Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

ARM Unveils Next-Gen Processor, Claims 5x Speedup

timothy posted more than 4 years ago | from the and-hammer dept.

Upgrades 283

unts writes "UK chip designer ARM [Note: check out this short history of ARM chips in mobile devices contributed by an anonymous reader] today released the first details of its latest project, codenamed 'Eagle.' It has branded the new design Cortex-A15, which ARM reckons demonstrates the jump in performance from its predecessors, the A8 and A9. ARM's new chip design can scale to 16 cores, clock up to 2.5GHz, and, the company claims, deliver a 5x performance increase over the A8: 'It's like taking a desktop and putting it in your pocket,' said [VP of processor marketing — Eric Schorn], and it was clear that he considers this new design to be a pretty major shot across the bows of Intel and AMD. In case we were in any doubt, he turned the knife further: 'The exciting place for software developer graduates to go and hunt for work is no longer the desktop.'"

Sorry! There are no comments related to the filter you selected.

Give ARM a chance. (2, Insightful)

Anonymous Coward | more than 4 years ago | (#33531750)

I for one certainly hope that ARM gets a chance in the more mainstream market; the more competition for Intel, the better!

Re:Give ARM a chance. (5, Interesting)

PCM2 (4486) | more than 4 years ago | (#33531778)

How much more mainstream can it get? ARM is everywhere. It's in your iPhone -- probably every single phone out there, actually -- in tablets, in NAS boxes, in DVD players... countless applications. If you mean it should compete with Intel CPUs for PC processors, on the other hand, one impediment may be that ARM is (at least at present) a 32-bit architecture.

Re:Give ARM a chance. (1)

Vintermann (400722) | more than 4 years ago | (#33531878)

The best bit: ARM chips are everywhere, and they are presumably very friendly to implementing Acorn Archimedes emulators. Archimedes on your fridge, yeah!

Re:Give ARM a chance. (1)

jimicus (737525) | more than 4 years ago | (#33531948)

There are already perfectly good emulators that run quite happily on x86, but getting hold of RISC OS is rather trickier unless you've bought and paid for a license (which is surprisingly expensive considering it's got very little modern software available, and these days is only really of any interest as an exercise in "how to design a very small OS for a 1980's version of a chip without many of the things we take for granted these days such as multi-user security or protected memory")

Re:Give ARM a chance. (1, Informative)

Anonymous Coward | more than 4 years ago | (#33531978)

http://www.riscosopen.org/

Re:Give ARM a chance. (1, Insightful)

Anonymous Coward | more than 4 years ago | (#33531990)

Yes, the £0.00 pricetag of the ROOL branch is horribly expensive in this modern age.

Re:Give ARM a chance. (2, Funny)

X0563511 (793323) | more than 4 years ago | (#33532096)

No kidding, isn't that like $1000?

Re:Give ARM a chance. (1)

ciderbrew (1860166) | more than 4 years ago | (#33532218)

add the sales tax and the import and export duty on top too. :(

Linux Support for the ARM Architecture (1)

Futurepower(R) (558542) | more than 4 years ago | (#33532228)

Re:Linux Support for the ARM Architecture (1)

jimicus (737525) | more than 4 years ago | (#33532246)

I meant software available for RISC OS, not ARM.

Re:Give ARM a chance. (2, Informative)

MemoryDragon (544441) | more than 4 years ago | (#33531994)

The cortex15 line extended the address range for memory to 40 bits which ought to be enough for the next few years.

Re:Give ARM a chance. (1)

Cyberax (705495) | more than 4 years ago | (#33532222)

Interesting. Do they have direct 64-bit addressing or do they use page mapping tricks?

Re:Give ARM a chance. (1)

Narishma (822073) | more than 4 years ago | (#33532392)

Think of it in terms of virtualization. The hypervisor has access to up to 1TB or memory but the individual OS instances are 32-bit and can only address up to 4GB.

Re:Give ARM a chance. (3, Interesting)

node 3 (115640) | more than 4 years ago | (#33532054)

How much more mainstream can it get?

I think he means in terms of being something consumers are aware of, like they are with Intel and AMD. Yeah, I think the contrast is being exaggerated more than a little bit here, as a lot of people don't really know about Intel or AMD, and vice versa it's not like nobody knows about ARM, but there definitely is a difference in mindshare here.

If you mean it should compete with Intel CPUs for PC processors, on the other hand, one impediment may be that ARM is (at least at present) a 32-bit architecture.

I can't speak for AC, but I think ARM netbooks would do the trick. Unfortunately, the longevity of the netbook market isn't exactly clear, and ARM netbooks implies Linux, which is even more uncertain a consumer market than Windows netbooks is.

But yeah, phones and tablets, ARM is where it's at for now.

Re:Give ARM a chance. (1)

devent (1627873) | more than 4 years ago | (#33532068)

Who cares if it's a 32-bit or a 48 or a 17 bit architecture? 64bit architecture is 20 years old on the desktop but right now nobody is using it anyway. If I get a Notebook with an ARM, which can run OpenOffice, Email, Firefox and maybe Flash, for half the price and have a battery life of 8 hours and more I really don't care what architecture it have.

Re:Give ARM a chance. (3, Informative)

dkf (304284) | more than 4 years ago | (#33532110)

64bit architecture is 20 years old on the desktop but right now nobody is using it anyway.

They're certainly using more memory than is practically addressable on 32-bit. Ordinary people do need that memory. They do work with large images. They do handle lots of data. They do have many things open at once. They do run large games. Not everyone needs it for everything, but being stuck with only 4GB of address space would really suck. (Luckily ARM isn't limited this way; cortex15 can address 1TB of memory directly, which is rather a lot more than anyone currently puts in a single machine at the moment.)

