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!

MIPS Technologies Porting Android 4.1 to MIPS Architecture

Unknown Lamer posted more than 2 years ago | from the architecture-wars-round-five dept.

Android 100

angry tapir writes with news on Android getting support for a third architecture. From the article: "ARM rival MIPS is continuing its push to make a mark in low-cost tablets and quickly trying to bring Android 4.1 (Jellybean) to its processors. 'We are working aggressively on bringing Jelly Bean to MIPS, and expect that it will be available to our licensees very soon,' said Jen Bernier-Santarini, director of corporation communications at MIPS, in an email. Tablets with MIPS processors are largely low-cost and have found buyers mostly in developing countries. MIPS last week said a new tablet called Miumiu W1 from Chinese company Ramos would become available in a few months in India, Latin America and Europe. The tablet has a 7-inch screen, a MIPS processor running at 1GHz, front camera and a microSD slot for expandable storage."

cancel ×

100 comments

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

In case you're wondering (4, Informative)

slashmydots (2189826) | more than 2 years ago | (#40685707)

Good, finally ARM manufacturers will stop having a monopoly where they can charge whatever they want. I've seen hints at OEM chip prices and they're ridiculous compared to even desktop chips. That will help everyone...just in time for x86 tablets to come out so people can actually run whatever they want.

By the way, if you're wondering as I did but were too lazy to look it up, yes, they actually named themselves MIPS without noticing that that's also Millions of Instructions Per Second, a method for measuring the speed of any CPU. Theirs stands for Microprocessor without Interlocked Pipeline Stages and it refers to an instruction set. What an unfortunate oversight. Stages could have been replaced with just about any other word to differentiate it.

Re:In case you're wondering (1)

game kid (805301) | more than 2 years ago | (#40685757)

What an unfortunate oversight.

Unless it was an intentional usurpation, like Microsoft's uses of .NET or DNS.

(Someone here made a comment about that; if I could find it I'd link it.)

Re:In case you're wondering (4, Interesting)

bluefoxlucid (723572) | more than 2 years ago | (#40685771)

OEM chip prices like the Tegra 3 at $35 for a quad core 1.4GHz with a fifth extremely-low-power core bounded to 500MHz in single processor mode? With a full system-on-chip including system bridges, memory controllers, and full nVidia graphics, $35 is ridiculous. Why a quad core Sandy Bridge processor doesn't cost half that!

Re:In case you're wondering (3, Interesting)

tepples (727027) | more than 2 years ago | (#40685841)

OEM chip prices like the Tegra 3 at $35

As a comment to a recent anti-Ouya story on Slashdot pointed out, even the data sheet for the Tegra 3 is available only to the highest volume manufacturers.

Re:In case you're wondering (1)

slashmydots (2189826) | more than 2 years ago | (#40685913)

And from the same company, a Geforce 210 card fully assembled costs around $35 so I can't imagine what the GPU originally cost and it's a bit faster. I think 610's just came out too and the price indicates the GPU was less than $35. I'm not sure if that's actually x86 actually but still. I know they're all feature heavy with energy savings and stuff and pricing based on performance isn't the best idea but I bet the electricity handling parts inside a Tegra 3 aren't quite as high grade and expensive as a 50-200W GPU lol.

Re:In case you're wondering (2)

bluefoxlucid (723572) | more than 2 years ago | (#40686397)

It's probably actually higher grade. The massive power output of a 50-200W processor is due to leakage--that is, it's due to poor efficiency. The Intel Atom for example was designed to leak less, and Intel's tighter packaging and lower TPD CPUs are based on new fabrication process that allows greater electrical efficiency. Bloated, poorly thought out designs bleed power as standing static field and heat--standing static field prevents smaller process, i.e. an imprecisely made junction will work on a 90nm process but at 32nm will bleed signal into all adjacent junctions and cause errors. Improving fidelity reduces bleed, allowing for a smaller process.

Somebody will clean up the stuff I glossed over for lack of understanding. The above's all just basics.

Re:In case you're wondering (1)

fuzzyfuzzyfungus (1223518) | more than 2 years ago | (#40686067)

Nvidia, dickish on providing specs? Impossible!

Re:In case you're wondering (1)

Anonymous Coward | more than 2 years ago | (#40687923)

Nvidia, dickish on providing specs? Impossible!

Companies making complex chips don't like releasing specs to all and sundry because someone might read them and realise they've broken a patent that they'd never previously heard of.

No specs even to (low volume) integrators (1)

tepples (727027) | more than 2 years ago | (#40696143)

Companies making complex chips don't like releasing specs to all and sundry

The problem comes when the maker of a component doesn't release specs even to companies integrating the component into a (lower-volume) product.

Re:In case you're wondering (2)

cachimaster (127194) | more than 2 years ago | (#40690151)

OEM chip prices like the Tegra 3 at $35 for a quad core 1.4GHz with a fifth extremely-low-power core bounded to 500MHz in single processor mode? With a full system-on-chip including system bridges, memory controllers, and full nVidia graphics, $35 is ridiculous. Why a quad core Sandy Bridge processor doesn't cost half that!

