bigwophh writes "ARM launched its new Cortex-A5 processor (codenamed Sparrow) this week, and while it's not targeted at the top end of the mobile market, it is a significant launch nonetheless. The Cortex-A5, which will likely battle future iterations of Intel's Atom for market share, is an important step forward for ARM for several reasons. First, it's significantly more efficient to build than the company's older ARM1176JZ(F)-S, while simultaneously outperforming the ARM926EJ-S. The Cortex-A5, however, is more than just a faster ARM processor. Architecturally, it's identical to the more advanced Cortex-A9, and it supports the same features as that part as well. This flexibility is designed to give product developers and manufacturers access to a fully backwards-compatible processor with better thermal and performance characteristics than the previous generation."
But it's worth noting that according to previous articles, Intel "envisioned" Atoms one day making it into high end phones. This latest move from Arm will prevent that, solidifying their lead.
Speaking (typing) from a Quad G5, PPC and watched the happenings in OS X community/developer scene since Intel transition announced. If Intel one day manages to make Atom (x86) run in same low power as ARM licensed CPUs, ARM is doomed.
Why? Compare the compile process of an open source, multimedia application on PPC and Intel. See the "bonus" stuff Intel chips get? Every kind of optimization, way more cheaper is available on Intel x86/SSE. Trust me, I am more amazed to Intel's developer/development/applicati
Acorn Computers tried in the 80's and 90's. The ARM processors were faster than their x86 rivals, and OS was years ahead of the likes of Windows and Mac OS. As you say, some monopolistic software company would never allow ARM to take off. Lucky ARM is now the most common architecture on the market.
It's sad x86 is still here, the platform should have been done away with years ago.
They were also much cheaper. I remember A3000s being under £100, when the cheapest PC that you could actually use seriously was at least £500, and probably closer to £1000. If you wanted a hard drive, it cost a bit more, but most RiscOS software at the time could run from floppy. If you got a 70MB or so hard disk (when PCs typically came with 250MB+) then you could store all of your applications and data on it easily.
Even Intel's shiny new Nehalem architecture is not much more than an updating of the DEC Alpha (ditto for AMD but their designs, at least, have been based on it for 10 years).
I'm shocked at this claim. Back in the day, Byte Magazine used to dissect processor architectures in a way you rarely see any more, apart from anything written by Jon Stokes over at Ars. Realworldtech picked up the torch, and I followed it for a while; smart guys, but you need a large Kool-Aid division factor to hang there.
I hope ARM beats x86 merely because x86 is an ancient technology that has a pile of limitations preventing the industry from moving forward as fast as it otherwise might. Previous attempts to move away from x86 failed due to the absence of software to run on the new machines. It's all fine and dandy if Microsoft write NT for the Dec Alpha and Itanium, but if there are no apps, it's pointless.
Actually there is a way for this to work. Microsoft ports Windows to Arm. Most of the time the processor is in kernel mode so that makes a difference. Now running user mode code through an emulator which is basically a big switch statement will not deliver a decent performance level. Microsoft could port their Office applications to ARM.
ARM have actually quite some experience of running non native instruction sets - Jazelle is mode where the ARM runs 80% of Java byte code natively. Basically there is an ext
I would love to have one of these in a "smartbook". Even though it won't run x86 binaries (I use linux anyway) it would be useful enough to let me leave my big arse laptop at home. With hours of battery life I wouldn't need to take a power supply with me.
So far though the only ARM smartbooks currently available have very limited RAM and disk space. I will have to wait and see what comes out in the next few months.
but I wouldn't put it in the 'cheap' category. They're not available yet, but the battery is supposed to last for a long time...but it uses the Intel Atom:
That looks nice, though the battery life could be better though.
Found more info on it [liliputing.com]. Looks like it uses a modded version of Mandriva. The USB flash as a hard drive replacement is interesting. Only problem is that you will have to buy the special G-key USB flash drives to have them fit nicely in the slot.
Why would you buy that when you can get a 10" Dell mini which runs every x86 app in existence through Windows, Ubuntu Preinstalled or Hackintosh?
For almost the same price it has:
Twice as much RAM. Twice as fast of a processor. Exponentially more software available. Twice as much battery life. And weighs exactly the same amount.
"Exponentially" means according to a function in which one of the terms is a constant raised to a term which includes the power of the x variable. It is not a synonym for "many times", and it cannot apply to something which is, even instantaneously, a constant, since it can only refer to a function. If you mean that the number of MIPS/Linux applications increases linearly while that of X86 functions is increasing exponentially you might have a point - except that, at any moment in time without more informat
The Loongson CPU is quite nice, but the 2F is closer to Atom in terms of power usage than an ARM chip (and a bit higher than even Atom). Note the 4 hour battery life, which is pretty poor for a machine in this class.
