PowerVR MBX in iPhone

[Rob Evans]

It seems that the iPhone main chip contains a PowerVR MBX 3D graphics processor.

From http://iphone.fiveforty.net/wiki/index.php?title=Firmware/all_flash/all_flash.m68ap.production/DeviceTree.m68ap.img2

device 0 (10 rec)
"device_type" => 0x78626D
"clock-ids" => 0x2
"reg" => (8) "\x00\x00\x00\x03\x00\x00\x00\x01"
"power-gates" => 0x2
"clock-gates" => 0x13
"compatible" => (13) "mbx,s5l8900x\x00"
"interrupt-parent" => 0x403BD0
"name" => 0x78626D
"interrupts" => 0xC
"AAPL,phandle" => 0x40C570

N.B. 0x78626D is ASCII for xbm - mbx in reverse format.

[RedGuard]

MBX libraries are also mentioned in crash logs (http://iphone.fiveforty.net/wiki/index.php?title=Sample_Crash_Log):-

0x31baf000 - 0x31bb1fff MBXConnect UUID (B5E73A95A84E4706A922D56674D4809D) /System/Library/Frameworks/MBXConnect.framework/MBXConnect
0x31bb4000 - 0x31be5fff OpenGLES UUID (3405A88B732E4DF3A127E182483D9E69) /System/Library/Frameworks/OpenGLES.framework/OpenGLES

[obo]

The following graphics-related MBX strings can be found in file57 in the zip file at the top of this page (http://iphone.fiveforty.net/wiki/index.php?title=KernelCache_Files_List):


AppleMBXDevice(%p): Graphics hang with pending 2D blit. Free slots=%d, IntStatus=%08x
AppleMBXDevice(%p): Graphics Restart. Known MBX hardware issue (rdar://4809859)
AppleMBXDevice(%p): TA not idle, deferring graphics restart
AppleMBXDevice(%p): Graphics Restart during 3D Blit. Dummy page corrupted=%d, 3DR=%d, ISP=%d, EVM=%d
AppleMBXDevice(%p): Graphics Restart during 3D Render. Dummy page corrupted=%d, 3DR=%d, ISP=%d, EVM=%d
EnableGLClockgateWorkaround AppleMBXDevice(%p) - Warning: Switching clockgate workaround modes when the HW is not idle. Results undefined.
%s: EnableGLClockgateWorkaround key of wrong type
AppleMBXDevice(%p)::flushWrapperCache: blit cache flush took too long
AppleMBX: Failed to add a surface mapping because prepare() failed or couldn't fit in MMU. Skipping command.
AppleMBXDevice(%p)::interruptHander: got MBX1_INT_TA_STREAM_ERR
Invalid surface %08lx while processing command sequence. Aborting command buffer.
virtual bool AppleMBXDevice::start(IOService*) mbx-clockgate chip-revision AppleMBX: Disabling auto clock gating because this is a EVT0/EVT1 AppleMBX: Enabling auto clock-gating: %d
IOCoreSurfaceRoot %s: IOCoreSurfaceRoot not available or of the wrong class
compatible mbx,s5l8900x true false AppleMBX: Detected %s. SupportsWriteCombining: %s
PPPPPPPP -RRRRRGGGGGBBBBB --------RRRRRRRRGGGGGGGGBBBBBBBB AppleMBXDevice(%p)::start - Failed to setup 3D blit support
IOMobileFramebuffer AppleMBX Workaround: Clock gating disabled
AppleMBXUserClient AppleMBXUserClient(%p)::mapSurface - Failed to malloc MBXSurface
Failed to look up CoreSurfaceID %x
Failed to lock a CoreSurfaceBuffer: err=%x
AppleMBX mapSurface: too large to map: size=%ld max allowed=%d
AppleMBXUserClient(%p)::wireSurface - Failed to create wired MBXSurface
AppleMBXUserClient(%p)::wireSurface - Failed to wire MBXSurface
AppleMBX wrapSurface: too large to map: size=%d max allowed=%d
AppleMBXUserClient(%p)::addRenderTarget: Failed to run AddRenderTarget command
cleanupMemInfo: failed to clean up surface
Failed to unlock a CoreSurfaceBuffer
PVR: (%u,%s)
Debug assertion failed! PVRDebugAssertFail

[roninja]

now to find out whether this is part of the SoC or a standalone chip!

[loekf]

now to find out whether this is part of the SoC or a standalone chip!