Is that a sarcastic question?
Tegra 3 and ARM in general is low power because it's small. You probably can pack 20 ARM cores inside a Sandy Bridge Core, even the Intel Atom, the smallest x86 core, is big next to an ARM core. You are comparing Apples to Oranges.

Re:In case you're wondering (1)

bluefoxlucid (723572) | more than 2 years ago | (#40711499)

Good, finally ARM manufacturers will stop having a monopoly where they can charge whatever they want. I've seen hints at OEM chip prices and they're ridiculous compared to even desktop chips.

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40692241)

Btw, a PowerVR SGX costs $0.30 . This includes the design, IP licensing, all software support, integration support and the additional design of any customizations. Just not the silicon.

Re:In case you're wondering (1)

Anonymous Coward | more than 2 years ago | (#40685823)

Good, finally ARM manufacturers will stop having a monopoly where they can charge whatever they want.

I though ARM processors were really inexpensive, we keep seeing cheaper and cheaper tablets, computers like the RaspberryPi, MK802, etc, all based on ARM
ARM have a monopoly, yeah, but it's because they're really better on price, performance and power consumption (AFAIK)

Re:In case you're wondering (1)

Anonymous Coward | more than 2 years ago | (#40685909)

You realize the Raspberry Pi only hits that price point due to heavy subsidizing by Broadcom, right?

Re:In case you're wondering (3, Informative)

daid303 (843777) | more than 2 years ago | (#40685959)

Good, finally ARM manufacturers will stop having a monopoly where they can charge whatever they want.

I though ARM processors were really inexpensive, we keep seeing cheaper and cheaper tablets, computers like the RaspberryPi, MK802, etc, all based on ARM
ARM have a monopoly, yeah, but it's because they're really better on price, performance and power consumption (AFAIK)

They are. But people always want cheaper and see monopolies where they want. To compare, we are currently in the process of replacing a 50 euro PowerPC chip with an 7 euro ARM chip, which is faster and more capable.

Re:In case you're wondering (3, Informative)

ericloewe (2129490) | more than 2 years ago | (#40685829)

They've been around for ages... Anyone who might need/want to know the architecture can easily differentiate MIPS from MIps, just ike everybody can distinguish ARM from arm.

Re:In case you're wondering (2)

slashmydots (2189826) | more than 2 years ago | (#40685931)

As long as it's in all caps, nobody should misunderstand it...unless they say "IT'S AN ARM-KILLING TABLET!" which definitely implies it's extremely heavy, lol.

Re:In case you're wondering (1)

obirt (713598) | more than 2 years ago | (#40688295)

Then what do you say to StrongARM?

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40692277)

Nothing, just a Thumbs up.

Re:In case you're wondering (1)

mvdw (613057) | more than 2 years ago | (#40694979)

"IT'S AN ARM-KILLING TABLET WITH 1 MIPS PROCESSOR!!1!1!one!!" Some more text to get over Slashdot lameness filter for all caps. That was kind of the point, and now the joke's been ruined.

Re:In case you're wondering (1)

MightyYar (622222) | more than 2 years ago | (#40686073)

I'm still bitter after trying to eat my Apple.

And my Commodore was a terrible military strategist.

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40686235)

Even without the context of the previous posts, here's my typical reaction to your comment:

And my Commodore was a terrible military strategist.

So you had a commodore called Commodore? Talk about coincidence...

I'm still bitter after trying to eat my Apple.

What kind of food was your so called Apple? Was it an apple, or maybe a new brand of sandwich? I sure hope you didn't try to bite your computer!

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40686611)

-1, Bland

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40688811)

What if like 5 guys in the audience came up and blanded you like right now, wouldn't that be funny?

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40688461)

-1, unfunny idiot

Re:In case you're wondering (1)

Canazza (1428553) | more than 2 years ago | (#40686347)

My Mega Drive couldn't even reach the pedals

Re:In case you're wondering (1)

galanom (1021665) | more than 2 years ago | (#40693241)

I think that both are properly capitalized as "MIPS". Why Mips or MIps? Unless you also say also Mflops?
Well, thankfully it doesn't matter anymore as no processor is measured in MIPS or MFLOPS. Even low power chips are in the range of Giga.

Re:In case you're wondering (1)

ericloewe (2129490) | more than 2 years ago | (#40696609)

Why MIps? I prefer it because:

Capital M for decimal Mega (as in million)
The i is kinda indifferent, but since Mips is the rabbit in Super Mario 64, I prefer a capital I
Lowercase p for "per"
Lowercase s because SI units are lowercase unless they're named after a person.

Re:In case you're wondering (1)

wjousts (1529427) | more than 2 years ago | (#40685907)

Stages could have been replaced with just about any other word to differentiate it.

Yeah, like Steps! ...oh wait...nevermind.

Re:In case you're wondering (4, Insightful)

fuzzyfuzzyfungus (1223518) | more than 2 years ago | (#40686053)

To what degree are 'ARM manufacturers' reasonably a monopoly? The rise of ARM devices whose performance people give a fuck about does seem to have opened room for whoever is currently selling the hottest part on the street to charge a nontrivial premium; but cut back a bit from the bleeding edge and it's a veritable knife-fight of utterly undistinguished and cheap offerings.