There are smaller devices available, which might be nice for lugging around - but keep in mind that the screen and Wifi are still big power draws, so the bigger the batteries the better.
by Anonymous Coward
on Sunday October 25, @12:22AM (#29862435)
The Cortex-A5 is a slight improvement over the MPCore/Arm11/Arm9. That's nice for those who need it, but it's miles away from the speed of a Cortex-A9, which is really what's going to be needed to battle Atom.
And since the A9 has announced by ARM quite some time ago, this posting should have been written then not now.
In reality, it's not clear which niche the A5 is going to occupy. It's probably going to be useful in lower end smartphones only, since current higher end models are already using the faster A8.
As a developer for products based on ARM9 and ARM11 SoCs the A5 is targeted squarely at me. I'm not sure why it's of any interest to slashdot. But it does appear to be a cheaper ARM11 (to the point of making the ARM9 obsolete) but with some of the features of the A8. While smartphones are all sexy and exciting, the staple for cell phone manufacturers are the simple ordinary phones. If they can cram more features into the same cheap phone it usually means they can sell more of them. Think of it as competing in the free phone market. Where the styling and brand and features are the only way to differentiate yourself rather than price. The customer is just going to pick 1-4 of the plan bundled phones.
the Cortex-A8 is out now on the 65nm process as are all the other low power device CPU's except Atom. Atom is currently on 45nm to get in the ballpark as the others but power usage is still pretty high. Cortex-A8 on 45nm should be in the pipeline soon and along with it, Cortex-A9. Those are going to shack the Atom up on price/watt and performance/watt. This is why Intel is moving Atom to 32nm ASAP but it's very expensive for them because they have to price the Atom low while at the same time use very expensive 32nm process space which they normally use for high profit desktop/server CPUs. So in 2011, along comes Cortex-A5 on 40nm so Intel would have to start looking at 2?nm processes to keep competing. I believe the ARM dude talks about this somewhat.
Size is a big deal and right now, Cortex-A8 on 65nm is rather large for smart phones. they pack some decent power for netbooks so I'm not sure what the delay is on that front. Cortex-A9 on netbooks would be very nice but I think they are just sampling now so it won't happen til next year( 2010 ).
ARM is a thorn in both Microsoft and Intel's sides and there is probably massive amounts of pressure on OEMs and manufacturers to stay away from it. Atleast on the netbook side. Remember, the head of the Thai Manufacturers Association said they fear Microsoft when talking about Linux on netbooks. ARM is an enabler for Linux so it too is a threat to Microsoft. But I sure hope the market gets to make the choice some how, some way.
ARM does not make chips, they design them. The process technology is up to the licensees. Some are using 45nm now, and have been sampling 32nm for a few months with plans to ramp up production in early 2010.
Looks like the Cortex-A5 has 50% more performance while using 1/3rd the power of the current generation ARM11 found in the iPhone. As a game developer this makes me hopeful that we'll see cellphones as a gaming platform without sacrificing useful battery life.
Most figures you find in the TFA are in terms of DMips, which is an awful metric to measure general CPU performance. Imagine how easy it is to optimize a loop which contains 100 instructions, which is 100% branch predicted and 100% cache hit at L1 D/I. This does not translate at all to web browsing performance which is thrashing (at least) your L2.
In term on u-architecture, we are looking at something similar to ARM11 on newer processes. TFA talks about: +80% DMips co
The Cortex-A5 has a more advanced L2 memory system with multiple outstanding transactions. This makes a huge difference for many workloads compared to the ARM11 cores. Thus, for workloads not contained entirely within the L1 memories the Cortex A5 should offer much better performance.
The A5 is, from a marketing standpoint, a cut down A8. It supports all of the new instruction set extensions introduced with the A8, and is intended to be binary-compatible, but is a lot slower. It is also a lot cheaper. A decent A8 SoC costs around $40, but you can expect A5-based cores to sell for well under $20.
From a technical standpoint, it's quite a different design. The A8 is an in-order superscalar design, with a 13-stage pipeline (and a 10-stage SIMD pipeline). The A5 is an in-order single-i
If it's not superscalar, why does it need a branch predictor? It only needs to know when the first instruction fails a cache hit, so that any results can be held.
Uh, what? You need a branch predictor because it's pipelined. It has an 8-stage pipeline, which means that it doesn't know the result of an instruction until eight cycles after it was issued. If you come to a conditional branch, you need to decide whether to take it or not. For example, if you have some C code saying something like 'if (a == 12)' then you can't decide whether to jump to the else block until you've computed the value of a, which will be 8 cycles in the future. Without a branch predictor, you just stall for 8 cycles and do nothing. Given that compiled code averages about one branch every 7 instructions, that means that you would be spending most of your time doing nothing.