If I get a Notebook with an ARM, which can run OpenOffice, Email, Firefox and maybe Flash, for half the price and have a battery life of 8 hours and more I really don't care what architecture it have.

The apps are what people care about, yes. But many apps like to have lots of memory because they work with lots of data. (Funny, that...)

Re:Give ARM a chance. (1)

devent (1627873) | more than 4 years ago | (#33532412)

Like I said, 64bit architecture is 20 years old but nobody (or a small fraction) is using 64bit Linux or 64bit Windows.

Anyway, it would be a great start if I can finally buy any ARM notebooks. So far I couldn't see any of them.

Re:Give ARM a chance. (0, Redundant)

Alioth (221270) | more than 4 years ago | (#33532074)

ARM is incredibly prevalent - more ARM cores are shipped than what Intel and AMD ships combined. Many devices have multiple ARM-based CPUs.

I have a tiny gyro unit for one of my radio control helicopters. Guess what it contains?

Re:Give ARM a chance. (1)

dkf (304284) | more than 4 years ago | (#33532118)

I have a tiny gyro unit for one of my radio control helicopters. Guess what it contains?

Hmm. Let me see... PDP-11?

Re:Give ARM a chance. (1)

Kjella (173770) | more than 4 years ago | (#33532076)

If you mean it should compete with Intel CPUs for PC processors, on the other hand, one impediment may be that ARM is (at least at present) a 32-bit architecture.

I don't see that as a huge drawback for at least taking on the netbook market, or possibly extending the netbook market to an even lower price point. There's not been any significant push for more memory in recent years, in fact the 4x4GB DDR2 is mostly replaced by 6x2GB DDR3 as the "top of the line" at mortal prices.

By far the greatest challenge is software, with no Windows or Mac support you'd be pushing Linux. A linux with no option to run Windows software through WINE or virtualbox for those occasional needs. Or you're trying to rebuild the entire desktop around a new ARM-oriented system, which seems like a massive job even if ARM is already in use many places.

Re:Give ARM a chance. (1)

X0563511 (793323) | more than 4 years ago | (#33532106)

Unless Windows or Mac get their heads out from their asses and go cross platform. I'd prefer Linux myself, but either way it wouldn't be a bad thing. Wishful thinking all around.

oblig (-1, Offtopic)

Anonymous Coward | more than 4 years ago | (#33532130)

Im in ur aifone, mainstreemin ur arm.

Re:Give ARM a chance. (5, Funny)

imakemusic (1164993) | more than 4 years ago | (#33532134)

ARM is everywhere. It's in your iPhone [...] in tablets, in NAS boxes, in DVD players... countless applications.

Sorry, I wasn't listening. I was looking at the woman in the red dress.

Kahless (-1, Offtopic)

Anonymous Coward | more than 4 years ago | (#33531758)

Its to fast get rid of it.

And the electricity? (1)

wizzor (1321693) | more than 4 years ago | (#33531762)

I hope they don't also want us to put a mains lead into our pockets to power that beast.

Re:And the electricity? (1)

Neil Boekend (1854906) | more than 4 years ago | (#33531894)

From TFA: "at a similar energy footprint"

Re:And the electricity? (1)

DarkIye (875062) | more than 4 years ago | (#33531972)

...to the A8. Unimportant detail there.

No Mains required (1)

maroberts (15852) | more than 4 years ago | (#33532090)

As others have quoted, it delivers 5 times the performance of the A8 at a similar energy footprint.

You'd probably only require mains if it was a 16 core system in your pocket, as I doubt that the above performance/energy footprint is for 16 cores.

Docks (5, Interesting)

ozmanjusri (601766) | more than 4 years ago | (#33531764)

It would be a great time to develop a standards-based dock/charger platform so we could drop our phones/tablets into an adaptor and have them display on a large monitor and accept standard USB peripherals.

That would really shake up the Wintel alliance.

Re:Docks (1)

Twinbee (767046) | more than 4 years ago | (#33531850)

Can't you connect any of the portables via HDMI to a monitor already?

Re:Docks (1)

arivanov (12034) | more than 4 years ago | (#33531910)

You can, however you have to play with cables. Cables != dock. Geek != consumer.

Re:Docks (1)

X0563511 (793323) | more than 4 years ago | (#33532114)

Funny, most consumers I know don't have any problem connecting chargers and/or audio cables. An HDMI isn't any different...

Re:Docks (1)

Cwix (1671282) | more than 4 years ago | (#33531950)

I know the droid x does hdmi. Its the only one ive heard of having it.

Re:Docks (3, Informative)

Tumbleweed (3706) | more than 4 years ago | (#33532100)

I know the droid x does hdmi. Its the only one ive heard of having it.

EVO 4G has it.

Re:Docks (1)

obarthelemy (160321) | more than 4 years ago | (#33532064)

which is not quite the same as a standard dock/charger with keyboard,mouse, lan, sound, charger... connectivity.

Re:Docks (2, Informative)

bytta (904762) | more than 4 years ago | (#33532168)

Can't you connect any of the portables via HDMI to a monitor already?

GSMArena lists 13 different phones with an HDMI port, and the trend seems to be increasing. http://www.gsmarena.com/results.php3?sFreeText=HDMI [gsmarena.com]

Re:Docks (1)

naranek (1727936) | more than 4 years ago | (#33531912)

No need for a dock. Just plug the monitor to HDMI output. You can use USB mouse and keyboard if you want, or plug an USB hub to the USB port to use wired controllers instead.