Oh my oh my... this is quite interesting. You can almost draw a block diagram just from the list of devices. Some interesting bits and pieces:

- ARM1176jzf-s - ARM11 with Trustzone (allows you to run a virtual CPU with security features, so in kind of sandbox)
- Interrupt controller : PL092 and DMA controller : PL080. These are off-the-shelf IP blocks from ARM itself.
- Security IP: looks like there's a HW RNG, SHA1 and PKE (private key accelerator ??) block.
- Looks like there's a CLCD and LCD controller. In other words there are in fact two LCD controllers, one for RAM-less and one for RAM-based LCDs.
- NAND flash controller with seperate ECC block
- NOR flash controller
- JPEG accelerator
- H.264 accelerator - thing is called h264bpd -> h.264 base-line profile decoder ?
- TV output (but is not used by Apple...)
- MPVD... multi-purpose video decoder or something ?
- MBX.. yes it's there
- MPL = mobile pixel link, LM2511 is National IC, was spotted in several teardowns
- TSL2561.. why is this IC in there ? This is a light sensor. To do backlight dimmning of the LCD depending on ambient light ?
- micron2020 camera ... yes CMOS camera sensor from Micron
- EDRAM ???
- NVRAM, next to NAND flash ?
- There seems to be an unique ID

[Magallanes]

From the page of ARM:
http://www.arm.com/products/CPUs/ARM1176.html

Optional Vector Floating Point coprocessor (ARM1176JZF-S)
Powerful acceleration for embedded 3D-graphics


But i'm not sure about how powerful it is. For instance today the Axim X51V, Nokia N93i and Nokia N95 are indeed powerful but the rest (even with dedicated gpu) are just a bluff with a crappy performance (Even Sony Ericssons with a OMAP 2420).

[Brimstone]

So all the rumors of nVidia winning a contract with Apple for the iPOD and iphone were wrong?

[Lazy8s]

The acceleration for 3D from the vector floating point co-processor isn't 3D-specific acceleration; it's just an FPU for floating point support which could be used in operations like T&L. That processor on the ARM page is just the ARM11 CPU, not a CPU + GPU.

The Sony Ericssons with lower graphics processor performance don't use the OMAP2420; they use a chip with a smaller graphics core, the PNX4008, configured with an MBX Lite, no VGP Lite, no FPU, and an ARM9.

[Jawed]

So all the rumors of nVidia winning a contract with Apple for the iPOD and iphone were wrong?
Yep, poor Arun's wet dream.

Jawed

[Tim Murray]

Well, this thread got linked by EETimes... (http://eetimes.com/news/latest/showArticle.jhtml;jsessionid=Q3VYA4V0MCTPWQSNDLSCK HA?articleID=200900740)

[Arun]

Yep, poor Arun's wet dream.Hey, I'm openly more biased towards PowerVR than any other semiconductor company out there, from a technological perspective. It's not my fault if there aren't enough opportunities to show them some love! :)

Honestly, I hadn't even realized that Samsung had a MBX license before all this. I obviously hadn't done my homework! (but fwiw, it seems that EE Times also got this partially wrong, because Samsung is not a 'new partner'. So, who is this new mystery partner? Hmmm!)

[Brimstone]

So did nVidia win a design contract with Apple for anything?


I'm wondering if the speculation was right on a nVidia+Apple contract, but they just got the target device wrong?


Was a contract ever hinted at in Imagination Technologies confrence calls?

[Arun]

So did nVidia win a design contract with Apple for anything? There is a pretty good chance that the next-gen high-end iPod is based on the same application processor as the iPhone IMO, so no. I don't really see NVIDIA fitting in the iPod Nano at this point either... So unless Apple decides to change their lineup, I don't see how they could possibly fit in, and even then it wouldn't make much sense.

Their next-gen platform, which will tape-out probably in a few months at worst if it remains on schedule, will probably compete for the next-gen iPhone and iPod, but that's another thing completely, and in the end, 'compete' is exactly what they'll do - they don't have a magic backdoor here, so it's hard to judge their chances of success without knowing anything about that upcoming chip.

[vitaminc]

So did nVidia win a design contract with Apple for anything?


I'm wondering if the speculation was right on a nVidia+Apple contract, but they just got the target device wrong?


Was a contract ever hinted at in Imagination Technologies confrence calls?

Portal Player was in Gen 7 iPods and was displaced by Samsung in Gen 8. nVidia bought off Portal Player afterwards.

Apple's notebooks use nVidia's GPU though.

[Arun]

Portal Player was in Gen 7 iPods and was displaced by Samsung in Gen 8. nVidia bought off Portal Player afterwards.I never managed to find any confirmation that PP was displaced by Samsung in the 'iPod with Video', except by the fact that NVIDIA only had $10M of PP revenue in Q107, and this roughly corresponds to their non-Apple revenue iirc. So, any link to a reliable proof of that, and any info on exactly when it happened? :)

[vitaminc]

I never managed to find any confirmation that PP was displaced by Samsung in the 'iPod with Video', except by the fact that NVIDIA only had $10M of PP revenue in Q107, and this roughly corresponds to their non-Apple revenue iirc. So, any link to a reliable proof of that, and any info on exactly when it happened? :)

http://ce.seekingalpha.com/article/16904

I remember PLAY had more than $100M in annual revenues before it losts everything and sold itself to NVDA.

They lost the iPod Nano socket to Samsung, but still has the Video iPod music decoding socket.

Video iPod uses Alphamosaic's (acquired by Broadcom) display decode chip though. I believe there were some rumors saying nVidia designed out Broadcom on the next gen iPod, but Apple has not announced their plans for next gen iPod yet.