The branch predictor makes a guess about which branch to follow, i.e. whether to continue to the body of the if statement or jump to the else block. It then starts executing whichever branch if guesses. If it guesses correctly, then the pipeline stays full. If it guesses incorrectly, the pipeline is flushed and none of the results of the instructions after the branch missprediction are committed. The processor resets itself to the branch and continues down the right track.
The branch predictor in the A5 gets about a 95% hit rate, so on average you have to flush the pipeline every 20 branches, which isn't too bad in terms of overhead. Superscalar makes no difference to the need for branch predictors. A superscalar chip is one that can issue more than one instruction per cycle. That means that independent instructions can be run side by side. This is quite nice on ARM chips, where a lot of instructions are predicated, as you can run both versions in parallel and only commit the one that was meant to be taken, but it's completely independent of the branch predictor.
It doesn't sound like it is necessarily slower, either, since you can get the same functions as the A8.
Nonsense. By that logic Atom is as fast as a Core 2 because you have the same instruction set on both. The A5 and A8/9, due to massive implementation differences, will execute different numbers of instructions per clock and not run at the same clock speed. The A5 will execute far fewer and runs at a lower frequency.
So this is why ARM and Global Foundries recently made a deal [hothardware.com]. ARM's Cortex-A5 is going to be built on a 40nm and Global Foundries already has that equipment, with AMD working hard to advance to the next node that frees up a lot of manufacturing power for ARM to use. Officially it was for Cortex-A9 at 28nm but what's to stop other stuff from being done in the shadow of the deal?
Its the Wifi/WWAN chips, and LCD screen which suck up the power, not the CPU. ARM is cool and all (pun intended) but if you make an ARM based Dell Mini 9, you're not going to end up with uber battery life, when you're on Wifi and running the screen bright.
The main reason why the CPU does not suck power is because most if not all mobile phones use ARM CPU cores. Imagine a mobile phone with an ATOM, shudder... You would gain some speed but your mobile phone would need fans:-(
ARM talked about the Cortex A9 (the one I'd actually like to have in a netbook) over two years ago [cnet.com]. There is still nothing you can get that actually has one in it.
Yay something to replace the ARM11. Hope it actually gets used.
What they mean is that the instruction set is compatible. So you can run the same binaries on both (although they would probably run faster if you recompiled them).
ARM has several different instruction set versions and optional extensions. You cannot run binaries interchangeably in a simple fashion. This is arguably true as well for x86's SSE and the ilk but to a much smaller degree. Why do you think cellphone vendors use Java ME even if, more often than not, they use ARM processors?
They're not saying "it's identical", they're saying "architecturally, it's identical", which is to say that any differences are non-architectural (i.e. performance, power consumption, etc).
Perhaps a car analogy would help...
If I say that color-wise my Ford Pinto is identical to my Ferrari, all I'm saying is identical is the color!
We really have to start looking more carefully at posts like this, which clearly contain entire paragraphs of unexamined assertions by company PR drones that may or may not be true. Bottom line: Kill this shit unless a trustworthy, honest reviewer with a decent track record says it. If that isn't happening, quit posting it here, where we have more important stuff to spend time on.
By the way, that "more important stuff" includes pulling our dicks and/or replaying World Championship Monopoly games move by move.
Microsoft can really change things around if they decided to port Win7 to ARM, instead of offering only Windows CE.
But considering monopolies, I wouldn't expect that any time soon.
People generally use Windows on PCs because they have x86 Windows software they need to run.
How many people have a stack of ARM software to run on ARM Windows? If you're going to need new software anyway, why would anyone in their right mind pick Windows to run it on?
How many people have a stack of ARM software to run on ARM Windows?
It's relatively easy to recompile software for a different architecture, as long as the API is the same. Of course there's no ARM Windows software now, but that would change pretty quickly.
Ok,
1) you don't have the source to recompile. It's not like you just have a repository to recompile. It lots of different companies that must work together, and they are only going to do what they see will be profitable. So only a selection defined by what the owners see as profitable will be ported.
2) the first port of software is the hardest and most Windows software has never been ported. Much of Windows software is written to just one implimentation of the API, so problems go hidden. You'll find old W
Microsoft can really change things around if they decided to port Win7 to ARM, instead of offering only Windows CE.
But considering monopolies, I wouldn't expect that any time soon.
People generally use Windows on PCs because they have x86 Windows software they need to run.
How many people have a stack of ARM software to run on ARM Windows? If you're going to need new software anyway, why would anyone in their right mind pick Windows to run it on?