It would be cool though, if the device could recharge itself using the HDMI connection.

Re:Docks (3, Interesting)

bgarcia (33222) | more than 4 years ago | (#33531914)

It would be a great time to develop a standards-based dock/charger platform so we could drop our phones/tablets into an adaptor and have them display on a large monitor and accept standard USB peripherals.

Not USB. I want a BlueTooth keyboard & mouse.

I'll accept an HDMI monitor connection for now (some phones have HDMI already), but eventually that should be wireless as well.

When that happens, I'll have no need for a laptop.

Re:Docks (3, Insightful)

nbharatvarma (784546) | more than 4 years ago | (#33531992)

Once you start getting consumers used to no-buttons-no-wires sort of a thing, there's no stopping.

I think we will see monitors / tv displays coming with an in-built wireless adapter, streaming content from the mobile which is lying on a charging pad.
The flip side is that we will get more and more locked on to proprietary content platforms.

Re:Docks (1)

hitmark (640295) | more than 4 years ago | (#33531976)

https://secure.wikimedia.org/wikipedia/en/wiki/PDMI [wikimedia.org]

You will find this at the bottom of the Dell streak, and most likely the Samsung Galaxy Tab as well. And i suspect the Toshiba Folio 100 may also sport such a connector.

Re:Docks (1)

X0563511 (793323) | more than 4 years ago | (#33532128)

Off-topic...

But did you really just link an SSL wikimedia page to slashdot? Not very kind of you.

I'd also be curious as to why you'd browse something like wikipedia via SSL, but I tunnel traffic via SSH so I don't have much to talk here either :P

Re:Docks (1)

bsDaemon (87307) | more than 4 years ago | (#33532298)

If you install the HTTPS-Everywhere plugin from the EFF, Wikipedia is one of the sights on the default encryption list. I suspect that's what he did.

Oh stop (5, Insightful)

Sycraft-fu (314770) | more than 4 years ago | (#33532052)

Not with the idea of a standards based chargers but this "Wintel alliance," crap. There is no such thing. x86 chips are used for desktop computers because they are the only things that have been cheap, common, and powerful. MS has no special interest in pushing Intel. DOS, and thus earlier Windows versions, were tied to x86. When NT came out, they abstracted it and indeed you could get NT4 for x86, PowerPC, and Alpha. Let me give you a hint how well those other versions sold. As such, they were discontinued.

Also when it came to 64-bit for the desktop time, MS cast in with AMD. Intel was pushing Itanium, which MS does support on their server OSes, but AMD's 64-bit extensions, called amd64 internally by the Windows tools, were what was used for the desktop. So you can get Windows 7 in x86 and x64 variants, and Server 2008R2 in x64 and IA64 variants.

Now for Windows CE (also the basis for Windows Mobile), their mobile/embedded OS, well then that runs on all sorts of things. x86, MIPS, ARM, and SuperH. Again, more could be added, this is just what is supported as that is what there is currently a market for.

What it comes down is they support the architectures that are used in the markets their OSes work in. There is no ARM version of Windows 7 because there are no ARM desktops that demand it. Porting an OS to a new architecture and maintaining it is not a zero effort task, so it isn't done unless it is worth it (unless it is NetBSD :D).

Also the reason x86/x64 continues so strong on the desktop is it works so well. It provides binary compatibility will all your old apps, and the CPUs that use it are fast and cheap. Thus far, I've seen nobody who can beat Intel and AMD in that market. Sure there are higher end CPUs that cost more and use tons more power, like Itanium and Power7. There are also chips that use less power and are cheaper, the ARM. However I've yet to see the chip that does better in their market, as in can do more operations with the same or less power and costs less.

So you want ARM desktops? Well first an ARM CPU that is competitive in that market has to come out. Competitive, please note, doesn't mean "Barely can compete with the low end." I'm talking something that makes you say "Wow, that is faster than my i5, and for less money." Then maybe there's interest. Should ARM desktops start to become popular, you can be pretty confident MS would move Windows over to them.

But please, stop pretending like there's some sinister conspiracy to keep alternate architectures down. There are only two reasons for the x86 dominance:

1) Compatibility. It is far nicer to have a chip that works with your old stuff. People will default to what's compatible unless given a good reason. I'm not going to pay the same amount for a CPU with the same performance that doesn't run my apps as for one that does. So whoever wants to break in to the market has to offer a good reason. Less cost, more performance, etc. Probably still need have a good emulators to support older apps.

2) Intel is really, really, good. Everyone likes to hate on Intel because they are big and there's automatic underdog love on Slashdot, but they are good at what they do. They spend a ton on R&D and the result is they are almost always ahead in terms of fabs and their CPUs tend to offer great performance for the money. Yes, they've bad problems, Netburst (P4) was an example, but currently it is impossible to touch the Core i series. They are fast, do a lot given their power budget, and have a good price.

Re:Docks (1)

the_womble (580291) | more than 4 years ago | (#33532186)

All "data enabled" phones in the EU are going to be chargeable through a micro-USB based standard socket.

Re:Docks (1)

PhilHibbs (4537) | more than 4 years ago | (#33532260)

Maybe - Apple agreed to this last summer, but still brought out the iPhone 4 with only their proprietary connector.

DisplayPort (0)

Anonymous Coward | more than 4 years ago | (#33532238)

1. Simple connection, especially optical
2. Includes more video bandwidth than you could ever need
3. Supports USB for keyboard/mouse
4. Supports audio out

Re:Docks (1)

Thanshin (1188877) | more than 4 years ago | (#33532282)

That would really shake up the Wintel alliance.