[INKster]

So did nVidia win a design contract with Apple for anything?


Besides the 8600M GT inside the new Macbook Pro's, there's always the Apple TV (Geforce 7300 GS) and the default graphics card inside the Mac Pro (7300 GT).

[hidefguy]

they use a smaller chip, the PNX4008, configured with an MBX Lite, no VGP Lite, no FPU, and an ARM9.

FYI, I believe the SE devices have a hardware FPU.

[Lazy8s]

Indication from Imagination Technologies that they were in the iPhone was inferred by considering the description and timetable for launch of the unnamed "other high profile handsets" in the following comment from their recent financial statements:
In the mobile phone market segment there are over 45 handsets that are based on our technologies. These include handsets from Nokia, Sony Ericsson, Motorola, NEC, Fujitsu, Mitsubishi, Panasonic, Sharp and Motorola. We continue to have a growing position in the Japanese mobile phone market through our very strong ranging across the latest DoCoMo phones. In addition to Sony Ericsson’s W850i, M600i, and P990i models and Nokia’s N93 and N93i models which are already shipping, we are now seeing, albeit a little later than forecast, a growing number of other high profile phones which are now shipping, or about to ship, in western markets. Amongst these are the acclaimed Nokia N95, Nokia E90, the Motorola MotoRIZR Z8 and MotoQ q9 and Sony Ericsson P1i. We also expect other high profile handsets to begin shipment starting from the second quarter of the current financial year. These new phones, targeted at western as well as global markets should significantly accelerate the volume ramp up for FY 07/08 whilst also demonstrating the real benefit of graphics for both the user interface and application content.
The possibilities for the configuration of the custom Samsung solution are numerous with options for the full or Lite versions of MBX, an accompanying VGP, the CPU variant, and the clock speeds.

Although today's announcement, that an "international electronics systems company" has licensed Imagination Technologies' "next generation graphics and video IP cores" under a "multi-use" agreement, combined with Apple's policy for secrecy about the identity of their parts' suppliers suggests that the announcement is about them, the "next generation" qualifier in the announcement would, in conventional Imgtec PR terms, refer to SGX. This would imply the possibility for SGX based iPhone, iPod, and Apple TV follow-ups, but it would leave unclear which MBX cores were licensed for the first iPhone. The ARM R-S (MBX Lite with no VGP Lite) agreement taken in January 2004 by Samsung covered just the S3C2460 at the time.

If Apple's design priority for the custom Samsung solution in this first iPhone was performance, a full MBX and also the VGP were probably included. If the CPU core really is at least a >500-MHz ARM11 and the GPU corresponds at a reasonable fraction of that, the hardware would overtake OMAP2420 systems finally as the most powerful in the portable sector.

[hidefguy]

Well, this thread got linked by EETimes... (http://eetimes.com/news/latest/showArticle.jhtml;jsessionid=Q3VYA4V0MCTPWQSNDLSCK HA?articleID=200900740)

A spokesman for Imagination said: "We can't say whether we are designed into the Apple iPhone."


Unbelievable. The device is out in the market place, people have hacked them apart yet neither Apple nor Imagination will confirm anything - this could only happen in the handset sector.

[vitaminc]

Unbelievable. The device is out in the market place, people have hacked them apart yet neither Apple nor Imagination will confirm anything - this could only happen in the handset sector.

this is exactly why i dont think nvidia will have much chance to succeed in cell phones. handset market is a very closed ended with in-house/proprietary hardware/softwares, compare to a standardized and commoditized hardware/software PC market.

[INKster]

this is exactly why i dont think nvidia will have much chance to succeed in cell phones. handset market is a very closed ended with in-house/proprietary hardware/softwares, compare to a standardized and commoditized hardware/software PC market.

Kind of like the PC discrete 3D graphics card scene, circa 1994... ;)

[Arun]

I remember PLAY had more than $100M in annual revenues before it losts everything and sold itself to NVDA.They had much more than that, $225M+ in 2005 and Q106 was also a very good quarter, with $72M+. But then in Q3, after the loss of the Nano, this happened:
The third quarter financial results we are reporting today are once again inline with our previous guidance, with revenue of $34.8 million. In the third quarter, more than 10% of this came from what we've termed other customers and we expect revenue from other customers to increase.
And this...
And before I turn the call back over to Gary, let me summarize our guidance for the fourth quarter. We expect revenue to be about the same as in the third quarter with a range of $31 million to $38 million.

So far so good, right? Then they got bought by NVIDIA and Q4 never got reported. But this was still said at NVIDIA's Q4 CC, keeping in mind that their Q4 ends on January 28th:
We closed the purchase of PortalPlayer on January 5th, but the revenue contribution from Portal was not significant, approximately $1 million.
This surely was a one-time thing because of timing issues, right? But then in the Q1 CC (and this was roughly in line with the Q4 guidance)...
PortalPlayer products accounted for $11 million in the quarter
[...]
We incurred a full quota of PortalPlayer expenses instead for the one month that was incurred in Q4. And this added about $10 million.
The expenses are what you'd expect, given that they were about $12.5M pre-acquisition and there might be some synergies at play. But the revenue? WTF?

