[tangey]

Originally Posted by ToTTenTranz

After going through all the trouble of "convincing" the major smartphone game companies to optimize their games to the Adreno 205 in the first Xperia Play?

I doubt that.

I don't see that being a major issue, as most of the the big companies writing for the "play" will be writting for other platforms too, which are either totally PowerVr or include PowerVr in the platform, thus the games will have already been optimised for PowerVr.

[Exophase]

Originally Posted by ToTTenTranz

After going through all the trouble of "convincing" the major smartphone game companies to optimize their games to the Adreno 205 in the first Xperia Play?

I doubt that.

Performance is obviously not going to be a concern, so I'll presume you're referring to portability concerns.

You can see some of the extensions here:

http://stackoverflow.com/questions/3...ndroid-devices

Most of the extensions are for debugging and/or profiling. The only real sticking points I see are the AMD compressed texture formats and GL_QCOM_tiled_rendering. GL_QCOM_writeonly_rendering is probably safe to ignore.

The change in texture compression will probably require recompressing the textures, which is not really a big deal so long as a similar size can be achieved without degradation in quality. GL_QCOM_tiled_rendering can probably be implemented with scissoring, although I doubt games even rely on this much and it can possibly just be ignored too. Either way it wouldn't necessarily be much of a problem to add to the driver's transparently.

[tangey]

Presentation from todays ST investors meeting:-

http://phx.corporate-ir.net/External...xUeXBlPTI=&t=1 (this is just the ST-ericsson relevant slides)

Not much new in there. but a few points:-

NovaThor L9600 chipset based on A9600 not available until 2012-2013. (sampling this year).

A9540 is quoted as being x3 U8500 in graphics. In the original announcement it was quoted as being "up to x4".
http://www.stericsson.com/press_releases/NovaThor.jsp

I wonder might this be another implementation of Mali400MP3 ?

U8500 has design wins with 5 leading smartphone manufacturers, ramping up H2 '11.


The full ST investors presentation is also available, which might also be interesting to some, and suggests that Mali is also designed into some of their high-end controllers.
http://phx.corporate-ir.net/External...xUeXBlPTM=&t=1

[stiftl]

1/2 OT: What are the differences between the U8500 and the Samsung Exynos?
For me they look nearly the same on the paper.

[Exophase]

Originally Posted by stiftl

1/2 OT: What are the differences between the U8500 and the Samsung Exynos?
For me they look nearly the same on the paper.

U8500 only has a single-core Mali-400, Exynos is Mali-400MP4.

[stiftl]

Originally Posted by Exophase

U8500 only has a single-core Mali-400, Exynos is Mali-400MP4.

Thx!

[Florin]

ST-Ericsson wins design at Nokia, or did they?

Curious chain of events.

[Ike Turner]

Originally Posted by Florin

ST-Ericsson wins design at Nokia, or did they?

Or maybe not. There's no design win yet, only talks. Looks like a PR damage control for the shareholders and analysts. At the end of the day it's Microsoft who decides and not Nokia anyway.

[Arun]

I talked with ST-E at MWC11, and my understanding is it's definitely a lot more than talk. However, ST-E was obviously taken by surprise like everyone else, and they had zero driver development on Windows Phone 7 (they do have experience with WinCE on older chips though). So my guess is that they've got 12 "design ins" but those will only become "design wins" if they execute on the driver front (and if Nokia does decide to go ahead with those specific models for other reasons unrelated to ST-E). Two big questions are GPU support (because right now Windows Phone 7 requires DXTC which Mali-400 doesn't have) and dual-core (Windows Phone 7 is still based on the WinCE6 kernel which doesn't support multicore). Maybe the start of fragmentation sadly...

As for Microsoft deciding silicon partners rather than Nokia, don't be silly. Nokia executives should be fired immediately (even more than they already deserve to be) if they didn't insist on a contract that gave them that kind of influence.

[Erinyes]

But given that they standardized on Qualcomm for the first gen devices, dosent it make more sense for Microsoft to go for Qualcomm dual cores for the next gen phones?

[Lazy8s]

At some point, Microsoft will need to certify other SoC suppliers so that their device partners have a real market for choice in design.

[Lazy8s]

The texel fill of this thing is still hard for me to get my head around. Obviously, the clock speeds are very high, and I assume this is using a low power graphics core for display compositing like the OMAP4470 to save the Rogue GPU from powering up much of the time (implying the possibility for a very very high clock ceiling for the GPU), but still... over 5G tex/sec base!?

I'm guessing the family of Rogue cores will include just one variant, which will serve as a building block for MP configurations, per line of feature support -- a line for Halti and DirectX 10+ and a line for DirectX 11+. But even the base cores must have quite a few TMUs, which I guess targeting 28nm and below affords.