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40687329)

The ARM manufacturers add their own IP (internal buses, peripherals, etc.) to the ARM core and that is what distinguishes their offerings from those of others. You make it sound as if they all make pretty much the same thing. I have worked on several ARM SoCs and I can tell you, some are a joy to work with and others are a real pain. The peripherals are what makes or breaks the device.

Re:In case you're wondering (1)

sapphire wyvern (1153271) | more than 2 years ago | (#40695215)

That's interesting!

If you have the time, I'd love to hear which were your favourite SoCs and which were the worst to work with - especially if you can comment on what were the distinguishing factors that made them a joy or pain to work with.

Re:In case you're wondering (3, Informative)

Anonymous Coward | more than 2 years ago | (#40686411)

MIPS has been around for some time. They used to make RISC processors for workstation class machines and even had a Windows NT distribution that was geared to high performance floating-point operations. This was in the early nineties when there were competitors in the 32-bit windows platform. DEC-Alpha, Intel, MIPS all had versions of Windows NT, and there were versions of AutoCAD, 3D Studio, and some of the Adobe products as well.

MIPS biggest success at the time was their use in SGI workstations that fueled the early nineties CGI craze. MIPS also produced the processor at the heart of the N64.

RISC architecture didn't win the desktop/workstation battle so companies like MIPS and ARM moved on to efficient platforms that end up powering low-power/portable devices like tablets/phones.

Re:In case you're wondering (2)

Narishma (822073) | more than 2 years ago | (#40686665)

MIPS also produced the processor at the heart of the N64.

And the PS2 and PSP and multitudes of routers and set top boxes.

Re:In case you're wondering (1)

Bert64 (520050) | more than 2 years ago | (#40686919)

One advantage MIPS has over ARM, is that while higher end and server class chips are new to ARM, MIPS was doing 64bit server-class chips and massive multiprocessing years ago... There is already a well defined MIPS64 architecture, complete with mature compilers and OS support.

Instead of targeting cheap and lowend, they should be going after low power servers...

Re:In case you're wondering (2)

unixisc (2429386) | more than 2 years ago | (#40687485)

Fully agree w/ all of the above posters. If any CPU has covered the entire spectrum of low power to high performance, it's been MIPS. Alpha used to be known for its excessively high power dissipation, PPC's low power offerings rarely was low in power consumption, ARM rarely had the performance, while PA-RISC and SPARC hardly played in the low power space. It's tragic that MIPS has lost the console market to the PPC, but they can still recoup w/ both tablets and low power servers. Currently, AFAIK, it's still the most popular for networking gear.

One unusual change that MIPS did was to go from a super-pipelined architecture to super-scalar when they introduced MIPS-IV. Alpha, by contrast, went from just super-pipelined to super-scalar, super-pipelined, while Intel went from super-scalar to super-scalar, super-pipelined. Nobody else went for super-pipelining, since the frequency increases wouldn't result in a substantial performance increase.

Incidentally, anyone know who the current manufacturers of MIPS are, outside China's Loongson and XBurst? Do NEC, QED or anyone else still make them? Also, which ones are popular - the ones based on the R4x00 or the ones based on the R50000 (MIPS IV)?

Aside from the MIPS, there is also OpenRISC, which uses most of the MIPS instructions, but w/ some exceptions. Wonder whether anybody would fab them, and how they would compare against the MIPS?

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40687885)

The only other active manufacturer I know of is Microchip, who went with MIPS for their PIC32 line of microcontrollers. Renesas have made some announcements regarding a partnership with MIPS at the start of the year, but nothing has come out of that yet. They're also have way too many architectures already, and are busy going bust.

I've never really made head nor tail of MIPS' architecture and core families. I believe MIPS32 4K and its variants were kind of popular, but since most usage of MIPS cores is deeply embedded it's hard to tell.

Most recently MIPS have aped ARM by dividing their core linup into three rebranded families: proAptiv (high-performace), interAptiv (midrange) and microAptiv (embedded and microcontrollers). Just to make everything more simple. I bet they introduced a couple of new ABIs too, just for the hell of it.

If you can cough up the money it shouldn't be hard to find a fab for the OpenRISC. Eg. ST Microelectronics fabbed the Godson/Loongson even before they properly licensed the MIPS32 core. However it's going to take more than a Kickstarter to make it happen.

Re:In case you're wondering (1)

Matt_Bennett (79107) | more than 2 years ago | (#40689309)

Microchip uses the MIPS 4K core in PIC32. I am not aware of any other microcontroller vendor that use MIPS in a released product. MIPS cores are all over the place. Since the majority (plurality?) of embedded programming is in C anyway, how much does the core really matter? In the microcontroller world, everything revolves around power and peripherals.

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40691307)

Dealing with microcontrollers it's almost inevitable that you have to deal with the core, eg. dealing with interrupts. You also want to be able to examine the compiler output, and it's good to know what the core's strong or weak points are.

Re:In case you're wondering (1)

Wesley Felter (138342) | more than 2 years ago | (#40689057)

MIPS is still big in networking; see Cavium and Raza/NetLogic/Broadcom.