I have yet to find a proper explanation to this. That amount of revenue would be just $6M from Apple if we expected non-Apple revenue to be flat, and a grand total of $0 from Apple if we expected non-Apple revenue to grow significantly. In either case, it doesn't make much sense to me. PortalPlayer's cash position remained roughly flat in Q4 too (because the net price was $160M, as expected) so there was no spike in this unreported quarter, as far as I can tell.

Maybe a very significant reduction in iPod Video production along with a reduction in ASPs... Still, weird.

[Lazy8s]

Because the S3C2460 apparently never made it to an end-user device, perhaps Samsung's January 2004 MBX Lite license was never used up and was still available for the iPhone chip. Maybe Samsung even intentionally passed up S3C2460 sales opportunities for it, though I doubt the whole scenario.

Imgtec would probably have to share the revenue from the chip with ARM in accordance with that old arrangement in this unlikely case, too.

[vitaminc]

Kind of like the PC discrete 3D graphics card scene, circa 1994... ;)

extremely different.

1994 PC 3D graphics add-on ->

Standadized hardware interface (ISA, followed by AGP and PCI-E) that allows plug/play.

Standardized OS (DOS, Windows).

Standardized form factor (AT, ATX)

Commoditized product. A PC bought from Packard Bell isn't much different from that of Compaq.

Open OEM/ODM and distribution channel. You have 345098364723986 Taiwanese guys trying to compete for the same Dell/HP order and cut throat prices. Commodity manufacturing for commodity product.


2007 cell phone graphics core ->

NON standardized interface. sometimes an add-in chip, sometimes integrated in application processor (samsung w/ imgtec), sometimes integrated in baseband (qualcomm w/ ati). And you cant plug/play.

NON standardized OS. In-house OS by different venders, Symbian 6, windows mobile.

NON standardized form factor. different sized phones have different PCB real estate budgets for chips.

Feature rich product. At a given price point, you have phones with different feature sets. e.g., W for walkman, N for smart phones, and iPhone for a cool browser.

Closed OEM/ODM and distribution channel. Can't just go to Taiwan for 1 stop shopping for PCB, distributor, OEM, etc.

[Snyder]

extremely different.

1994 PC 3D graphics add-on ->
Standardized OS (DOS, Windows).

OS maybe, but 3D API? ;)

[davefb]

is that arm chip definate?

because thats a jazelle one ( accelerated java)..

[Simon F]

What exactly is in the iPhone? Blend-Tec answer (http://www.youtube.com/watch?v=qg1ckCkm8YI).

Sigh....someone with more money than sense

[Arun]

Sigh....someone with more money than senseHey, don't complain - more royalties for you guys! ;)

[hidefguy]

What exactly is in the iPhone? Blend-Tec answer (http://www.youtube.com/watch?v=qg1ckCkm8YI).

Sigh....someone with more money than sense

What a strange video - I was surprised that it blended so quickly. I hope that dude didn't inhale the black smoke from the iPhone debris - I can't but believe that there must be some pretty toxic compounds given off.

[poopypoo]

Unbelievable. The device is out in the market place, people have hacked them apart yet neither Apple nor Imagination will confirm anything - this could only happen in the handset sector.

Heh. Apple's doing the smart thing - they don't want any brand recognition to get out besides their own. Sucks for ImgTech, tho -- but I figure word will get out enough to boost their stock anyway. ;)

[kLy]

Hi

Very much n00b to the embedded graphics chips so please excuse this if it's a stupid question.

So do we actually know for a fact which chip this is and how it can perform? The iPhone seems to obviously use the OpenGLES framework included, so I take it this chip is powering the fancy animations and whatever Quartz equivalent Apple is using on the phone?

According to Lazy8s, this could be quite a kickass 3D graphics processor? Could there be something in the Nintendo + iPhone rumours that were circulating a few weeks ago? :) At the very least we should get better graphics than the ngage which did things in software on its ARM processor right?

[vitaminc]

OS maybe, but 3D API? ;)

well, not 1994, but openGL or stuff of that sort was pretty popular at 96/97.

admittedly, i didn't get a 3D gfx card until 2001 until the beta of warcraft3. :p

[RussSchultz]

is that arm chip definate?

because thats a jazelle one ( accelerated java)..
All ARMs past 9 have the 'jazelle' stuff in them. Its mostly marketing speak as the jazelle piece doesn't seem to speed much up, and costs a bundle to license the JVM from somebody.

I'm not even sure that ARM pushes that it exists anymore.

[wco81]

So how much are these iPhone processors?

Especially compared to what's currently used in iPods?

There is of course speculation that the next iPods to be unveiled this fall or winter will be just the iPhone without the phone bits for current prices.

I don't know, an iPod with a 3.5-inch multitouch screen, maybe a 80 GB HDD, Wifi for $250 or $350?

With Cover Flow display and Internet features?