Because 6 months before you can even buy "Windows 8 - ARM Edition", Microsoft will have released a Visual Studio patch that enables "ARM" as a target alongside the existing x86/x64/Itanium platforms. Both.NET and Java will have runtimes ported as well. Converting 32-bit code from one CPU to another is much easier than going from 32-bit to 64-bit, so it wouldn't take very long for vendors to update their software for it. Also, Microsoft strongarms ISVs into compatibility. For example, it's often hard (or h
I've said this before. Aside from games, very little legacy software is CPU-bound. A modern emulator can get somewhere between 50-80% of the host native speed on emulated software, and not all of the code that is running will be emulated. Take a look at a typical Windows application. Most spend at least 50% of their CPU time in system library code. A half-decent emulator will just pass these calls to the native versions of the libraries, so for half of the CPU time you are running native code. A lot of recent Windows applications use some.NET code. This will be JIT compiled to ARM, so it's also native. The remaining code will be emulated, but the number of programs for which this will be too slow is very small.
Oh, and most people do not have a stack of x86 Windows software. They have one or two Windows programs that they depend on (or, at least, would not abandon without a lot of persuasion). You can bet that an ARM version of Windows would be accompanied by an ARM version of Office, and if MS really wanted to push it then they'd give a free download of the ARM binaries to people who owned the x86 version.
In terms of C programming environment, x86 and ARM are very similar. C does a terrible job at abstracting the differences between SPARC64 and x86 (for example), but it does a lot better at abstracting the differences between ARM and x86. Most software, unless it uses inline assembly or SSE / MMX intrinsics, is a straight recompile. The SSE and MMX intrinsics can be implemented in terms of NEON or slower scalar operations, so the code will compile, even if it doesn't get the same performance.
It would be best for Microsoft if ARM on the laptop/desktop was a complete flop. Sure, if what others say is true about the portability of Windows internals, Microsoft could release a version of Windows 7 for ARM. But really, what would be the point?
The biggest strength of Windows is running Win32 apps, and they are all compiled for Win/x86. Microsoft would have to provide development tools that encourage developers to make ARM binaries along side x86 binaries to even have a chance at making it happen. Look at the average computer user's software catalogue, you will find many apps (and games) that were bought long ago and would cost money to upgrade to a potential ARM port if the company that made them are sill even in business. Those programs are never going to be ported to Win/ARM. Then there are all the drivers for last years peripheral hardware (assuming that the laptop's hardware is supported) that won't work.
I don't believe they can do what Apple did either. Apple was able to move to x86 from PPC because the control the hardware and moved their whole product line to it (killing PPC market). Any developers that wanted to stay in business had to port to x86. MS would be introducing a side product that would have a very small fraction of the bigger x86 customer base.
In the end all that Win/ARM has left is the few open source apps that choose to build an installer for it and the familiarity of the Windows desktop environment.
It would be in their interest to do everything in their power to make sure this doesn't ever get off the ground. We will have to wait and see what their next move will be.
> Apple was able to move to x86 from PPC because the control the hardware and moved their whole product line to it (killing PPC market)
and losing me as a customer in the process, albeit slowly as s/w became more and more incompatible with PPC. Of course, that wasn't the only reason, but still.
Apple did not kill the PPC market. IBM did at least the desktop market, one day they decided to give up the PPC desktop processors without telling Apple. Apple did not have a choice, there were new desktop and notebook processors in the pipeline, while IBM busily was working on their high end server processors and was designing console processors for Sony and Microsoft with their old cores.
>> Microsoft can really change things around if they decided to port Win7 to ARM
Heard it through the grapevine that this is EXACTLY what they're doing, albeit not in a context you mentioned. A subset of full blown Windows kernel is being ported to ARM (a-la iPhone Mach) as a foundation for their "next" next gen mobile OS.
Now that is silly. 8086 had like 29 thousand transistors. 80386 had some 275 thousand transistors. The StrongARM SA-110 processor had 2.5 million transistors, more transistors than a 80486, and that was years ago. x86 decoding is hardly the issue people think it is. Not at todays transistor budgets. Intel has surprised a lot of people with Atom and they should be able to shrink it further.
1) The A5 is not meant to take on Atom. The A9 is. 2) The A5 is not architecturally identical to the A9. The A9 is an in-order, multi-issue core. The A5 is an out-of-order, single-issue core. The only thing similar is it has the Cortex A-series ISA.
What the A5 is is a CPU that completely obliterates the ARM11-derived cores, used in everything from NVIDIA Tegra to the Nintendo DS. It's an update of the ISA, and a more capable core, with better thermals. That's it. Whereas every low-end smartphone now has the same damn QualComm ARM11-based core, in a year, they'll all have the A5.
Summary is misleading (Score:5, Informative)
The Cortex-A5 is aimed at phones. The Cortext-A9 is the one aimed at netbooks. The article referenced in the summary makes this clear.
Re:Summary is misleading (Score:4, Interesting)
I agree - the summary is bad.
But it's worth noting that according to previous articles, Intel "envisioned" Atoms one day making it into high end phones. This latest move from Arm will prevent that, solidifying their lead.