Re:In case you're wondering (1)

Bert64 (520050) | more than 2 years ago | (#40702823)

I've actually been trying to buy a Loongson-3, but they don't seem to be available anywhere... They published pictures of various motherboards, but none of them seem to be available to buy.

Re:In case you're wondering (2)

TheRaven64 (641858) | more than 2 years ago | (#40688543)

One disadvantage MIPS has is that it has a completely batshit insane architecture full of things that kind-of vaguely made sense in a research project and have been a liability for over a decade.

I'm currently working the MIPS back end in LLVM and every day brings a new WTF. ARM, at least, has a mostly sane architecture and in the 64-bit variant has removed a load of stuff that doesn't make sense with newer pipeline designs (e.g. store multiple, conditional adds, and so on). MIPS just accumulates legacy cruft. It's not quite as bad as x86 in that regard, but it's also an astonishingly verbose instruction set. Where ARM or x86 can do something in 2-3 instructions, MIPS is lucky to manage in half a dozen. It's not a coincidence that the decline of MIPS on the high end coincided with instruction cache utilisation being important. Oh, and every MIPS vendor adds some extra incompatible changes to the instruction set just to make life even more fun.

Re:In case you're wondering (1)

Wesley Felter (138342) | more than 2 years ago | (#40689037)

For some reason I looked at the MIPS Web site the other day and they have no 64-bit cores. It looks like they've completely abandoned 64-bit.

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40688075)

RISC architecture didn't win the desktop/workstation battle so companies like MIPS and ARM moved on to efficient platforms that end up powering low-power/portable devices like tablets/phones.

If you think that Intel or AMD x86/x64 CPUs are still executing something like "rep stosw" in hardware, I've got a bridge to sell you.

RISC won the battle. Just because you can't see it directly doesn't mean it isn't there.

*WOOSH* (0)

Anonymous Coward | more than 2 years ago | (#40688423)

By the way, if you're wondering as I did but were too lazy to look it up, yes, they actually named themselves MIPS without noticing that that's also Millions of Instructions Per Second, a method for measuring the speed of any CPU.

https://en.wikipedia.org/wiki/Pun [wikipedia.org]

Re:In case you're wondering (1)

pchan- (118053) | more than 2 years ago | (#40688723)

This is either either comedy or extreme stupidity, but I can't tell which.

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40689285)

This is either either comedy or extreme stupidity, but I can't tell which.

Regarding the ARM `monopoly' the post itself is either sarcasm or malcontent idiocy. Hard to say which. The "Informative" up-mods are, however, genuinely pathetic.

Re:In case you're wondering (0)

Anonymous Coward | more than 2 years ago | (#40693539)

Buh is this a different (sold off) MIPS then has been around for a VERY LONG TIME at one point owned by SGI, to be just noticing the name?

Fragmentation (4, Insightful)

Dan East (318230) | more than 2 years ago | (#40685789)

Great. Now we'll see the same fragmentation Windows CE had all those years. Most games use the NDK and contain binary compiled specifically for ARM. Obviously those apps will not run on the MIPS processor. Microsoft eventually learned this was not a good thing and finally forced all OEMs to use ARM to qualify for Pocket PC branding.

Now all we need is Android running on SH3 and we'll have gone full circle.

Re:Fragmentation (4, Insightful)

Tapewolf (1639955) | more than 2 years ago | (#40685847)

Great. Now we'll see the same fragmentation Windows CE had all those years. Most games use the NDK and contain binary compiled specifically for ARM. Obviously those apps will not run on the MIPS processor.

The NDK now has MIPS support out of the box. Going forward it would probably be a good idea to compile for all supported targets.

Re:Fragmentation (0)

Anonymous Coward | more than 2 years ago | (#40686553)

An interesting side effect of Google's market design is that there will not be a MIPS version, an Atom version, and an ARM version of these apps. Rather, there will be a single app which technically can contain MIPS, Atom (x86), and ARM code.

As more CPU become supported, including sub-variants (example, hardware floating point and not), more and more space is ultimately wasted on every target. I suppose in the long term, as more CPUs become supported, it will push the available flash space upwards. The down side is, expect apps to grow larger over time, consuming more bandwidth to download and update. If you're on a metered connection, expect android phones to indirectly cost you slightly more in the future.

Re:Fragmentation (0)

Anonymous Coward | more than 2 years ago | (#40686781)

No, When you put an application on the Android Market, You can have different compiled binaries of the same app. You can specify which devices each variant of the app are installed on. Each device can have support for just the hardware it runs.

Re:Fragmentation (1)

Bert64 (520050) | more than 2 years ago | (#40686943)

Or handle it at the market stage, and only send/store the appropriate binaries based on the device installing it...