Do the chipsets and other components required for these features seem as likely for a $350 product compared to a $500 or $600 product?

[Lazy8s]

An SoC application processor with an ARM11 family core, an MBX family core, and some DSPs typically costs around $20.

[muratmat]

An SoC application processor with an ARM11 family core, an MBX family core, and some DSPs typically costs around $20.

Yeah, to be precise $20 each, for bunch of 1000 pieces.

[roninja]

iPod Touch = same Processor as the iPhone with MBX at the heart. My guess is yes.

[wco81]

On a related note, some people noted that Cover Flow rendering on the other iPods seemed to be a bit sluggish.

Rather than Cover Flow or in addition to it, what kind of processing power and video would it take to do the visualizations which iTunes and other software do on computers?

[RussSchultz]

On a related note, some people noted that Cover Flow rendering on the other iPods seemed to be a bit sluggish.

Rather than Cover Flow or in addition to it, what kind of processing power and video would it take to do the visualizations which iTunes and other software do on computers?

That kinda seems odd to me, since it appears (though we'll know more in the next few days when teardowns happen) that the NAND, iPod Classic, iPod Touch, and iPhone video capabilities are basically identical, and might the same SOC. My guess originally would have been the different SOCs, with the Touch and iPhone having beefier processors.

But, to answer your question, I'm not sure which visualizations you're talking about, but the typical thing like spectrum analysis, or pulsating blobs, or waveform display aren't terribly intense.

The coverflow stuff is probably pretty hard on the ARM11 processor without 3d acceleration assuming it supports the reflections of the album art I've seen in some demos like I think it does. I'm sure that its possible to have some hacks to make it easier, but they don't make 3d accelerators for nothing. ;)

[wco81]

The iTunes visualizations.

You have these pulsing graphics you can have it display while it's playing music.

I think MP3 software has had them since Win Amp.

EDIT: While the visualizations may not be graphically demanding, you'd obviously be keeping the backlight on to display them, much longer than browsing through Cover Flow.

So there would be little utility to using them on battery power.

Maybe it would still be nice if you take you iPod to a party, plug it into an AV system.

[RussSchultz]

Oh, absolutely.

The backlight is the largest power consumer in an PMP, generally.

[darkblu]

has anybody here noticed that the iphone and ipod touch use different main parts?

iphone (http://www.ifixit.com/Guide/iPhone/Logic-Board/105/7/Page-10/Logic-Board): Apple nomenclature '339S0030 ARM', corresponds to Samsung S5L8900 (http://www.semiconductor.com/resources/reports_database/view_device.asp?sinumber=18016)

ipod touch (http://www.ifixit.com/Guide/iPod/iPod-Touch/130): Apple nomenclature '339S0029 ARM', corresponds to what on Samsung's side?

[roninja]

no idea but both use MBX which is the most important aspect.

[darkblu]

true. has it been confirmed, btw, that it's mbx and not mbx lite?

[roninja]

MBX not officially confirmed

[Megadrive1988]

Late Feb 12, 2008, heh, this is the first I've read of the possibility of PowerVR MBX being in iPhone. I must first say that I really don't know a darn thing about iPhone, haven't really been interested but now I am!

Has it been confirmed that there's any variant of PowerVR in iPhone?

[Arun]

Yes, it uses a MBX or a MBX Lite, that's confirmed based on firmware analysis. In fact, it might be confirmed to be a full MBX, but I can't quite remember that right now...

[darkblu]

In fact, it might be confirmed to be a full MBX, but I can't quite remember that right now...

any hints to that confirmation?

[Arun]

I don't remember, otherwise I'd have said that already! ;) The chip definitely is a S5L8900 and a number of sites are claiming that's a full MBX, but I can't find any reliable source for that claim. Hmm.

[roninja]

Its not something official, however it is fairly common knowledge

[Lazy8s]

Nothing I've seen distinguishes which member of the MBX family the iPhone uses. If the license came from the original Samsung deal, it would be an MBX Lite, but the whole Apple arrangement could've changed the circumstances.

Whether a complementary VGP is also integrated is another unknown.

The only spec I think I know about its graphics processor is that the clock speed is currently at 103 MHz.

[darkblu]

i think that unless apple planned the iphone/touch to be a gaming devices, VGP presence in there is highly unlikely. even more so if the cpu already supposedly has fp SIMD extensions.

[archie4oz]

Nothing I've seen distinguishes which member of the MBX family the iPhone uses. If the license came from the original Samsung deal, it would be an MBX Lite, but the whole Apple arrangement could've changed the circumstances.

Whether a complementary VGP is also integrated is another unknown.

The only spec I think I know about its graphics processor is that the clock speed is currently at 103 MHz.

According to the SDK, it's an MBX Lite...

[wco81]

You got it already?

So what do you think 30% of the proceeds being Apple's cut? I guess iTunes is convenient and a distribution portal which reaches a lot of users. But seems pretty steep percentage.

Or a "nominal fee" for iPod Touch apps.?

You can't access the dock but apparently you can design games using the accelerometer.