Parent
But what if Atom really works fine on smart phone? (Score:3, Insightful)
Speaking (typing) from a Quad G5, PPC and watched the happenings in OS X community/developer scene since Intel transition announced. If Intel one day manages to make Atom (x86) run in same low power as ARM licensed CPUs, ARM is doomed.
Why? Compare the compile process of an open source, multimedia application on PPC and Intel. See the "bonus" stuff Intel chips get? Every kind of optimization, way more cheaper is available on Intel x86/SSE. Trust me, I am more amazed to Intel's developer/development/applicati
Re:First the Beatles; Now the ARM? (Score:5, Interesting)
Acorn Computers tried in the 80's and 90's. The ARM processors were faster than their x86 rivals, and OS was years ahead of the likes of Windows and Mac OS. As you say, some monopolistic software company would never allow ARM to take off. Lucky ARM is now the most common architecture on the market.
It's sad x86 is still here, the platform should have been done away with years ago.
Parent
Re: (Score:2)
They were also much cheaper. I remember A3000s being under £100, when the cheapest PC that you could actually use seriously was at least £500, and probably closer to £1000. If you wanted a hard drive, it cost a bit more, but most RiscOS software at the time could run from floppy. If you got a 70MB or so hard disk (when PCs typically came with 250MB+) then you could store all of your applications and data on it easily.
premature evaluation (Score:3, Interesting)
I'm shocked at this claim. Back in the day, Byte Magazine used to dissect processor architectures in a way you rarely see any more, apart from anything written by Jon Stokes over at Ars. Realworldtech picked up the torch, and I followed it for a while; smart guys, but you need a large Kool-Aid division factor to hang there.
This probl
Re: (Score:3, Interesting)
I hope ARM beats x86 merely because x86 is an ancient technology that has a pile of limitations preventing the industry from moving forward as fast as it otherwise might. Previous attempts to move away from x86 failed due to the absence of software to run on the new machines. It's all fine and dandy if Microsoft write NT for the Dec Alpha and Itanium, but if there are no apps, it's pointless.
Actually there is a way for this to work. Microsoft ports Windows to Arm. Most of the time the processor is in kernel mode so that makes a difference. Now running user mode code through an emulator which is basically a big switch statement will not deliver a decent performance level. Microsoft could port their Office applications to ARM.
ARM have actually quite some experience of running non native instruction sets - Jazelle is mode where the ARM runs 80% of Java byte code natively. Basically there is an ext
Love to have one (Score:2)
I would love to have one of these in a "smartbook". Even though it won't run x86 binaries (I use linux anyway) it would be useful enough to let me leave my big arse laptop at home. With hours of battery life I wouldn't need to take a power supply with me.
So far though the only ARM smartbooks currently available have very limited RAM and disk space. I will have to wait and see what comes out in the next few months.
Re:Love to have one (Score:4, Interesting)
MIPS rather than ARM, but these things [amazon.com] are cheap and look pretty useful.
EMTEC Gdium Liberty 1000
Parent
Re: (Score:2)
If battery life is what you want, you might consider one of these :
http://europe.nokia.com/find-products/mini-laptop [nokia.com]
but I wouldn't put it in the 'cheap' category. They're not available yet, but the battery is supposed to last for a long time...but it uses the Intel Atom :
CPU and chipset
* Intel® Atom(TM) Z530, 1.6 GHz
* Intel® Poulsbo US15W
Re: (Score:2)
That looks nice, though the battery life could be better though.
Found more info on it [liliputing.com]. Looks like it uses a modded version of Mandriva. The USB flash as a hard drive replacement is interesting. Only problem is that you will have to buy the special G-key USB flash drives to have them fit nicely in the slot.
Not bad at all.
Re: (Score:3, Interesting)
Why would you buy that when you can get a 10" Dell mini which runs every x86 app in existence through Windows, Ubuntu Preinstalled or Hackintosh?
For almost the same price it has:
Twice as much RAM.
Twice as fast of a processor.
Exponentially more software available.
Twice as much battery life.
And weighs exactly the same amount.
I do not think Exponentially means what you think (Score:3, Funny)
Re: (Score:2)
Re:Love to have one (Score:4, Interesting)
http://www.alwaysinnovating.com/touchbook/ [alwaysinnovating.com]
http://promos.asus.com/US/1000HE/ASUS/index.html [asus.com]
Two netbooks with long battery lives.
There are smaller devices available, which might be nice for lugging around - but keep in mind that the screen and Wifi are still big power draws, so the bigger the batteries the better.
Parent
No, it's not... (Score:4, Interesting)
The Cortex-A5 is a slight improvement over the MPCore/Arm11/Arm9. That's nice for those who need it, but it's miles away from the speed of a Cortex-A9, which is really what's going to be needed to battle Atom.