As soon as smartphones have enough power to run excel, word and outlook at (current - 5years) office speeds, office wintel will be replaced on a phone price basis.

We'll still have desktops for photo/video edition, gaming, and many other things that can still burn any amount of computing power.

And, some years later, someone will invent the direct brain connection and we'll go back to needing massive hardware beasts to process our home virtual worlds.

Snoop filtering? (0, Redundant)

CarpetShark (865376) | more than 4 years ago | (#33531766)

The block diagram:

http://img.hexus.net/v2/channel/news/2010/sep/armeagle3-big.jpg [hexus.net]

refers to a "snoop control unit" and "snoop filtering". Is this some kind of DRM?

Re:Snoop filtering? (0, Redundant)

CarpetShark (865376) | more than 4 years ago | (#33531792)

Answering my own question: I guess it is DRM amongst some processor scheduling/bus control stuff, yeah. There's a reference to "data security using the TrustZone memory model" below:

The Snoop Control Unit (SCU) connects one to four Cortex-A5 processors to the memory system through the AXI interfaces. The SCU maintains data cache coherency between the Cortex-A5 processors and arbitrates L2 requests from the processors and the ACP. The SCU programmers model also includes support for data security using the TrustZone memory model.

-- Cortex-A5 MPCore Technical Reference Manual - 2.1.8.: Snoop Control Unit [arm.com]

Re:Snoop filtering? (1)

Vintermann (400722) | more than 4 years ago | (#33531868)

The TrustZone memory model appears to be a MMU extension of sorts. It's used for supporting all sorts of operating system security at the hardware level, not just DRM. If your OS doesn't care about DRM, the processor won't, either...

Re:Snoop filtering? (1)

CarpetShark (865376) | more than 4 years ago | (#33531936)

Yes, but if the OS does care, on an embedded device that you can't bypass the OS startup on, then you've little hope of reverse-engineering drivers etc.

Re:Snoop filtering? (0)

Anonymous Coward | more than 4 years ago | (#33532120)

Well, then don't buy that embedded device.

Re:Snoop filtering? (4, Informative)

TheRaven64 (641858) | more than 4 years ago | (#33531998)

No, nothing at all to do with DRM. Snooping refers to checking the contents of other caches for cache coherency. Cache comes from the French, meaning hidden - it is memory that the programmer doesn't see directly, so the CPU has to act in exactly the same (programmer-visible) way as if it were not there. This is pretty simple when you have just one core, but when you have more than one it becomes difficult.

If you have two threads, on different cores, both accessing the same memory, then each will try to pull it into the memory into the cache. This is fine, as long as both are reading it. When one writes to it, the copy in the other core's cache must be updated or the two threads will have an inconsistent view of main memory. This is called cache coherency. The snoop control unit is responsible for all of the cache-to-cache communication. Because ARM cores typically live on a die with other units that share the same RAM, it is also responsible for ensuring that the caches remain consistent with modifications to RAM by the other coprocessors.

Re:Snoop filtering? (0)

Anonymous Coward | more than 4 years ago | (#33532294)

Many people don't know this, but Snoop Dogg is actually an avid anti-DRM hacker. CSS, AACS, BD+, Snoop's all up in dat shizzle, and ARM knows it. Hence, the snoop control unit and snoop filtering

Was it ever the desktop? (3, Interesting)

Nursie (632944) | more than 4 years ago | (#33531794)

I thought most of the interesting stuff took place on the server?

Well either way, I wish them luck. Having competition and diversity in the processor market is a very good thing and forces everyone to step up to the mark, benefiting everyone.

And if they've managed to keep the power envelope down then even better.

Re:Was it ever the desktop? (2, Interesting)

dbIII (701233) | more than 4 years ago | (#33531968)

If it has 16 cores and doesn't use a lot of power it will be on the server or at least in RAID cards.

Re:Was it ever the desktop? (1, Informative)

Anonymous Coward | more than 4 years ago | (#33532398)

RAID cards? Of all things, why would you do that?

XOR calculations, you say? Well, how does having 16 cores help with that, one core is enough with sufficient memory bandwidth. So you say increase number of pins to add bandwidth? Well, packaging issues will arise.

It's a common misconception that RAID cards have powerful processors. They do not, server can XOR 5000-20000 megabytes per second on CPU accessing main memory, while most RAID controllers anywhere between 200 and say, 2000, for RAID5 or RAID6. RAID6 is more work in theory, but in reality takes on slightly longer time to compute, because it's a bus limited problem, and in practice your XOR data set will remain in CPU cache.

Of course combination(s) of RAID 0 and 1 you don't need any XORs at all. You might need additional checksum computation, unless your hardware does it for you for "free" (and many controllers just don't bother).

There's high likelihood the data that was just transferred from disk will very soon be needed by kernel or user process anyways. Conversely for writing, data was probably already in CPU cache for exactly the same reason. In those cases CPU XOR rate is actually significantly higher than in isolated simple first case.

When server does the calculations, it can also reliably verify data integrity of data after read DMA over the bus, and you get this nearly 'for free' due to CPU cache.

RAID controllers simply do not require much processing power. Of course SSD disks will change the equation a bit, but then you just need more bandwidth, you don't need other cores competing for same bandwidth.

Only good reason to have such a controller in the first place is just battery backed up cache they contain to improve database insert/transaction rate.

I think it would be about time to make the controllers simple 'dumb' devices and have a separate battery backed up cache as a module on a special connector on server motherboard or PCI express slot.