[silent_guy]

You got it already?
I'm installing the SDK as we speak. :wink:

So what do you think 30% of the proceeds being Apple's cut? I guess iTunes is convenient and a distribution portal which reaches a lot of users. But seems pretty steep percentage.
I think it's very reasonable. Compare it to selling apps for, say, PalmOS. There you had to make a deal with one of the many app portal sites and the cut was more like 40%. You still had to manage notifying users about upgrades etc.

Really important to me (as a iPhone user) is that buying an app is effortless. My credit card info is already stored at Apple anyway, so it's really just a matter of impulse buying without the physical action of getting your card out of your pocket.

For developers, the barrier to entry is just $99. My guess is that this is going to be wildly successful and that we'll see more apps than any platform before it. The quality of those remains to be seen, but inevitably, there'll be stuff that will stand out.

Still 4 months to wait...

[archie4oz]

So what do you think 30% of the proceeds being Apple's cut? I guess iTunes is convenient and a distribution portal which reaches a lot of users. But seems pretty steep percentage.

Reasonable. I would've preferred 12-25% but it's not bad considering how that apple not only hosts, but also manages billing, any marketing, etc... Plus the level of store integration into the handset is pretty slick (You can obviously see that they were heavily inspired by Installer.app; giving it an iTunes mobile styled makeover).

You can't access the dock but apparently you can design games using the accelerometer.

As well as the camera, photo library, address book, Wi-Fi and EDGE. No word on accessing music library though (handy way of doing custom backrounds).

[wco81]

There might be some deals for placement on the App. store. The way they do it for the music and video content.

If developers rush in and there are tons of apps. available for it, there will probably be a premium for prominent placement.

With the "Made for iPod" certification, there's some QA by Apple as part of the vetting? Maybe something similar for apps.

Apple may have to slow down development of bundled apps., to give breathing room to developers (MacWrite and MacPaint). Maybe this means no iChat or not as much urgency, if AIM and other clients come out. Then again, who pays for IM software.

Does the SDK indicate how much RAM is available and have any guidelines/limitations on storage?

[tangey]

According to the SDK, it's an MBX Lite...

Excellent news !!

[NocturnDragon]

Excellent news !!

Excellent news?

Being a MBX it's not news,
and being a MBX Lite while being news it's not excellent, a MBX non Lite would have been excellent.

[tangey]

Show me where apple have previously confirmed MBX of any sort in the iphone. There has been supposition and assumption, but this is the first official recognition, it is therefore, regardless of your assessment, NEWS for me.

It is also EXCELLENT news if you are a follower of IMG IP, in that it finally confirms that the iphone contains IMG IP as opposed to someone elses IP, it is therefore, regardless of your assessment, EXCELLENT NEWS for me.

[roninja]

and hopefully an indicator for more Excellent News in the future....

[wco81]

How do mobile game sales stack up against mobile productivity apps. sales?

You only buy a new email client once or twice, maybe something like Opera once.

But you could buy games over and over again, it seems.

So maybe in future models, they'll look at putting in more dedicated gaming silicon?

[Entropy]

You got it already?

So what do you think 30% of the proceeds being Apple's cut? I guess iTunes is convenient and a distribution portal which reaches a lot of users. But seems pretty steep percentage.

Uhm - 30% for publishing/promo and distribution? Very reasonable.
Ask any band how large a cut they get from sales of their products. :)

This is a particularly good deal for software developers that are not tied to a publisher. They get 70% of the end-user price, and retain all rights to their product. Add to that the possibility to get funding. If I were a one-man-band, or a small game developer house this would be very attractive proposition indeed.

[Diamond.G]

According to the SDK, it's an MBX Lite...

Where in the SDK do you see that?

[archie4oz]

In the iPhone OS Programming Guide under "Drawing with OpenGL ES." There's also several links back to ImgTec in there...

[wco81]

How capable is the MBX or MBX Lite?

In a SJ Mercury article, they said games could be more powerful than those on the DS or PSP.

That has to be a misunderstanding by the writer, who was quoting Carmack saying some nice things about the iPhone SDK.

Does the MBX or MBX Lite compare to the Broadband Engine in the PSP?

What other devices are using the MBX and MBX Lite chips

It seems a lot of enthusiasm from games developers to the iPhone SDK is more about what they perceive as the business opportunity, not because the iPhone hardware is that much more capable than any other portable device out there.

About the only thing that stands out is that there are no size restrictions on iPhone applications as there are with other mobile platforms.

Not being able to background processes on iPhone apps. shouldn't matter too much with games.

[Arun]

How capable is the MBX or MBX Lite?

In a SJ Mercury article, they said games could be more powerful than those on the DS or PSP.MBX Lite being faster than the PSP's GPU seems like a massive amount of overoptimism to me. DS on the other hand, wouldn't surprise me at all.

It seems a lot of enthusiasm from games developers to the iPhone SDK is more about what they perceive as the business opportunity, not because the iPhone hardware is that much more capable than any other portable device out there.Well, the ARM11 core is certainly no weakling; I'm not aware of any shipping mobile phone wiht noticeably more performance than it.

