Presentation of a 6GHz second gen Cell Processor at ISSCC

That was january 2005.

Today Broadcom offers HDTV-on-a-chip for $30. That includes almost all you need to receive, decode and display a HDTV stream (including full HD-DVD/BluRay support).

So while Toshiba might want to be leading edge technologically they also want to turn a profit, and here cutting cost on the BOM is essential.

Cheers

And Cell costs how much? $40? plus SCT chip $25? and together they will do things like decode/scale several streams and display them as thumbs on the screen, instant replay, provide on screen and bluetooth control programability, ethernet connectivity etc. (plus the possibility of things like web browser, hard drive connectivity for Tivo functionality etc). When you pay $1500 for a high end HDTV, I can see how the extra $35 might be a dealbreaker.
 
when you say "That includes almost all" is that real HD though as in UK BBC mbaff Mpeg4-AVC/H.264 or if you must the VC-1 (Divx with bells on) or just old hat US Mpeg2 HD? or is that part covered in another sister chip.

I'm guessing it's just MPEG2 HD. The blurb on EET didn't specify. Though I'm sure Broadcom will have a SoC ready with h.264/VC-1 if demand ever shows up for that.

My point was as much that the SoC contained tuner, decoder, scaler, audio processing, driver etc. all in one cheap chip.

You can do decoding and scaling on CELL but you still need auxilliary chips for the tuner, to drive the display panel itself etc, not to mention the boutique RAM. So total system cost will be higher than a Broadcom based one.

Cheers
 
I'm guessing it's just MPEG2 HD. The blurb on EET didn't specify. Though I'm sure Broadcom will have a SoC ready with h.264/VC-1 if demand ever shows up for that.

My point was as much that the SoC contained tuner, decoder, scaler, audio processing, driver etc. all in one cheap chip.

You can do decoding and scaling on CELL but you still need auxilliary chips for the tuner, to drive the display panel itself etc, not to mention the boutique RAM. So total system cost will be higher than a Broadcom based one.

Cheers

Toshiba's equivalent is the SCC chip. Cell + SCC > Broadcom. I am not sure how much tuner circuitry would be integrated into the Broadcom vs the SCC though, and Cell will require some minimal external RAM + ROM or Flash memory at least (if this is not incorporated on the SCC chip). The SPEs use their local stores so the RAM requirement is minimal, although Toshiba's high end features (which Broadcom can't emulate) will require a lot of external RAM.
http://news.zdnet.com/2100-9584_22-5833453.html
http://www.hotchips.org/archives/hc17/2_Mon/HC17.S1/HC17.S1T3.pdf

Broadcom is cheaper if you want a cut price system, but Cell + SCC is far more capable/versatile, and on HDTVs costing $1000+ a few bucks cut in price isn't going to be noticed. What is going to be noticed is Tivo PVR capability + Internet browsing for say $100 more (add HDD + RAM), and HD-DVD/BD player/recorder for another $150 (add bare optical drive).
 
If that's true, why did they say they'd have Cell TVs out in 2006? Were they expecting 65nm to be out earlier? What's bothering isn't just the lack of Cell sets, but any real showcased prototypes. At least other speculative technologies (SED TVs) get shown every year! Wouldn't they have a Cell TV prototypr around by now showing wonderful Cellness and just waiting for a 65nm shrink to go into mass production? Why not sell that at stupid money as a premium range device?

Due to its cost, Cell should only be suitable for high end consumer products (or industrial products) with premium features.

I believe most of the slow showing are due to software issues... since they now need to implement almost everything in software, rather than ASICs. For these advanced features (e.g., Toshiba engineer's idea about video conferencing), they may need some sort of embedded OS to run on Cell.

If we are seeing Linux and GameOS released recently on Cell late last year, I think other RTOSes will take similar or longer timeframe. So it would be hard to show any functioning demo at this point. They probably didn't expect it to take so long and so much resources to build the layers beyond simple demos. But these are just my speculations.

I definitely look forward to Phil's claim that we will see video and audio communication features in PS3 come March 2007.

Nevertheless, I agree that it will take strong management commitment to roll out any Cell consumer products though. I also think that the 6GHz Cell is just something for another market (The scientific computing people), so I don't see a big problem for rolling it out now. The software and needs are more ready in that segment.
 
Back
Top