And since the A9 has announced by ARM quite some time ago, this posting should have been written then not now.
In reality, it's not clear which niche the A5 is going to occupy. It's probably going to be useful in lower end smartphones only, since current higher end models are already using the faster A8.
A5 is for people like me (Score:4, Interesting)
As a developer for products based on ARM9 and ARM11 SoCs the A5 is targeted squarely at me. I'm not sure why it's of any interest to slashdot. But it does appear to be a cheaper ARM11 (to the point of making the ARM9 obsolete) but with some of the features of the A8.
While smartphones are all sexy and exciting, the staple for cell phone manufacturers are the simple ordinary phones. If they can cram more features into the same cheap phone it usually means they can sell more of them. Think of it as competing in the free phone market. Where the styling and brand and features are the only way to differentiate yourself rather than price. The customer is just going to pick 1-4 of the plan bundled phones.
Parent
Re:No, it's not... (Score:5, Interesting)
Size is a big deal and right now, Cortex-A8 on 65nm is rather large for smart phones. they pack some decent power for netbooks so I'm not sure what the delay is on that front. Cortex-A9 on netbooks would be very nice but I think they are just sampling now so it won't happen til next year( 2010 ).
ARM is a thorn in both Microsoft and Intel's sides and there is probably massive amounts of pressure on OEMs and manufacturers to stay away from it. Atleast on the netbook side. Remember, the head of the Thai Manufacturers Association said they fear Microsoft when talking about Linux on netbooks. ARM is an enabler for Linux so it too is a threat to Microsoft. But I sure hope the market gets to make the choice some how, some way.
LoB
Parent
Re: (Score:2)
ARM builds even its high-end cores as softcores these days. It is the implementor, not ARM who decides which process node to use.
Re: (Score:2)
Good news for future iphone (Score:4, Interesting)
Looks like the Cortex-A5 has 50% more performance while using 1/3rd the power of the current generation ARM11 found in the iPhone. As a game developer this makes me hopeful that we'll see cellphones as a gaming platform without sacrificing useful battery life.
Re: (Score:2, Informative)
Be careful not to buy marketing bullshit.
Most figures you find in the TFA are in terms of DMips, which is an awful metric to measure general CPU performance. Imagine how easy it is to optimize a loop which contains 100 instructions, which is 100% branch predicted and 100% cache hit at L1 D/I. This does not translate at all to web browsing performance which is thrashing (at least) your L2.
In term on u-architecture, we are looking at something similar to ARM11 on newer processes.
TFA talks about:
+80% DMips co
Different L2 memory interface makes the difference (Score:2, Informative)
The Cortex-A5 has a more advanced L2 memory system with multiple outstanding transactions. This makes a huge difference for many workloads compared to the ARM11 cores. Thus, for workloads not contained entirely within the L1 memories the Cortex A5 should offer much better performance.
Re: (Score:2)
The phone I have - Nokia N900 - uses the ARM Cortex A8. I wonder how the processors compare...
Re: (Score:3, Informative)
From a technical standpoint, it's quite a different design. The A8 is an in-order superscalar design, with a 13-stage pipeline (and a 10-stage SIMD pipeline). The A5 is an in-order single-i
Re:Good news for future iphone (Score:5, Informative)
If it's not superscalar, why does it need a branch predictor? It only needs to know when the first instruction fails a cache hit, so that any results can be held.
Uh, what? You need a branch predictor because it's pipelined. It has an 8-stage pipeline, which means that it doesn't know the result of an instruction until eight cycles after it was issued. If you come to a conditional branch, you need to decide whether to take it or not. For example, if you have some C code saying something like 'if (a == 12)' then you can't decide whether to jump to the else block until you've computed the value of a, which will be 8 cycles in the future. Without a branch predictor, you just stall for 8 cycles and do nothing. Given that compiled code averages about one branch every 7 instructions, that means that you would be spending most of your time doing nothing.
The branch predictor makes a guess about which branch to follow, i.e. whether to continue to the body of the if statement or jump to the else block. It then starts executing whichever branch if guesses. If it guesses correctly, then the pipeline stays full. If it guesses incorrectly, the pipeline is flushed and none of the results of the instructions after the branch missprediction are committed. The processor resets itself to the branch and continues down the right track.
The branch predictor in the A5 gets about a 95% hit rate, so on average you have to flush the pipeline every 20 branches, which isn't too bad in terms of overhead. Superscalar makes no difference to the need for branch predictors. A superscalar chip is one that can issue more than one instruction per cycle. That means that independent instructions can be run side by side. This is quite nice on ARM chips, where a lot of instructions are predicated, as you can run both versions in parallel and only commit the one that was meant to be taken, but it's completely independent of the branch predictor.
It doesn't sound like it is necessarily slower, either, since you can get the same functions as the A8.