[Lazy8s]

http://www.pocketpcfaq.com/videos/Intel-3D-Graphics-Demo.wmv

http://img16.imageshack.us/img16/7813/mbxlite7ht.jpg (http://imageshack.us)

Twilight is a graphics demo running on the MBX Lite in the Dell Axim X50v. It uses OpenGL ES and was developed by Futuremark.

PowerVR's tile based, deferred shading/texturing graphics architecture is likely a lot more effective with bandwidth and fillrate than either the PSP or DS's design, and its capabilities of unconditional color accuracy for alpha blends, lower penalty AA, DOT3 per-pixel lighting, and up to anisotropic texture filtering give it a more advanced feature set. Being probably multiple times as small in size as the PSP's GPU, though, and probably having lower power consumption likely leaves the iPhone's MBX Lite at around one-third to one-quarter of the PSP's graphics performance.

MBX family processors released ahead by several months of either the DS or PSP back in 2004. That Axim X50v launched back then, employing an MBX Lite that was part of Intel's (now transferred to Marvell) 2700G multimedia dedicated co-processor chip. The 2700G might've been clocked lower than the iPhone's graphics core.

Wikipedia's entry for PowerVR lists a lot of other devices equipped with an MBX processor.
http://en.wikipedia.org/wiki/Powervr

[Diamond.G]

1/3 to 1/4 seems pretty low. Is that DC levels? But with better IMG quality?

I wonder how long it takes Futuremark to come out with a benchmark for the iPhone.

[MoHonRi]

Remember the Dreamcast?

Considering it used a Series 2 chip at 100 Mhz and it rivaled (in my opinion) the PS2 solution, I think there is still quite a bit of capability in the iPhone/iPod touch graphics hardware.


We'll see exactly what developers can come up with, but I've got high hopes. My concern isn't about the graphics it's more about the control options that are possible. That might be the limiting factor in game software.

[wco81]

Producer of Monkeyball was quoted as saying they could get console-quality graphics.

An EA guy said the accelerometer and the big touch screen gave them options, like on-screen buttons.

Would be better if they could use Bluetooth to support control devices as an option.

Would be better still if for the next rev of the iPhone, Apple threw in a couple of shoulder buttons.

Or maybe some kind of feedback to use with virtual buttons.

Could future designs be driven by gaming requirements or more likely, flashy UI effects and video media support?

[Entropy]

We'll see exactly what developers can come up with, but I've got high hopes. My concern isn't about the graphics it's more about the control options that are possible. That might be the limiting factor in game software.

The touch screen and the accelerometer opens possibilities. It will be very different from a PSP, but that may well be for the better.

The sheer number of downloads of the SDK is staggering. 100000 in four days. Of course, only a small fraction will ever develop anything, but it still indicates an amazing interest!

[MoHonRi]

Yep, I totally agree Entropy.

I personally want a 'real' PDF eBook reader. My thoughts were you could use the standard music navigation ... pushing play would start an auto scroll, forward/reverse would navigate by page, the chapter/track navigation would go navigate by chapters. Holding play and pressing forward or reverse would adjust scroll speed... and of course a TOC where you could go to any page/chapter in the book...

The only 'proble' would be getting the PDF files onto the iPod/iPhone...

(of course that application has nothing to do with the graphics chip... so I'll just be quiet now ;) )

[Lazy8s]

The performance of iPhone's MBX Lite should be well short of Dreamcast's, too. Similar to Dreamcast, though, it displays with superior image qualities compared to PSP.

[Diamond.G]

@Lazy, are you inferring N64 level with good IQ? Or more like somewhere between N64 and DC. I was always under the impression that the DS was a mini N64, is that accurate as well?

@MoHonRi, the iPhone/Touch are powerful, but from what Lazy is saying, not that powerful.

[darkblu]

http://www.pocketpcfaq.com/videos/Intel-3D-Graphics-Demo.wmv

<image>

Twilight is a graphics demo running on the MBX Lite in the Dell Axim X50v. It uses OpenGL ES and was developed by Futuremark.
lazy, do you know if the x50v has a VGP-class part, or TnL is all sw?

[Simon F]

lazy, do you know if the x50v has a VGP-class part, or TnL is all sw?
I think it may be the Intel part which has no VGP.

[Xmas]

Yes, the 2700G doesn't have VGP.

[darkblu]

thanks for the input, guys.

[Ailuros]

The performance of iPhone's MBX Lite should be well short of Dreamcast's, too. Similar to Dreamcast, though, it displays with superior image qualities compared to PSP.

What's the iPhone's MBXLite clocked at? Even if they're operating at the same frequency, the comparison would be purely on a GPU vs. GPU basis and I'm not so sure that the MBX Lite would lose after all, since it's 2 generations apart from the DC chip (if memory serves well) and there have been quite a few advancements even on "simple" tiling algorithms since then. Fetch the SoC specs of that iPhone and compare to that: http://www.firingsquad.com/hardware/dreamcasthw/page2.asp

[MoHonRi]

Nothing I've seen distinguishes which member of the MBX family the iPhone uses. If the license came from the original Samsung deal, it would be an MBX Lite, but the whole Apple arrangement could've changed the circumstances.