[Ailuros]

These numbers imply either 8 TMUs @ ~667MHz or 12 TMUs @ ~450MHz, and given the 2.5GHz frequency on the CPU and some of the power saving tricks I know about, I'd much rather bet on the former. It also implies 40 flops/TMU, which may seem strange but could be easily explained in at least three different ways: 1) 5-way FMAC with 4 shader cores per TMU, 2) 4-way FMAC with 4 shader cores per TMU + interpolation (on or off shader core?), 3) 4-way FMAC with 5 shader cores per TMU. All of them (and more) are perfectly plausible, so let's leave it at that.

Compared to the SGX544s in OMAP5, that's more than twice the GFlops per TMU, and also significantly improved API support (OpenGL ES Halti and OpenCL Full Profile with on-chip local memory from what I've heard on the grapevines).

http://www.beyond3d.com/content/articles/112/

Either case scenario of the 2 Arun proposes implies 4 TMUs/core. He's suggesting either MP2@667MHz or MP3@450MHz. If each core truly has 4 TMUs it's definitely high time we see some AF in embedded devices. On chip local memory is far more tickling as a shred of information though than anything else.

[ToTTenTranz]

Since the Mali400 doesn't support DXTC, I wonder if that doesn't dictate the U8500 can only be used in Symbian models?
They've been claiming "Gigahertz processors" in future symbian devices for a while, even after the February 11th Elopcalipse.

[Exophase]

Originally Posted by ToTTenTranz

Since the Mali400 doesn't support DXTC, I wonder if that doesn't dictate the U8500 can only be used in Symbian models?
They've been claiming "Gigahertz processors" in future symbian devices for a while, even after the February 11th Elopcalipse.

I'm sure lack of DXTC in hardware won't lock out phones from WP7 if Nokia really wants to deploy it this way. It'll just mean that the textures are decompressed in the drivers, same with paletted textures on a lot of GPUs today.

[mczak]

Originally Posted by Exophase

I'm sure lack of DXTC in hardware won't lock out phones from WP7 if Nokia really wants to deploy it this way. It'll just mean that the textures are decompressed in the drivers, same with paletted textures on a lot of GPUs today.

Do we know it really doesn't support it in hardware? Wouldn't be the first gpu which supports it but it's not enabled in OpenGL due to licensing costs...
Uncompressing in the driver sucks though, eats up ram and these chips are starved enough for bandwidth that just increasing texture bandwidth usage by a factor of 4/8 isn't really what you want to do (could recompress to etc of course but that's probably not what you want to do neither).

[Exophase]

Originally Posted by mczak

Do we know it really doesn't support it in hardware? Wouldn't be the first gpu which supports it but it's not enabled in OpenGL due to licensing costs...
Uncompressing in the driver sucks though, eats up ram and these chips are starved enough for bandwidth that just increasing texture bandwidth usage by a factor of 4/8 isn't really what you want to do (could recompress to etc of course but that's probably not what you want to do neither).

We don't know that it doesn't, but that'd be pretty strange for IP. Wouldn't ARM just include the cost of DXTC licensing as an option for its own licensing?

Uncompressing obviously wouldn't have good results but it's better than not supporting an OS outright.. transcoding to ETC could possibly be made optional. I have no idea what kind of quality loss you get from that.

[Heinrich4]

About A9600 with A15 and PowerVr 6 rogue ...DXTC is really needed if the PowerVR possesses pvr-tc?

About Mali-400 i found this:

http://forum.xda-developers.com/show....php?t=1068567

[Ailuros]

Originally Posted by Heinrich4

About A9600 with A15 and PowerVr 6 rogue ...DXTC is really needed if the PowerVR possesses pvr-tc?

Series5 supports PVRTC, ETC and DXTC for compatibility reasons.

About Mali-400 i found this:

http://forum.xda-developers.com/show....php?t=1068567

That's weird since a DXT1 extension is mentioned here: http://www.glbenchmark.com/phonedeta...2&testgroup=gl

...but then again it's supposed to have as GL Vendor ARM, NVIDIA and PowerVR so it's obviously quite a colourful platform having a bit of everything

[tangey]

I've heard Arun suggest/worry regarding ST-E ability to deliver their A9540 & A9600 according to their roadmap, it appears that ST-E themselves are concerned about this, as can be seen in this article about their new design centre in CA.

http://www.eetimes.com/electronics-n...Silicon-Valley

"ST Ericsson has taped out a dual-core ARM Cortex A-15 set to ship in 2012. It will outgun rivals including the Omap 5 from Texas Instruments because the STE chip uses the Imagination Rogue graphics core, said Gilles Delfassy, chief executive of ST Ericsson and former head of TI's wireless business unit. Due to use of a new vector-processing architecture, the chip should also have smaller size, cost and power consumption than its rivals, he added"

"We have a road map which is very aggressive, but the key question is will we deliver on it on time," Delfassy said.