Nonsense. By that logic Atom is as fast as a Core 2 because you have the same instruction set on both. The A5 and A8/9, due to massive implementation differences, will execute different numbers of instructions per clock and not run at the same clock speed. The A5 will execute far fewer and runs at a lower frequency.
Parent
So this is why ARM and Global Foundries... (Score:2, Informative)
Wifi + LCD, not the CPU (Score:5, Insightful)
Its the Wifi/WWAN chips, and LCD screen which suck up the power, not the CPU. ARM is cool and all (pun intended) but if you make an ARM based Dell Mini 9, you're not going to end up with uber battery life, when you're on Wifi and running the screen bright.
Re: (Score:2)
http://www.arm.com/products/security/trustzone/index.html [arm.com]
Yea cool
Re: (Score:3, Insightful)
The main reason why the CPU does not suck power is because most if not all mobile phones use ARM CPU cores. Imagine a mobile phone with an ATOM, shudder... :-(
You would gain some speed but your mobile phone would need fans
Being late to the game is what is killing these... (Score:3, Interesting)
Re: (Score:2)
Late? They said 2010 in the article you linked.
In this article, they said Cortex A5 in 2011.
More advanced identity? (Score:2)
Architecturally, it's identical to the more advanced Cortex-A9
How can it be identical, when it's more advanced? Those two are opposites.
Or is their definition of identity itself more advanced? ^^
Like "(==) a b = a >= b" in Haskell?
Re: (Score:3, Informative)
ARM has several different instruction set versions and optional extensions. You cannot run binaries interchangeably in a simple fashion. This is arguably true as well for x86's SSE and the ilk but to a much smaller degree. Why do you think cellphone vendors use Java ME even if, more often than not, they use ARM processors?
The hardware archite
Re: (Score:3, Insightful)
They're not saying "it's identical", they're saying "architecturally, it's identical", which is to say that any differences are non-architectural (i.e. performance, power consumption, etc).
Perhaps a car analogy would help...
If I say that color-wise my Ford Pinto is identical to my Ferrari, all I'm saying is identical is the color!
More PR Bullshit (Score:3, Funny)
We really have to start looking more carefully at posts like this, which clearly contain entire paragraphs of unexamined assertions by company PR drones that may or may not be true. Bottom line: Kill this shit unless a trustworthy, honest reviewer with a decent track record says it. If that isn't happening, quit posting it here, where we have more important stuff to spend time on.
By the way, that "more important stuff" includes pulling our dicks and/or replaying World Championship Monopoly games move by move.
More info at Arstechnica (Score:5, Informative)
http://arstechnica.com/gadgets/news/2009/10/arm-fills-out-cpu-lineup-with-cortex-a5.ars [arstechnica.com]
http://www.brightsideofnews.com/news/2009/10/21/arm-announces-cortex-a5-for-the-next-15-billion-cellphones-and-mids.aspx [brightsideofnews.com]
Re:MS (Score:5, Insightful)
Microsoft can really change things around if they decided to port Win7 to ARM, instead of offering only Windows CE.
But considering monopolies, I wouldn't expect that any time soon.
People generally use Windows on PCs because they have x86 Windows software they need to run.
How many people have a stack of ARM software to run on ARM Windows? If you're going to need new software anyway, why would anyone in their right mind pick Windows to run it on?
Parent
Re: (Score:2)
It's relatively easy to recompile software for a different architecture, as long as the API is the same. Of course there's no ARM Windows software now, but that would change pretty quickly.
Re: (Score:2)
1) you don't have the source to recompile. It's not like you just have a repository to recompile. It lots of different companies that must work together, and they are only going to do what they see will be profitable. So only a selection defined by what the owners see as profitable will be ported.
2) the first port of software is the hardest and most Windows software has never been ported. Much of Windows software is written to just one implimentation of the API, so problems go hidden. You'll find old W
Re: (Score:3, Insightful)
Microsoft can really change things around if they decided to port Win7 to ARM, instead of offering only Windows CE.
But considering monopolies, I wouldn't expect that any time soon.
People generally use Windows on PCs because they have x86 Windows software they need to run.
How many people have a stack of ARM software to run on ARM Windows? If you're going to need new software anyway, why would anyone in their right mind pick Windows to run it on?