Re:Was it ever the desktop? (1)

TheRaven64 (641858) | more than 4 years ago | (#33532006)

This is a laptop / server chip design. It fits into ARM's product line above the A9 and provides features that are more interesting on the server than anywhere else. It is also likely to have a larger power envelope than the A9.

Re:Was it ever the desktop? (1)

Moraelin (679338) | more than 4 years ago | (#33532372)

That's exactly what I was wondering too. I'm pretty sure I'm not going to see a company putting its WebSphere application server or Oracle or DB/2 database on a cell phone or netbook any time soon. Nor (I hope to the elder gods) where they'll make their personnel enter the data or program those servers on cell phones instead of some kind of desktop.

Granted, some of those servers may or may not have ARM CPUs, but then that's not what he's implying there. And a lot are running on PowerPC already. The server world is somewhat less fanboyish about either AMD or Intel.

Does it have 64-bit addressing? (4, Interesting)

Tapewolf (1639955) | more than 4 years ago | (#33531796)

32-bit addressing was seriously impressive in 1987, compared to Acorn's then-current machine with 32KB, including video memory. But now even smartphones are starting to come with 512MB, 1GB of memory. Does ARM have a strategy for getting past 4GB?

Re:Does it have 64-bit addressing? (5, Interesting)

forkazoo (138186) | more than 4 years ago | (#33531860)

32-bit addressing was seriously impressive in 1987, compared to Acorn's then-current machine with 32KB, including video memory. But now even smartphones are starting to come with 512MB, 1GB of memory. Does ARM have a strategy for getting past 4GB?

From what I understand, the A15 will support 40 bit physical addressing. So far, I'm not certain if that's segmented, or sane. I heard a claim that in a multicore setup, different cores might be configured with distinct memory controllers so that the various cores need not address strictly the same 40b worth of memory, enabling some sort of NUMA setup. Dunno if that will ever happen in practice. 1 TB RAM is likely to be sufficient for the commercially relevant life of the CPU.

Re:Does it have 64-bit addressing? (3, Informative)

hitmark (640295) | more than 4 years ago | (#33531996)

Combined with the virtualization support, i suspect one could allocate the different cores to different OS images and use the address space to slice up the RAM as needed. Consider having a rack of these in a web hotel, with each core running its own server instance. Hell, given that one can fit a ARM SoC on a DIMM, one could make such a rack very easily expandable with the correct mother/logic-board.

Re:Does it have 64-bit addressing? (4, Informative)

MemoryDragon (544441) | more than 4 years ago | (#33532042)

It will come down to, if you know the old intel address modes to things called segments, which means you have so called segments of max 4 gigs you have to juggle around. This system on assembly level was quite evil because you had to shift around with segments for code data stack and whatsoever.

The + side it offered another layer of code injection protection. But for complexity reasons it was very unpopular, and when the segment spaces became big enough most compilers just rolled one huge segmetn and placed code and data there.

For a processor designer this approach however is very elegant because they can increas the memory range ad inifnitum while keeping the register size the same and thus keeping backwards compatibility.

From a programmers point of view segments are hell because you never know when you run into the boundary set by the segment and then the shuffeling beings. Also if you have data bigger than the segment you have to press it into multiple ones.

I am not sure if I like the way arm is going there just to keep the backwards compatibility. One point in time they will have to break it to keep the power consumption low (Intel just added on top of everything the next fluff), and I guess given their current success in the mobile phone area, they shun it a little bit to roll out the next breach in backwards compatibility like they had done in the past.

It's not _that_ bad (1)

Moraelin (679338) | more than 4 years ago | (#33532394)

Actually, it's not _that_ bad for most applications.

I have actually programmed assembly back in ye goode olde days of 16 bit CPUs and segment registers, and the reason it was evil was that you ran into that limit all the time. Even the most trivial operations had to juggle registers. You couldn't even process a 640x480 pixel image in 16 colours without running into segment maths. (Incidentally that aforementioned image would need about twice the memory you could address with 16 bits without segment maths.) Even addressing two pixels on the same row or column could mean needing to change the segment first.

By comparison 4 gigabytes is still a lot. There are precious few applications where you need more than 4 GB in a single array, which is when you'd actually need segment maths.

And frankly those are nonexistent in the normal desktop or even vanilla web page world, because they have to be able to run on machines which don't even have that much.

Just having over 4 GB total data is not the old hell. If each individual piece of data is smaller than 4 GB, you can just have the segment be part of the pointer, and only need to load it once. You don't need to do more segment maths just to get the 65537'th byte of that buffer.

Don't get me wrong, it's still more elegant to not have to worry about segments at all. But the alternative is not anywhere near the old hell.

Re:Does it have 64-bit addressing? (1)

thue (121682) | more than 4 years ago | (#33532194)

But what if you want to memory-map your 2TB Hard disk as virtual memory?

Re:Does it have 64-bit addressing? (1, Informative)

Anonymous Coward | more than 4 years ago | (#33531874)

The strategy for ARM to address more than 4 GiB RAM is called LPAE and it is as hackish as it sounds [tgdaily.com] .

Re:Does it have 64-bit addressing? (1)

minasoko (710100) | more than 4 years ago | (#33531880)

Does ARM have a strategy for getting past 4GB?

Yes. [theregister.co.uk]

Re:Does it have 64-bit addressing? (4, Informative)

romiz (757548) | more than 4 years ago | (#33531896)

According to ARM's web site [arm.com] , there are 'Long Physical Address Extensions (LPAE)', that allow addressing 1 TiB (40 bit). The marketing schematics for the processor mentions a "Virtual 40b PA" for each CPU.

