I can confirm they are (Score:4, Informative)
Because "we require" rarely means "we won't touch you with a bargepole unless you have". It's there to weed out the chaff who think they're not good enough or important enough to apply.
I've applied for numerous jobs that have "required" things like MCSE's and A+, and first-class degrees and I clearly state that I don't have them, but what I do have is X amount of experience doing Y.
The bright employers (i.e. the only type you *want* to work for anyway) pick it up and say "Oh, right, he's probably spent so long DOING the job, he never got around to paying the certification tax on a bit of paper to say he could do it." or "He was out earning a wage in this sector while our own guys were still in university playing with microcontrollers". The bad ones, of course, shove it off and it gets lost in the HR department because it "doesn't meet criteria".
I've also advised people to ignore this sort of thing in the past, so long as you *CAN* put forward a reasonable case of being suitable for the job anyway, and it's never perfect (there is no magic way to get a job) but it's helped a lot of them to get positions they didn't think they were good enough for. How many of the industry founding fathers and visionaries had PhD's or Masters? Nowhere near all, and they still got there.
Don't blatantly ignore high requirements, just substitute what you have instead (and, if you like, in your covering letter explain that: "Although I notice that the job requirements include X, I feel that my extensive expertise in position Y performing task Z should be sufficient to prove that I'm capable of performing to the standards required") if you think you have a shot of doing the JOB.
Applications processes are mainly about weeding out the vast number of applicants, but secondarily they are about YOU weeding out the vast number of jobs available. Because if your employer can't see that you can do the job, just because you have an absence of certain desired letters after your name, you probably don't want to work there anyway (and they probably will ignore your application, but the chances that they veto you for future posts because of your politely-worded ambition are vanishingly small... and again, those sort of people you just don't want to work for anyway).
That may be *why* they bothered emailing everyone. Because they aren't just interested in PhD's, but they just want a high standard of applicant. One who has those qualifications, or one who has the skills and knows how to get through a job application process by playing on them.
The worst that happens is they say No, and keep your information on file for future reference. The chances it will prejudice any future applications - a concern I've heard from the people I've given personal advice - are basically zero (do you really think HR departments keep years and years and years worth of applications that they are already TRYING to narrow down to just a few candidates from thousands and somehow and check them for every post? No.).
And, you never know, they might just say "Well, actually, you're not right for this particular position, but we are just about to advertise for X as well, and that's look more suited to you."
In job-hunting, there's nothing wrong with being ambitious, so long as you're honest. And even if they offer it you and you don't like the idea of working in a crowd full of bitter PhD's, or it's not better than your current job, again - you can so "no" just as easily as they can.
Re: (Score:2)
Oh I agree with what you're saying but 1) the job is in Dallas, TX. 2) In my experience, these large companies are very hard to get into w/o meeting the basic requirements. If you know someone, you can get into them, but I bet the application would never make it past HR. I'm a pretty spot on match for 90% of their requirements, maybe more. But I am not going to bother applying for a job that is somewhere I don't want to live, and is also likely just a waste of my time. I have a job already and am only c
Cheap servers? (Score:3)
10 machines with say 4 cores each and 4G each would give a cluster with 40 cores and 35 gigs of in ram storage; all for around $1000. Plus anything by ARM would probably be pretty good efficiency-wise.
Due to redundancy and the extreme capacity adding flexibility I would much prefer $99 machines to just a boring regular server with just an big old ARM chip. Or even a boring regular server with a pile of ARM chips.
Re: (Score:2)
So what you're saying is "Imagine a beowulf cluster of these things!"?
Re: (Score:2)
Kim Possible is the Supreme Kim. Cute as hell too.