Re:Fragmentation (4, Informative)

bluefoxlucid (723572) | more than 2 years ago | (#40685873)

It doesn't matter really. ARM uses some 0.1-1.0W, MIPS uses 10-20W for slower clock speeds. ARM has fixed-width single-decode instructions; MIPS has three types of instructions of variable width. ARM does damn near everything in one clock, including evaluate-and-execute prefixed instructions ( { if ( n ) m = 5; } is 2 insns: 'cmp n' and a prefixed 'movnz m, 5'. If n == 0, movnz means 'nop'; otherwise it means 'mov'. Instead of 'cmp n; jnz @@a; mov m,5; @@a:' where jnz and mov have to be evaluated in separate stages. Yes it's been 11 years since I did assembly, it was 286 and 6502, and I'm unfamiliar with ARM by far). MIPS is slow. You may as well put an Intel CELERON in there if you go MIPS.

Re:Fragmentation (0)

Anonymous Coward | more than 2 years ago | (#40685897)

ARM also has an instruction set with multiple widths.

Re:Fragmentation (0)

Anonymous Coward | more than 2 years ago | (#40686661)

MIPS instructions are fixed width. 64 bit ARM is ugly compared to MIPS solution.

Re:Fragmentation (0)

Anonymous Coward | more than 2 years ago | (#40686815)

BS. ARM has thumb2 which has variable width instructions and like ARM, base MIPS has 32 bit instructions only. Also, if conditional prefixes were so great, why's ARM64 eliminating them.

MIPS32 can do that in 3 instructions:
move $t1, 5
sltiu $t0, n, 1
movn m, $t1, $t0

Re:Fragmentation (4, Insightful)

TheRaven64 (641858) | more than 2 years ago | (#40688659)

Also, if conditional prefixes were so great, why's ARM64 eliminating them.

ARMv8 is not eliminating them, it's reducing the number of instructions that have them. Conditional instructions are useful because you can eliminate branches and so keep the pipeline full. For example, consider this contrived example:

if (a < b)
a++;

On ARMv7 and earlier, this would be a conditional add. The pipeline would always be full, the add would always be executed, but the result would only be retired if the condition is true. On MIPS, it would be a branch (complete with the insanity known as branch delay slots, which if you look at the diassembly of most MIPS code typically means with a nop, so you get to waste some i-cache as well) and if it's mispredicted then you get a pipeline stall.

On ARMv8, you don't have a conditional add, but you do have a conditional register-register move and you have twice as many registers. The compiler would still issue the add instruction and then would do a conditional move to put it in the result register. From the compiler perspective, this means that you can lower PHI nodes from your SSA representation directly to conditional moves in a lot of cases.

Basically, 32-bit ARM is designed for assembly writers, ARMv8 is designed for compilers. As a compiler writer, it's hands-down the best ISA I've worked with, although I would prefer to write assembly by hand for ARMv7. I wouldn't want to do either with MIPS, although I currently am working on MIPS-based CPU with some extra extensions.

Re:Fragmentation (0)

Anonymous Coward | more than 2 years ago | (#40689897)

As the example I posted illustrates, MIPS does have conditional moves and has for years (movn and movz). Yes, branch delays do suck but try doing an unaligned load on MIPS vs ARM.

Re:Fragmentation (1)

antime (739998) | more than 2 years ago | (#40691357)

ARM has supported unaligned loads for a while (since ARMv6 I believe).

Re:Fragmentation (0)

Anonymous Coward | more than 2 years ago | (#40693029)

Fair enough, I'm not familiar with ARMv6 but with ARMv4 and 5 unaligned load were a bitch compared to MIPS lwl and lwr.

Re:Fragmentation (2)

pchan- (118053) | more than 2 years ago | (#40691831)

ARMv8 is not eliminating them, it's reducing the number of instructions that have them. Conditional instructions are useful because you can eliminate branches and so keep the pipeline full. For example, consider this contrived example:

if (a < b)
  a++;

On ARMv7 and earlier, this would be a conditional add. The pipeline would always be full, the add would always be executed, but the result would only be retired if the condition is true. On MIPS, it would be a branch (complete with the insanity known as branch delay slots, which if you look at the diassembly of most MIPS code typically means with a nop, so you get to waste some i-cache as well) and if it's mispredicted then you get a pipeline stall.

On ARMv8, you don't have a conditional add, but you do have a conditional register-register move and you have twice as many registers. The compiler would still issue the add instruction and then would do a conditional move to put it in the result register. From the compiler perspective, this means that you can lower PHI nodes from your SSA representation directly to conditional moves in a lot of cases.

Basically, 32-bit ARM is designed for assembly writers, ARMv8 is designed for compilers. As a compiler writer, it's hands-down the best ISA I've worked with, although I would prefer to write assembly by hand for ARMv7. I wouldn't want to do either with MIPS, although I currently am working on MIPS-based CPU with some extra extensions.

Actually, ARM's reasoning is that modern branch predictors on high end AP's can do a good enough job of following a test and branch and keeping the pipeline(s) full that there is very little value in conditional instructions on future chips. It's hard to cause a pipeline stall or bubble by branching a few instructions forward or back on these CPUs since they are decoding well in advance of the execution pipelines. Added to that, there is an energy cost in executing an instruction and throwing away the result. Obviously, not all cases are wins. In the example you noted, a register to register mov on a register-renaming system is basically a 0-cycle operation (never makes it out of the instruction decoder), so it's hard to do better than that.

Re:Fragmentation (0)

Anonymous Coward | more than 2 years ago | (#40687555)

quit talking out your ass dude.
someone mod this joker down.