Unfortunately, the detailed A15 documentation is not available yet, so we're left to speculate over what this means. But at the same time, the supported architecture remains ARMv7 and there is no hint of any major changes on the instruction side. An easy implementation would use a MMU with 40-bit physical addresses to map this amount of memory, but the process size would remain at 4 GiB to avoid any drastic change to the programming model.

Re:Does it have 64-bit addressing? (1)

Tapewolf (1639955) | more than 4 years ago | (#33531932)

Unfortunately, the detailed A15 documentation is not available yet, so we're left to speculate over what this means. But at the same time, the supported architecture remains ARMv7 and there is no hint of any major changes on the instruction side. An easy implementation would use a MMU with 40-bit physical addresses to map this amount of memory, but the process size would remain at 4 GiB to avoid any drastic change to the programming model.

Yeah, that's the picture I'm getting from the collection of links provided to my query. A 64-bit address register would have been nice, but it looks more like they're aiming this at virtualisation, e.g. to provide multiple 'instances' of a 4GB address space to several VMs.

Re:Does it have 64-bit addressing? (3, Insightful)

MemoryDragon (544441) | more than 4 years ago | (#33532004)

Yes back to segmentation :-) but seriously it is good enough for the lifetime of this processor which is 2-4 years and good enough for many but not all server purposes.

Re:Does it have 64-bit addressing? (1)

roy23 (159499) | more than 4 years ago | (#33531952)

It has 40-bit addressing, which give it access to 1TB address space

Re:Does it have 64-bit addressing? (1)

jimicus (737525) | more than 4 years ago | (#33531960)

Bit of a shame, then, that in 1987 it didn't support 32-bit addressing (IIRC instructions were 32 bits wide but the address bus was only 24 bits) and even if it did, it relied on a separate memory controller.

The MEMC1 in the early Archimedes models supported.... oooh, 1MB of RAM. You could upgrade the memory (no SIMM sockets then, you had to have it soldered on), you also had to upgrade the chip to a MEMC1a, which supported 4MB.

(note: much of this is a hazy recollection - constructive correction welcomed!)

Re:Does it have 64-bit addressing? (0)

Anonymous Coward | more than 4 years ago | (#33532032)

Addressing was 26bit in early ARMs.

MEMC1 supported 4MB, I believe the MEMC1a was more of a bug fix and offered some performance improvements.

Re:Does it have 64-bit addressing? (1)

MemoryDragon (544441) | more than 4 years ago | (#33531984)

They extended the addressing to 40 bit... but only for the memory, the register addressing still is 32 bit for backwards compatibility reasons.

Re:Does it have 64-bit addressing? (5, Informative)

miffo.swe (547642) | more than 4 years ago | (#33532154)

The 4 GB barrier was overcome a long time ago on 32 bit systems. The reason people still think its a problem is because Microsoft decided you as a customer shouldnt be able to use more than 4 GB memory on 32-bit since Windows 2000 . The limitations are solely artificial today on Windows 32-bit but linux gladly handle any memory you toss at it.

Excellent article explaining the issue:
http://www.geoffchappell.com/viewer.htm?doc=notes/windows/license/memory.htm [geoffchappell.com]

I have also yet to see a benchmark where 64-bit in itself gives significant advantage outside large calculations an simulations.

Re:Does it have 64-bit addressing? (1)

Tapewolf (1639955) | more than 4 years ago | (#33532204)

The 4 GB barrier was overcome a long time ago on 32 bit systems. The reason people still think its a problem is because Microsoft decided you as a customer shouldnt be able to use more than 4 GB memory on 32-bit since Windows 2000 .

Er, ARM is not an x86 derivative. This new revision does seem to have added some flavour of PAE, but AFAIK 4GB is an absolute limit for all currently-manufactured ARM microprocessors.

Re:Does it have 64-bit addressing? (1)

pstorry (47673) | more than 4 years ago | (#33532356)

I think you'll find it's giving significant advantage.

To the bank accounts of Intel and AMD, as it's giving people (often gamers) a "reason to upgrade"... ;-)

Generally, though, I'd agree with you.

When I last bought a machine, it was before the time of Windows 7. 64-bit was an option, but not a good one. So I went with 32-bit and 4Gb of RAM, mostly because of reasons I suspect you'd agree with:
a) For playing games under Windows, I lose nothing. A 768Mb graphics card means I lose 768Mb of RAM under Windows, but the game itself can only use 2Gb and that still leaves 1.3Gb for the OS to play in for disk cache. What's the problem?
b) For doing anything productive I use Linux, where PAE allows all 4Gb to be used with no RAM loss, and no noticable performance hit.
c) 64-bit Windows XP was utter crud, mostly because of driver issues.

64-bit is inevitable, but I wonder how many people will actually use it that much. People editing video at home stand more chance than the average gamer of using >4Gb. Try telling that to a gamer, though. ;-)

Re:Does it have 64-bit addressing? (1)

Xargle (165143) | more than 4 years ago | (#33532268)

Acorn's then current machine had 128K base.

Power specs of ARM vs Intel, AMD, Power6, Alpha? (0)

Anonymous Coward | more than 4 years ago | (#33531802)

Someone please post the specs for power consumption and head dissipation of the ARM, so we
can direct this discussion on comparing how it compares to the leading and former CPU fab?

I still have a nice Dual Alpha 1GHz system that I use for development purposes, and it's
heat dissipation and rackmount footprint are simply superior to the modern equivalents,
so maybe a rackmount of ARM systems could retire this Alpha fanboi or maybe raise the Alpha
that nearer to the Halls of Val Halla?