To that end, Delfassy said he has replaced some engineers in ST Ericsson and brought "on two executives with strength in product execution. One is a senior vice president from the former Infineon wireless group who worked closely with Apple; another is a former Sony Ericsson executive who has supervised groups of more than a thousand engineers."

Still no info as to what graphics are in the A9540.

[Lazy8s]

Can't wait for some OpenCL comparisons of the A15s versus the Rogues.

Not in a competitive sense; wouldn't be fair of course. Just in a relative sense.

[ToTTenTranz]

A9600 to be in future Nokia Windows Phone devices?
http://www.stericsson.com/press_rele...sson_nokia.jsp

November 02, 2011

NovaThor™ platform to enable Nokia to extend Windows Phone devices to new price points and geographies

Geneva, Switzerland, November 2, 2011 - Nokia has selected ST-Ericsson as a supplier for future devices it plans to introduce based on the Windows Phone mobile platform.

“We are pleased to have been selected by Nokia as a key partner for Windows smartphones, in line with our goal to be present in all segments and major operating systems,” said Gilles Delfassy, president and CEO of ST-Ericsson. “Our NovaThor platforms continue to gain traction as they enable customers to bring great smartphones to the market.”

Earlier NovaThor SoCs with Mali 400 in a Windows device seems unlikely since they don't have any kind of DirectX compliance, more importantly DXTC support.

On the other hand.. it does say "extend Windows Phone devices to new price points", which kind of implies it'll allow for cheaper devices using a lower priced SoC (U5500?).


Unless it's all more than a year away and these new low-cost Nokia Windows devices will actually have an unnanounced mid-end SoC with a low-end Rogue GPU.

[tangey]

Originally Posted by ToTTenTranz

A9600 to be in future Nokia Windows Phone devices?
http://www.stericsson.com/press_rele...sson_nokia.jsp




Earlier NovaThor SoCs with Mali 400 in a Windows device seems unlikely since they don't have any kind of DirectX compliance, more importantly DXTC support.

Does window phone have DirectX as a requirement ?

Originally Posted by ToTTenTranz

Unless it's all more than a year away and these new low-cost Nokia Windows devices will actually have an unnanounced mid-end SoC with a low-end Rogue GPU.

Maybe, Maybe Not, ST-ericsson has specifically NOT divulged the graphics in the A9540 chip. All they say is that its x4 current gen. Given that current gen is single core mali, the logical conclusion is that its Mali400MP4, but if so straightforward, why not just say it.

I also noted an Anandtech table in a recent review of the snapdragon S4 cites that the A9540 has PowerVR series 5, which if true is interesting as STM/ST-Ericsson does not currently have a series 5 licence (or if they do, it has never been made public).

http://www.anandtech.com/show/4940/q...t-architecture

I emailed anand and asked for a source for the data, didn't get a reply.

[Arun]

Originally Posted by tangey

Does window phone have DirectX as a requirement ?

Not desktop DirectX, but yes, and it does require DXTC. You could obviously get away with decompressing the textures as ChainFire3D does on Android to allow Tegra games to play on other platforms, but that's obviously a suboptimal solution.

Maybe, Maybe Not, ST-ericsson has specifically NOT divulged the graphics in the A9540 chip. All they say is that its x4 current gen. Given that current gen is single core mali, the logical conclusion is that its Mali400MP4, but if so straightforward, why not just say it.

I specifically asked Louis Tannyeres about that at MWC11 and he responded by saying they have not made any announcements on this subject and quickly switched to another question. This is from the same person who openly told me about the presence of heterogeneous CPUs in the A9600 and confirmed they could scale down the Rogue in A9600 by at least 4x for lower-end derivatives (implying it's at least a quad-core). So he was VERY open about a lot of things but not open at all about such a seemingly trivial detail.

So I think it's pretty clear it's not a Mali-400. It might either be a custom IP from ARM that adds DXTC to be compliant with WP7 but that's quite a stretch and it seems more likely that they did license Series 5XT for A9540. Or hey, it might be from Vivante - now that would be a funny surprise! I wouldn't hold my breath though since they said they were going for a 2 supplier strategy on GPUs, not 3 suppliers.

If it is a Series 5XT then it's probably a SGX544 and the A9540 is starting to look at *lot* like OMAP4470 - only it's on 32nm@GF rather than 40nm@UMC. Not a bad position for ST-E to be in and it's understandable that Nokia would pick such a product as a second source.

I'm not sure how they expect that specific chip to extend WP7 to "new price points and geographies" and that's even less true with A9600. I don't see how it would be cheaper (in terms of full system BOM) than the MSM8255 they're using today or the MSM8930 on Qualcomm's roadmap in a similar timeframe (although it's faster than both of them). It's certainly very competitive though and Nokia needs a second source to get good pricing from Qualcomm so it's a good choice. And it's some badly needed good news for ST-Ericsson who are currently losing $200M per quarter. You read that right - nearly a billion dollars in negative cash flow per year!

[I.S.T.]

How long have they been losing that much money?