Re:Fragmentation (5, Informative)

YoopDaDum (1998474) | more than 2 years ago | (#40687809)

ARM uses some 0.1-1.0W, MIPS uses 10-20W for slower clock speeds.

Not anymore, by far. Forget about MIPS as in Silicon Graphics workstations ages ago. Now MIPS is an embedded IP provider, very similar to ARM. And they do have low power cores quite similar to ARM. Who is on top in mW/MHz changes over time, but MIPS do have some competitive offers.

Now what ARM has for it is that it became the defacto architecture for mobile (nobody got fired to chose ARM and all that), and it has much more resources than MIPS. So ARM has a more extensive IP offer, and can work on process optimization too. By this I mean that where MIPS will provide a soft core in RTL, ARM can also provide hard macros optimized for some fab process. And even if you want to go soft core and optimize yourself, ARM can provide a ready to use optimization package to get you started.

ARM has fixed-width single-decode instructions; MIPS has three types of instructions of variable width.

No, they're actually very similar: their native instruction size is 32 bits, but both support a 16 bits instruction mode which is in its second generation in each case (Thumb2 for ARM, can't remember the MIPS name... Maybe MIPSe?).

MIPS is slow. You may as well put an Intel CELERON in there if you go MIPS.

Why the comparison with a discrete chip? MIPS do no sell discrete chips anymore, it's all IP. Then in IP they have offer that are performance competitive with the same class ARM. I'd give the edge in the high end to ARM though, thanks to their close work with the fab to optimize their implementation.

Re:Fragmentation (1)

evilviper (135110) | more than 2 years ago | (#40687973)

MIPS is slow. You may as well put an Intel CELERON in there if you go MIPS.

I don't know where you get your information from. MIPS processors have had a much higher DMIPS/MHz than ARM CPUs for as long as I can remember.

Re:Fragmentation (1)

cachimaster (127194) | more than 2 years ago | (#40691073)

Mod parent down!
MIPS 10-20W? you cannot drop numbers like that without any citation! I have in my hand a PIC32, a full MIPS that consumes some milliwatts. MIPS and ARM are Instruction sets, not CPUs. There are slow and fast implementation of the ARM ABI, and slow and fast implementations of MIPS ABI.

Re:Fragmentation (0)

Anonymous Coward | more than 2 years ago | (#40693989)

So you say you're unfamiliar, yet make irrational comparisons with a 20W processor probably from a 4000 MIPS from an Indy SGI?

You'd expect MIPS to have at least used a better process for any of their chips and get a power gain.

How the hell someone talking about 286 and 6502s (note that 286 were in the market waaaaaaaayy longer than 11 years ago), with no accurate comparison data, gets modded +4 Informative? Did /. became a piNata where points just come from thin air? Or is this "whose line is it anyways" and Drew is just giving points away?

Re:Fragmentation (0)

Anonymous Coward | more than 2 years ago | (#40686147)

NDK can cross-compile for ARM, MIPS, and x86 simultaneously already, and when you push the package to the Android Google Play Market Store or whatever they're calling it now, it will detect what device is downloading it and give them the correct architecture.

Obviously if you use assembler you're fucked but that's been true since before I was born.

Re:Fragmentation (1)

naturaverl (628952) | more than 2 years ago | (#40686743)

Most games use the NDK and contain binary compiled specifically for ARM. Obviously those apps will not run on the MIPS processor.

Um... Unless they are recompiled to run on MIPS? I don't really see the problem as GCC already supports this.

Re:Fragmentation (1)

romiz (757548) | more than 2 years ago | (#40687179)

Now all we need is Android running on SH3 and we'll have gone full circle.

The newest Renesas application chips are based on ARM, with a SH4 core only as a coprocessor, so this particular monster will probably never exist.

Restricted boot (1)

ickleberry (864871) | more than 2 years ago | (#40685825)

It's not x86 so it's not safe from mandatory M$ restricted boot.

Re:Restricted boot (0)

Anonymous Coward | more than 2 years ago | (#40687409)

Yes it is safe, just don't ever buy anything with Microsoft-locked UEFI boot.
If everybody does that, there really is no problem whatsoever.
The OEMs will not sell them if there is no market for them.
You may ask your lawmakers to order them to put a sticker on the product: "this is not a general-purpose computer; instead this computer is locked down by Microsoft to only install sofware Microsoft allows".

I know it's a bad pun.......... (0)

Anonymous Coward | more than 2 years ago | (#40685943)

But how many BogoMips does that proccessor have?? >.>

Incidentally... (4, Interesting)

fuzzyfuzzyfungus (1223518) | more than 2 years ago | (#40685985)

Forgive my ignorance; but when and how did MIPS get relegated to second-class status? I still see them crop up from time to time, certain cheapy router SoCs still come out with MIPS cores; but ARM appears to have gone rampaging across much of the territory that Intel hasn't already entrenched themselves in.

Was there a fuckup or an epic design win at some point in the past?