Inb4 Linuxgames.com

Re:Power specs of ARM vs Intel, AMD, Power6, Alpha (4, Informative)

Tapewolf (1639955) | more than 4 years ago | (#33531986)

I don't know the heat dissipation figures, but I can safely say I have never yet seen an ARM processor with a heatsink. As for power consumption a quick google seems to show that an 800MHz OMAP3 draws around 750mW at full load. This new A15 core is supposedly going to have similar figures.

Re:Power specs of ARM vs Intel, AMD, Power6, Alpha (4, Informative)

Seth Kriticos (1227934) | more than 4 years ago | (#33532224)

According to this [slashgear.com] , a typical cortex a9 core draws about 250mW. As this has a very similar architecture (still ARMv7), it should be somewhere in similar regions, maybe more, as they boosted the frequency. So I guess a 16 core version will draw something like 4W+, maybe more. Non-the-less, this is still an incredibly good figure for a web server type processor, though a little heat sink might appear.

I'm only guessing here though, based on previous figures. There is no practical data so far on the exact figures.

Re:Power specs of ARM vs Intel, AMD, Power6, Alpha (0)

Anonymous Coward | more than 4 years ago | (#33532162)

Well, it's not that simple as ARM licenses the core to a CPU vendor, who then integrates one or several cores, along with a good deal of other stuff (DSP, GPU, video codecs, peripheral bus controllers, RAM, Flash, etc.), all at a process size of their choice, into an SoC, then you get power numbers for the whole thing. So any of the half-dozen or so OMAP 3xxx SoCs from TI, Tegra, from nVidia, A4 from Apple, and a bunch others are all single Cortex A8 core systems, but have varying capabilities and power consumption. Power also varies strongly with load and with what functional units are in use, down to around 1mW at idle (clock-stop).. Somewhere around 1W at full load on the CPU and reasonable duty cycles on other units is typical for a 0.8-1 GHz SoC with a full complement of functional units -- less if you don't have (or just don't use) the GPU/DSP/video codec accelerator, as you likely wouldn't for development purposes. They royally kick Atom's ass, but I have no idea how they compare to Alpha.

Re:Power specs of ARM vs Intel, AMD, Power6, Alpha (3, Informative)

anss123 (985305) | more than 4 years ago | (#33532236)

They royally kick Atom's ass,

The Atom looks bad on work/watt, but still wins in raw performance.

but I have no idea how they compare to Alpha.

The alpha is a "floating point monster", or was anyway, and since ARM doesn't focus on floating point I doubt they compare. The Atom might keep up though.

Well *that* sounds painful.... (4, Funny)

Eternal Vigilance (573501) | more than 4 years ago | (#33531808)

"It's like taking a desktop and putting it in your pocket," said Schorn.

That's gotta be one of the most uncomfortable marketing images ever.

"Is that an ARM in your pocket or are you just glad to see me?"

Re:Well *that* sounds painful.... (1)

L4t3r4lu5 (1216702) | more than 4 years ago | (#33532176)

It's an arm.

Yours,

Hans Reiser.

So it's six times the speed of the A8? (1)

noidentity (188756) | more than 4 years ago | (#33531810)

Claims 5x Speedup [...] deliver a 5x performance increase over the A8

pSo it's six times the speed of the A8 then? (1x + 5x = 6x)

Re:So it's six times the speed of the A8? (1)

Merls the Sneaky (1031058) | more than 4 years ago | (#33531946)

Or the marketing droid told him it would sound better that way. ;)

Re:So it's six times the speed of the A8? (1)

dorre (1731288) | more than 4 years ago | (#33531974)

No. The 5x performance increase over the A8 means that the increase is over A8's predecessor is 5x greater..
E.g. Speed of A8 = 100, speed of A7 (?) = 70, difference is 30-> A15 is 70+(5+1)*30=250.
Now, the A15 is 2.5 times faster than the A8. Now that was straightforward wasn't it?

Eagle (1)

dandart (1274360) | more than 4 years ago | (#33531864)

Literally FLY on the back of a giant eagle's arm? huh? Someone's got this confused, guys...

Fully capable Linux based TVs coming very soon. (2, Interesting)

Old Flatulent 1 (1692076) | more than 4 years ago | (#33532016)

Right now my Samsung 5000 series LED tv runs an arm with busybox linux as the firmware. It is only a matter of time before TVs become fully internet capable and use usb 3 for storage. I also have seen demos of touch screen remotes that have qwerty capability for your TV. So the only thing missing is a simple cursor system and presto you have it all. Seeing that arm processors are becoming this powerful the market for all in one home entertainment devices is there. If Microsoft does not see this coming and continues to have mediocre support for arm based devices then embedded Linux will continue to dominate the living room. Three of my home entertainment devices are already based on the Linux kernel!

Mini ARM for my desktop, please! (4, Interesting)

udippel (562132) | more than 4 years ago | (#33532048)

'The exciting place for software developer graduates to go and hunt for work is no longer the desktop.'

Why, actually, why??
I am really really looking forward to a desktop with low power footprint. There is no need here to run MS-crapware; no Crysis or other high-resource gaming.
Gimme a nice desktop, low-low power, that boots to Debian on ARM, and I throw mine out of the window. And I already have a 80+ PSU, single row of RAM, dual-core EE AMD. It still has a 45W TDP; plus AMD does not sell the Energy Efficient (EE) any longer except to OEMs; at least in this country.
Throw out the 24-pin plus 12 V power supply, let's do everything on 12 V, give it 6 USBs, Sata, HDMI/DVI, Ethernet and WiFi. A mini ARM.
And, yes, I want to be able to add a hard disk of my own, maybe a DVD- or BlueRay-Drive, so add some space.