Because 6 months before you can even buy "Windows 8 - ARM Edition", Microsoft will have released a Visual Studio patch that enables "ARM" as a target alongside the existing x86/x64/Itanium platforms. Both .NET and Java will have runtimes ported as well. Converting 32-bit code from one CPU to another is much easier than going from 32-bit to 64-bit, so it wouldn't take very long for vendors to update their software for it. Also, Microsoft strongarms ISVs into compatibility. For example, it's often hard (or h
Re:MS (Score:5, Interesting)
I've said this before. Aside from games, very little legacy software is CPU-bound. A modern emulator can get somewhere between 50-80% of the host native speed on emulated software, and not all of the code that is running will be emulated. Take a look at a typical Windows application. Most spend at least 50% of their CPU time in system library code. A half-decent emulator will just pass these calls to the native versions of the libraries, so for half of the CPU time you are running native code. A lot of recent Windows applications use some .NET code. This will be JIT compiled to ARM, so it's also native. The remaining code will be emulated, but the number of programs for which this will be too slow is very small.
Oh, and most people do not have a stack of x86 Windows software. They have one or two Windows programs that they depend on (or, at least, would not abandon without a lot of persuasion). You can bet that an ARM version of Windows would be accompanied by an ARM version of Office, and if MS really wanted to push it then they'd give a free download of the ARM binaries to people who owned the x86 version.
In terms of C programming environment, x86 and ARM are very similar. C does a terrible job at abstracting the differences between SPARC64 and x86 (for example), but it does a lot better at abstracting the differences between ARM and x86. Most software, unless it uses inline assembly or SSE / MMX intrinsics, is a straight recompile. The SSE and MMX intrinsics can be implemented in terms of NEON or slower scalar operations, so the code will compile, even if it doesn't get the same performance.
Parent
x86 abi (Score:3, Insightful)
You can bet that an ARM version of Windows would be accompanied by an ARM version of Office
But how easily would Microsoft Office (for Windows 8 ARM Edition) run third-party extensions designed for Microsoft Office (for Windows x86)?
Most software, unless it uses inline assembly or SSE / MMX intrinsics, is a straight recompile.
A lot of programs' file formats depend on details of the x86 ABI because the programs pretty much just fwrite() a struct to disc.
Re:MS (Score:4, Insightful)
It would be best for Microsoft if ARM on the laptop/desktop was a complete flop. Sure, if what others say is true about the portability of Windows internals, Microsoft could release a version of Windows 7 for ARM. But really, what would be the point?
The biggest strength of Windows is running Win32 apps, and they are all compiled for Win/x86. Microsoft would have to provide development tools that encourage developers to make ARM binaries along side x86 binaries to even have a chance at making it happen.
Look at the average computer user's software catalogue, you will find many apps (and games) that were bought long ago and would cost money to upgrade to a potential ARM port if the company that made them are sill even in business. Those programs are never going to be ported to Win/ARM. Then there are all the drivers for last years peripheral hardware (assuming that the laptop's hardware is supported) that won't work.
I don't believe they can do what Apple did either. Apple was able to move to x86 from PPC because the control the hardware and moved their whole product line to it (killing PPC market). Any developers that wanted to stay in business had to port to x86. MS would be introducing a side product that would have a very small fraction of the bigger x86 customer base.
In the end all that Win/ARM has left is the few open source apps that choose to build an installer for it and the familiarity of the Windows desktop environment.
It would be in their interest to do everything in their power to make sure this doesn't ever get off the ground. We will have to wait and see what their next move will be.
Parent
Re: (Score:2)
> Apple was able to move to x86 from PPC because the control the hardware and moved their whole product line to it (killing PPC market)
and losing me as a customer in the process, albeit slowly as s/w became more and more incompatible with PPC. Of course, that wasn't the only reason, but still.
Re: (Score:3, Interesting)
Apple did not kill the PPC market. IBM did at least the desktop market, one day they decided to give up the PPC desktop processors without telling Apple. Apple did not have a choice, there were new desktop and notebook processors in the pipeline, while IBM busily was working on their high end server processors and was designing console processors for Sony and Microsoft with their old cores.
Re: (Score:2)
>> Microsoft can really change things around if they decided to port Win7 to ARM
Heard it through the grapevine that this is EXACTLY what they're doing, albeit not in a context you mentioned. A subset of full blown Windows kernel is being ported to ARM (a-la iPhone Mach) as a foundation for their "next" next gen mobile OS.
Re: (Score:3, Insightful)
Simpsons Did It (Score:2)
So, Sparrow, we meet again.
Yes. Sometimes I think that I am getting too old for this game.
-- The Crepes of Wrath --
Re:Press Release (Score:5, Informative)
And it's full of misinformation:
1) The A5 is not meant to take on Atom. The A9 is.
2) The A5 is not architecturally identical to the A9. The A9 is an in-order, multi-issue core. The A5 is an out-of-order, single-issue core. The only thing similar is it has the Cortex A-series ISA.
What the A5 is is a CPU that completely obliterates the ARM11-derived cores, used in everything from NVIDIA Tegra to the Nintendo DS. It's an update of the ISA, and a more capable core, with better thermals. That's it. Whereas every low-end smartphone now has the same damn QualComm ARM11-based core, in a year, they'll all have the A5.
Parent