Re:Incidentally... (3, Informative)

k(wi)r(kipedia) (2648849) | more than 2 years ago | (#40686273)

Wikipedia [wikipedia.org] is your friend. Apparently, like an unwanted child, the company got passed around a few times, being bought by SGI, only to be spun out again. It's easy to speculate how an engineer working for an unstable company like that would have other things in mind besides designing the fastest and greatest processors.

Re:Incidentally... (0)

Anonymous Coward | more than 2 years ago | (#40686327)

Expensive license costs.

Re:Incidentally... (0)

Anonymous Coward | more than 2 years ago | (#40686351)

Forgive my ignorance; but when and how did MIPS get relegated to second-class status? I still see them crop up from time to time, certain cheapy router SoCs still come out with MIPS cores; but ARM appears to have gone rampaging across much of the territory that Intel hasn't already entrenched themselves in.

Was there a fuckup or an epic design win at some point in the past?

Mips decided to concentrate on their 64-bit offerings and selling chips (more profit in chips) and left the low-end 32-bit licensing IP space open for ARM to gain a foothold. SOCs wanted cheap licences and 32-bit was good enough... By the time Mips woke up, it was late to the party.

Re:Incidentally... (2, Interesting)

Anonymous Coward | more than 2 years ago | (#40686385)

MIPS is stuck in an unfortunate limbo between ARM and PowerPC. They lost the home console market to PowerPC (PS1, PS2, N64 were MIPS, but NGC, 360, Wii, PS3 are PowerPC). They lost the portable console market to ARM (PSP was MIPS, PS Vita is ARM, and Nintendo went straight from Z80 to ARM). They're still popular for el cheapo home routers, but they're being squeezed by ARM on one side (small servers/plug-boxes/routers) and by PowerPC and Atom on the other side (NAS, larger home servers). Pro networking gear, of course, runs on PowerPC.

This is a doomed attempt to gain a small slice of the cheapo Chinese tablet market, but honestly, with Chinese ARM chips like the Allwinner A10 out there, their chances of success are minimal.

Re:Incidentally... (1)

Bert64 (520050) | more than 2 years ago | (#40686993)

As ARM moves higher end, MIPS would be better placed... While ARM is only just coming up with a 64bit variant, MIPS has had one for years and which already has support from linux/gcc/etc.

Going after the cheapest end of the market is probably not the best choice, going after the low power server and highend tablet/smartphone market would make a lot more sense.

Re:Incidentally... (3, Informative)

YoopDaDum (1998474) | more than 2 years ago | (#40687879)

I'm not sure that MIPS is so well placed in the high-end. Yes, they've been high end a long time ago and have had 64 bits support for ages. But today it's a different game, they provide embedded IP now. And where ARM can help their customers optimizing the implementation for a given process (ARM gains this experience by making hard macros and working closely with TSMC, GlobalFoundries...), MIPS has much less resource and just do soft macros. Then up to you to do the optimization. In other words, if you go ARM for an embedded high-performance SoC IP you can leverage a lot of work that ARM does, that you will have to do with MIPS. To get an implementation that is less common in the end.

So the high end may be tough for MIPS. But in the medium end, where price is critical and performance less so, they can be an interesting choice.

The luck of market speciality and the iPhone (0)

Anonymous Coward | more than 2 years ago | (#40686443)

Very early on, back in the 1990s, ARM and MIPS differentiated themselves by ARM going after phones and MIPS going after computer appliances in their desperate quest for revenue. Thus MIPS being in the PS1, N64, PS2 and current routers. This turned into a massive win for ARM in the aftermath of the iPhone, when smartphones became the breakaway non-x86 personal computing platform. Now MIPS is trying to get in on the party.

Originally, again back in the 1990s, MIPS had better support under Windows CE, and thus was primed for the market segment ARM currently rules, that of "handheld personal computers." Of course those devices weren't also phones, so them were niche devices. And Apple, in choosing ARM for the iPhone over PortalPlayer (iPods) and MIPS, not only was looking at their phone expertise, but Apple also had helped float ARM back in 1990, and still owned an interest in the company.

Luck of the draw.

Re:Incidentally... (0)

Anonymous Coward | more than 2 years ago | (#40686683)

Forgive my ignorance; but when and how did MIPS get relegated to second-class status? I still see them crop up from time to time, certain cheapy router SoCs still come out with MIPS cores;

Let's rewind a bit.

[bzzpwwwt] certain cheapy router SoCs

And again.

[zwwt] cheapy router SoCs

Ahh, that might be where the second-class status came from!

Re:Incidentally... (0)

Anonymous Coward | more than 2 years ago | (#40687339)

The top of the range routers also use MIPS. When the telecomms makers picked an ISA for licensing, MIPS was used in supercomputers and ARM was limited to small microcontrollers.

Re:Incidentally... (1)

Anonymous Coward | more than 2 years ago | (#40687241)

Whereas ARM is prolific in consumer-grade portable devices (phone, tablets, etc), MIPS is more prevalent in embedded devices and datacenter appliances. Especially in the networking field, for some reason. A lot of wifi access points, routers, and "modems" have MIPS inside. (WRT54G, for example.) High-end network gear from Cisco, Radisys, and other manufacturers often have dozens of MIPS cores per device to move packets from one network subsystem to the next.