Re:Mini ARM for my desktop, please! (2, Interesting)

gbjbaanb (229885) | more than 4 years ago | (#33532280)

I'm thinking of the marketplace these would be targetted at.

Sure, hard-core gamerz will not want one if it doesn't run the absolute latest super-graphics games that require 2 PSUs and 4 Gfx cards for their neon-light equipped gaming rigz. but, ignoring them....

My account manager always has his (old) smartphone glued to his ear when i see him. And he uses his PC for email and the odd word document. That's easily replaced with a smartphone, one that could connect to a big monitor and keyboard while still being portable would be perfect for him - and the rest of the sales and managerial types out there. That's a good 50% of all PC sales I think.

The rest of home users want something that lets them do 'netbook' style stuff - web, email, text, social networks, youtube. Well, that's covered and I think PC sales are dropping for home users already.

Business users - again, most of them do email, web and some odd LoB apps. The latter are a problem, unless they become web-apps, which is where the smart money is going nowadays (although that tends to be for easy deployment and management of the apps), once entirely webapps, there's not reason most people need a PC at all.

I think the future is for mobile devices, not PCs. The dinosaur that is Microsoft is dead, its just that the signals havn't reached its brain yet. Just like IBM many years ago, and others since.

Re:Mini ARM for my desktop, please! (0)

Anonymous Coward | more than 4 years ago | (#33532308)

The dinosaur that is Microsoft is dead, its just that the signals havn't reached its brain yet.

Or the 90% of the market that they own either, I guess.

Just another MS hater who has to find some other hope that MS is dying since Linux on the desktop failed that task. Keep on running your mouths boys. It makes me laugh more and more each year you guys wait in the wings for your big day. Just keep on waiting.

Re:Mini ARM for my desktop, please! (4, Interesting)

gmarsh (839707) | more than 4 years ago | (#33532326)

Marvell OpenRD-client:

http://www.globalscaletechnologies.com/t-openrdcdetails.aspx [globalscal...logies.com]

Has an ARM9 at 1.2GHz, half a gig of RAM, sound, VGA video, lots of USB, SD card reader, 2 GbE ports, eSATA and a spot for a 2.5" hard drive in it. Mine draws 10W from the wall. And it happily runs Debian.

My only beef is the video (XGI Z11) has absolutely horrible driver support, so don't expect the thing to play Blu-ray.

Re:Mini ARM for my desktop, please! (1)

udippel (562132) | more than 4 years ago | (#33532370)

Of course, that's what I can foresee. But 1280x1024 is already far out of the scope. Nevermind the lack of hardware acceleration at those specifications. A bit of compiz is quite okay for me; doesn't have to be rotating cubes.
Give it an extra slot 5.25", and HDMI. Otherwise Marvell won't sell all too many.
And ping me when that machine comes to the market, please.

I know many CS graduates (2, Funny)

Chrisq (894406) | more than 4 years ago | (#33532150)

I know many CS graduates who have thought that the most interesting stuff to play with is in the pocket.

obligatory (0)

Anonymous Coward | more than 4 years ago | (#33532210)

Imagine a Beowulf cluster of these!

Multicore ARM and suboptimal instruction sets (5, Interesting)

Anonymous Coward | more than 4 years ago | (#33532348)

I'm currently working with several concurrency development groups within the SUNY system; we are partnered with Oracle, Google, and IBM as well as a few others. Upon mention of ARM not a single co-worker has been able to resist going into rant mode about the lack of reasonably quick CAS and LL/SC implementations. Further, barriers and fences apparently take so long to establish that to fake a CAS you are looking at three to six hundred cycles compared to about a dozen for current generation i7's and SPARCs (optimistic CASing). Can anyone speak to the implementation of the features on this new chip?

ARM, Acorn, RISC, x86, MIPS and RAQ2 (3, Interesting)

GuyFawkes (729054) | more than 4 years ago | (#33532366)

Have run all of these, in anger, in production, at one point or another.

I still have an extremely soft spot for the RAQ2, 64 bit MIPS processor.

Image link - http://dev.gentoo.org/~vapier/pics/mipsel-raq2/inside-main-board.jpg [gentoo.org]

Nota Bene, NO HEAT-SINKS OF ANY KIND, and yet these puppies could saturate a 10 Mbit connection (of course this was the days before flash and stuff) and the whole mainboard used about 10 watts, most of which was the RAM, the biggest power eater was the IDE HD.

Downside was it was MIPS, which is a lot like the downside of the Acorn ARM based A series and Risc-PC series, eg not x86 compatible, ergo not mainstream.

Now that ARM is used is zillions of other devices, ARM is no longer the backwoods, everywhere except in "a computer" eg desktop or server.

Which means ARM on the desktop or ARM on the server won't suffer so badly for not being x86... it will still suffer, but not so badly.

RAQ3 went away from MIPS to x86, IMHO because of this accessibility and availability of x86 code, not because it was technically superior to MIPS... one RAQ3 wasn't more powerful than two RAQ2 in any sense except power consumption and thermal rejection.

In practical terms x86 has gone nearly as far as it can go, both in terms of light speed and die size, and thermal dissipation per cubic mm, so the alternatives are catching up, not so much because of sheer lifting power, but because of thermal dissipation per cubic mm they still have "development room" left to play around in.

The next 5 years or so are going to be interesting, as this "development room" is explored and used up, and especially so if anyone comes out with a robust cross architecture compiler / translator.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?