PowerVR Series5 still alive and it's "high end"

R

rake

Newcomer
From the financial statements released two days ago:

* PC/Console - We are currently developing our next generation advanced graphics technologies, which are a key vehicle for taking our fundamental 3D technology forward and is also a platform that allows us to target PC, console and arcade market opportunities.
Click to expand...

Further clue is in their results presentation slideshow on this slide http://www.imgtec.com/investor/Prelim03/Prelim03.asp?Slide=20 which states they are aiming for "high end".

Also quite a few vacancies advertised on the careers section of their site in the PowerVR division. Would be nice to see a part this year, especially if it's high end.
 
I'd love to see PowerVR5 smash the NV35 as PowerVR2 smashed TNT1.

too bad there were not enough PowerVR2 chips for Dreamcast AND PC cards. the 1 year+ delay (or 18 mo? i forget) of PowerVR2 for PC was the last time PowerVR was aimed at the highend, and seriously damaged PowerVR brand. i never even looked a PowerVR3 Kryo. And was deeply saddened by PowerVR4 being scrapped. I long for the return of the PowerVR glory days :)

may PowerVR5 be the triumphant return of the Videologic folks
(long since under different name of which i forget, oh yeah Imagination)
 
megadrive0088 said:
I'd love to see PowerVR5 smash the NV35 as PowerVR2 smashed TNT1.

too bad there were not enough PowerVR2 chips for Dreamcast AND PC cards. the 1 year+ delay (or 18 mo? i forget) of PowerVR2 for PC was the last time PowerVR was aimed at the highend, and seriously damaged PowerVR brand. i never even looked a PowerVR3 Kryo. And was deeply saddened by PowerVR4 being scrapped. I long for the return of the PowerVR glory days :)

may PowerVR5 be the triumphant return of the Videologic folks
(long since under different name of which i forget, oh yeah Imagination)
Click to expand...

i don't think so. Because of the speed the big guys keep developing new products, the timeframe for the small guys to earn money with a certain product line is pretty short.
Because of one good product the market doesn't change much.
ATI had the clearly superiour product line over 3 quaters and could not manage to win substantial market share.
Do you think a small company like powervr has the ability to do that? i doubt that very much. As i said the timeframe is pretty short because the big guys will speed up as much as they can.
The business model powervr has is also a big disadvantage because they need big partners to manufacture the product. We saw what happened back in those Kyro II days.
 
It seems to me that this is a really good time for PoverVR to make a comeback. This because the chip factories seems to have problems with their high end processes. And both Nvidia and Ati is depending on this (Nvidia to a larger extent i guess) while PowerVr is not since they, at least in the past, have been using less transistors for similar funcationality/speed.
 
Richthofen said:
The business model powervr has is also a big disadvantage because they need big partners to manufacture the product. We saw what happened back in those Kyro II days.
Click to expand...

All indications we've had so far suggest that they are doing it all themselves this time, nt least because we haven't heard anything about any partners.
 
What really makes me wonder is how they finance their design work. To make a high end entry into the pc space late this year I'd estimate, that you'd need at least a .15 design with ~100 Mio transistor. Considering 160 mio $ was often mentioned for the design of GF4 and considering that most work was reused from GF3 than, wouldn't bringing a high end graphics chip to the market require somewhere near 500 mio $ with nowadays design tool and masking costs, without considering distribution & manufacturing costs. Also if they really intend to do it alone, would it be even feasible to build up your own distrbution network for an ip-company like imgtech given the short window of opportunity in the graphics card market.
 
PiNkY said:
What really makes me wonder is how they finance their design work. To make a high end entry into the pc space late this year I'd estimate, that you'd need at least a .15 design with ~100 Mio transistor. Considering 160 mio $ was often mentioned for the design of GF4 and considering that most work was reused from GF3 than, wouldn't bringing a high end graphics chip to the market require somewhere near 500 mio $ with nowadays design tool and masking costs, without considering distribution & manufacturing costs. Also if they really intend to do it alone, would it be even feasible to build up your own distrbution network for an ip-company like imgtech given the short window of opportunity in the graphics card market.
Click to expand...

You can read about the new SIS graphics spinoff, XGI, for instance here:
http://www.xbitlabs.com/news/video/display/20030520142447.html

Look at the numbers mentioned.
I've found it remarkable how Jen-Tsun of nVidia in every public adress I saw referred on the web remarked how high the cost for GPU development had escalated. Now why would he keep pointing out that? Well, the only really valid reason I could see was that he wanted to deter one or more potential competitors from entering the fray.

All other indications I've seen, such as the size of S3, the rough size of XGI, other industry data points, imply that the number you come up with, roughly half a billion dollar, is vastly inflated, and purely derived from such nVidia public adresses.

On the other hand, I have no way to pinpoint what the actual cost would be for ImgTech.

Entropy
 
Well, it's getting more and more obvious the NV40 isn't a TBDR, since it uses GDDR2. My conclusion, thus, would have to be that the NV40 is simply an unified shading architecture, including a PPP.

That means the PowerVR5 might have quite an advantage over it in specific cases, but that in others, thanks to its unified shading architecture, the NV40 might also have an advantage.

In case anyone doesn't remember the one and only serious info we got for the NV40 ( beside the fact it uses GDDR2 ) , this is from CMKRNL, several months ago:
I had stated earlier that the programmable tessellation unit was going to be in NV35. It's not clear to me anymore that this is the case. Apparently this will be in a 4Q'03 part, which leads me to believe that it will be NV40, not NV35. This part will also contain a completely revamped unified shading model. This means that both vertex and pixel shaders will share the exact same ISA and constructs. In other words, pixel shaders will also have access to constant based/dynamic branching. What's most interesting is that nVidia is not the only company doing these things in that timeframe.
Click to expand...

He's obviously refering to the R400 there, but that has been delayed quite massively AFAIK.
Also, I think it was determined the R400 probably had dynamic resource allocation for that unified shading architecture, so it's likely the NV40 would also have that.


Uttar
 
RussSchultz said:
COuld you share with us why GDDR2 means tile based renderer?
Click to expand...

To be clear, he said GDDR2 means NOT a tile based renderer. But regardless, I'd like to know what his logic is as well.
 
Back to the topic at hand....

I see nothing to indicate that the "Series5" is actually the achrchitecture that ImgTech is talking about when referring to the PC space, and there's no real good hints about timing either.

Based on that slide in the first post, their current focus is not on PC/console/arcade. That comes "later"....whatever that means.
 
Well, do you really need 30GB+ of bandwidth for a TBDR? It'd kinda be overkill, no?

Anyway, yeah, let's get back to Series5...
Come on, Kristof... Ever heard of Smilies talk?
There are 20 smilies - so you can't do the last 6 letters, but damn, who cares about them, anyway? :D Simply leave a blank space for any of those six letters ;) ( And no, a sentence made fully out of those last 6 letters is not gramatically possible )


Uttar
 
You must log in or register to reply here.

Similar threads

R
PowerVR high-end ready.
2
Replies
24
Views
3K
Mendel
M
R
  • Locked
new high-end PowerVR graphics technology (arcade)
Replies
1
Views
2K
Dave Baumann
Dave Baumann
G
ATI Quarterly Earnings Press Release
Replies
14
Views
4K
Geo
G
D
  • Locked
"PSX" market failure causes analysts to reconsider
2
Replies
24
Views
4K
Sonic
S
Back
Top