Re:Incidentally... (0)

Anonymous Coward | more than 2 years ago | (#40687483)

Simple greed. MIPS blew it with their licensing scheme and never recovered.

As far as I understand it... (1)

emil (695) | more than 2 years ago | (#40689727)

  • Code density - the same code can often compile to fewer bytes on ARM. The 6502 influenced the ARM instruction set, yeilding many tricks, shortcuts, and optimizations. MIPS is a more "conventional" design, and suffers from (standard) RISC code density bloat.
  • Power - the original ARM dissipated 0.1 watts; MIPS has had to work to get down that low.
  • Transistor count - the original ARM had 30,000 transistors, and has not ramped up (as) significantly in core transistor count (disregarding new functional units).
  • Lack of 64-bit bloat - MIPS was forced to scale to supercomputer range, and swallowed legacy high-performance baggage which impedes embedded suitability. ARM has laser-focused on high-performance for small devices, and is just now introducing 64-bit.

MIPS - there's a blast from the past (3)

Chrisq (894406) | more than 2 years ago | (#40686029)

I remember when Windows ran on MIPS!

Re:MIPS - there's a blast from the past (1)

TheGratefulNet (143330) | more than 2 years ago | (#40687435)

the old DECstations (not VAXstations) used MIPS chips inside. I still have an r3000 or something lying around. ultrix 4.2 was the last I remember of that series. seems like more than a lifetime ago.

Re:MIPS - there's a blast from the past (0)

Anonymous Coward | more than 2 years ago | (#40689573)

The "radio" in my car has a MIPS processor, it runs Windows CE 6

There are some hacks to get more functionality out of it, but until someone figures out how to load drivers on it I won't be able to get a GPS lock.

Would be interested in loading android on it, but then I would probably loose the Bluelink service.

Re:MIPS - there's a blast from the past (0)

Anonymous Coward | more than 2 years ago | (#40693333)

I'm glad to see I'm not the only old-timer around =]

All we need now is sh3.. (0)

Anonymous Coward | more than 2 years ago | (#40686059)

.. And we'll be back in the bad-old wince days! Man, I don't miss that platform at all.

Mips sure has been a waning platform. SGI's gone, and with it their high-end. Arm has been eating them up in the mobile space for decades, and as a halo effect it's been replacing mips in the embedded fields too.

There is, however, a lot of renewed interest coming from china. Their home-grown chips are mips based and they're churning out more, faster, higher core count packages every couple of months. (In fact I bet this is the basis for most of the interest in mips-andriod.) I bet we'll be seeing those seep in to market. Heck, nvidia just lost a bunch of GPGPU customers in china because they refused to develop mips linux drivers.

Mips has nothing on ARM (0)

Anonymous Coward | more than 2 years ago | (#40686141)

Good luck trying to match ARM's mimd, simd, thumb, jazelle, every instruction supporting conditionals, and the support for foreign ISA's.

Re:Mips has nothing on ARM (0)

Anonymous Coward | more than 2 years ago | (#40687125)

MIPS have had SIMD for a while, MIPS16 is their version of a narrower instruction set. Jazelle is deprecated (no-one even used it because of licensing BS), conditionals on every instruction are wasteful and were removed from Thumb-2 and ARM64.

In most respects, ARM and MIPS are pretty much equal. There are however vastly more ARM implementations out there, especially if you're talking about chips anyone can buy without being a billion-dollar telecomms company. The only place you're currently likely to run into MIPS is if you're using PIC32 microcontrollers.

Goodbye closed interface (1)

DeTech (2589785) | more than 2 years ago | (#40686597)

Finally I'm one set closer to getting apps on my smart tv box.

MIPS for super computers (1)

techtech (2016646) | more than 2 years ago | (#40686685)

Seems like MIPS has been used in budget super computers lately in China. Nice that they are early out with porting this. Someone should make a cheap unbranded, unthemed, vanilla. android phone.

Is this the year? (0)

Anonymous Coward | more than 2 years ago | (#40686965)

Is this the year of the Linux tablet? Is this the year of the Linux smartphone? Was that last year? Wooot!

So that means RMS could install it on his Leemote (0)

Anonymous Coward | more than 2 years ago | (#40688065)

Just sayin....

Chinese Innovation lost on West :( (0)

Anonymous Coward | more than 2 years ago | (#40689407)

I hope this catches on in chinese market place. For those who aren't on the up and up of what are considered "cheap chinese knockoffs." They actually have some great products, usually in the Portable Music Player market (which Ainol and Ramos usually do), everything plays OGG, FLAC, MVK, in hardware (yes I know the difference between a container and an encoding scheme bare with me...), they often advertise 1440p ( while this standard isn't out so you can watch it in that, it does mean 1080p doesn't lag), have HDMI outs, USB-OTG, and other stuff that is not amazing and you can get this for like 50-100 bucks. Though the down sides are horrible battery life(good batteries are expensive), and low long term storage memory; 16 gigs max, but expandable.

PSP (0)

Anonymous Coward | more than 2 years ago | (#40690225)

Prepare to get a port for the PSP.

Check for New Comments
Slashdot Login

Need an Account?

Forgot your password?