Whether a complementary VGP is also integrated is another unknown.

The only spec I think I know about its graphics processor is that the clock speed is currently at 103 MHz.


Edit -- nm, it appears that the info around the net says that the bus speed got bumped up to 103 Mhz. Which is not necessarily the clock speed of the MBX Lite.

The only info I got on the MBX lite clock speed while googleing was about an SDK a long time ago 2004 that said the max speed for it was ~50 Mhz and at that speed and with the SDK release it could do ~500,000 Polys a second. Of course that was in 2004.....


http://www.iphoneatlas.com/2007/12/03/112-update-boosts-iphones-clock-speed/

[Lazy8s]

The polygon performance of the MBX Lite should approach around one million per second, so it's not up to Dreamcast levels but well beyond N64 and DS.

http://img512.imageshack.us/img512/3098/earth8lz.jpg (http://imageshack.us)
(a scaling earth benchmark running on the Axim and featured at Loewe's Deferred Power -- http://www.mitrax.de/ )

[Ailuros]

I've seen Loewe's demo on an Axim in realtime when he visited me ;) The question still remains what the iPhone MBX Lite is clocked at. I don't recall the x50 MBX Lite frequency but if memory serves well it was either around 75MHz or below. Manufacturing processes have advanced since then and frequencies are higher nowadays; I'm not saying it is, I'm merely asking if you have any info on the final frequency of that iPhone thingy.

If you still should have the older MBX whitepapers in your hands, compare it to the newest one on their homesite.

POWERVR MBX family currently comprises two
variants scalable for a range of area and performance
requirements enabling it to accommodate the needs
for many target markets. Performance scales with
clock speeds up to 233MHz and beyond.

Triangles/sec* 3.4m – 7.4m
Pixels/sec* 270m – 600m
* Realistic SoC performance at 200MHz. Peak performance
significantly higher dependant on content and operating
conditions.

[Lazy8s]

Interesting; I hadn't noticed that latest performance scale being quoted for the MBX family.

While I don't know for certain what the clock speed of the iPhone's graphics core is, I've been suspecting 103 MHz, that of the system bus.

[Ailuros]

Interesting; I hadn't noticed that latest performance scale being quoted for the MBX family.

While I don't know for certain what the clock speed of the iPhone's graphics core is, I've been suspecting 103 MHz, that of the system bus.

Ask Loewe he most certainly knows what the MBXLite in his Axim is clocked at; if it should be anywhere in the 50MHz region and the iPhone contains something in the =/>100MHz region there's quite a difference after all. How that measures against a Dreamcast I'd still have no idea, but I wouldn't be surprised if it would at least with the right frequency come damn close to it.

If we'd be talking about a MBX+VGP it would be easy to say that it would beat a DC hands down.

[Simon F]

If we'd be talking about a MBX+VGP it would be easy to say that it would beat a DC hands down.
IIRC, an MBX should, in general, be quite a bit faster than a CLX at the same clock rate. The addition of the VGP then offloads a lot of work from the host CPU which makes the whole system faster.

[darkblu]

IIRC, an MBX should, in general, be quite a bit faster than a CLX at the same clock rate. The addition of the VGP then offloads a lot of work from the host CPU which makes the whole system faster.

interesting.. didn't the CLX do one pixel per clock?

[Simon F]

interesting.. didn't the CLX do one pixel per clock?
The texturing and shading processor did one pixel per clock as does MBX - the latter is more efficient when AA is being used.

The HSR front ends of both chips run at higher pixel/clock rates but, IIRC, MBX has some additional efficiency improvements.

[Lazy8s]

Doesn't the CLX2 have a higher effective peak opaque fill -- maybe 32 Z comaparators compared to 8 or less -- than MBX?

[Simon F]

Doesn't the CLX2 have a higher effective peak opaque fill -- maybe 32 Z comaparators compared to 8 or less -- than MBX?
Yes.... but MBX adds one important facility which, in practice, makes up for this.... but I doubt I should say any more.

[Ailuros]

Doesn't the CLX2 have a higher effective peak opaque fill -- maybe 32 Z comaparators compared to 8 or less -- than MBX?

Again consider that the CLX2 and MBX are two whole technology generations apart. Of how many pixels/clock is the CLX2 capable of anyway?

If memory serves well MBX didn't inherit maybe one aspect of the Series4 generation, which probably makes it's Multisampling on one axis capability rather a moot point.

[Iron Tiger]

Clock for clock, the iPhone's MBX Lite should outperform the Axim's since the iPhone's screen is at a lower resolution. Most every accelerated demo or game I ran on my X50v was at 640x480. Also consider that the Dreamcast ran at that res.

Process shrinkage may not have led to an increase in clocks as the iPhone has MUCH better battery life and stays cool in operation (only heating up when wireless components are active).