Interesting Info from COO of ATI

My personal guess is its a die shrink with (perhaps) fewer pipes. Or maybe not. The RV250 (i.e. 9000/9000 pro) was exactly that for the 8500.




edit: change H to n, to go from hot to not.
 
The RV250 (i.e. 9000/9000 pro) was exactly that for the 8500.

Compared to the R-200 (Radeon 8500) The RV250 has fewer teture units per pipe, but it is not a die shrink. (Both are 0.15u)

I thought CMKRNL had already established (assuming we continue to hold his credibility in high regard) that R-350 is a 0.15 micron part. The only part that still seems shrouded in mystery concerning the fab process is the RV350. (I assume the RV350 is also the basis for the M10).

So, I would guess that the RV350 could be a die-shrink R-300 with fewer (4, presumably) pipes...same as M10. (I assume M10 and RV-350 are functionally the same exact core, only packaged differently...just like R9000 and M9). R-350 is a complete mystery AFAIAC.
 
So at least two parts that can probably be announced about the time the NV30 becomes generally available.

A DX9 notebook part--pretty much has to be a .13 micron process, fewer pipes.

A part designed to maintain mindshare by beating NV30 benchmarks--could be a tweaked R300 (perhaps with exotic cooling?) or a more thoroughly reworked chip. According to CMKRNL, .15 micron. DDR2 is probably not necessary since they already have a bandwidth advantage, faster regular DDR is available, and they've shown interest in skipping ahead to GDDR3 which will come later in 2003.
 
WaltC said:
T2k said:
I picked up some info yesterday night... in a club ;) (if you were over there you know what I'm talking about ;)): it seems R350 is just an overclocked R300 with no ddr2.
Dunno but previously I expected ddr2 - well, we'll see... ;)


This would be in line with what I have suspected all along--what's the point in making a significant jump in the spring, and then another significant jump in late summer--when you don't have to? Or, as someone else suggested, R350 could be a value part for notebooks (that might or might not fit in with what was said about R350.) I guess I have to concede at this point that we do have some decent evidence that "R350" exists (not that I doubted you, HB, I was just looking for some confirmation from ATI and this would *appear* to be that--except for the nature of the R350, of course.)

But let's say yields have improved and pipelines get tweaked, etc., and you come up with a better cooling solution (not like nv30's--just a lot more efficient than at present)--I don't think 400MHz-425MHz is out of the question for R300. The whole point of the 256-bit bus is to be able to put off the move to DDR II until you have the GPU power to fuel such a bus and you've given the II technology a bit of time to mature. If they stick to DDR but move to 2.2-2.3ns DDR, the combination would significantly enhance current R300 performance (enough to easily steal nv30's thunder--assuming nv30 actually hits 500MHz in quantity), and then save your .13 micron ~500MHz R400 beastie, coupled with your ~40 gig/sec DDRII/256-bit bus for the late-summer/fall release--at which time that product will easily keep up with and probably surpass whatever nVidia might wish to do with its nv30 fall refresh.

But I'm not placing bets...;) ATI surprised the heck out of me with R300--won't be making glib projections about them again...

You're (almost) right... ;)
 
Well isn't ddr2 slowest speed 500mhz ? So ati could infact make a 450mhz r300 with 450 mhz ddr1 ram. I also think it would be faster than a 500mhz geforce fx. I'm sure ati has a trick or two incase a faster r300 loses against the geforce fx. They have had plenty of time to prepare and of course how far off is the r400? Only time will tell i guess all i know is its great for all of us
 
Well isn't ddr2 slowest speed 500mhz ?

Atually, the slowest is 400 Mhz:

http://www.samsungelectronics.com/s...R-II_SDRAM/128M_bit/K4N26323AE/k4n26323ae.htm

500 Mhz is currently the fastest AFAIK.

The fastest DDR that I know of is at 400 Mhz. So there is "overlap" right now between the fastest DDR and the slowest DDR-II.

What I don't know, is how their costs or relative performance compare. Performance is probably about a wash or a bit better for DDR-II, but cost is probably also a little be higher.
 
Blah

This hole Nvidia - ATI argument is just stupid. o_O Sorry, I need to release and this threads info happens to come along at my boiling point. One isn't better than the other or ahead of the other because their product cycles are 6 months apart, yeah, ATI has a better card, in Feb, Nvidia will have a better card, in July ATI will have a better card, next Feb Nvidia will have a better card......blah blah and so on. People get so tired of the bickering, its all about what time of the year are you ready to plop down the cash.

***edit***
BTW, I'm not a fan of either, just whichever comes when I have the cash, so I'm not arguing for on or the other. Just releasing.....ahhhh :)
 
Geeforcer said:
DaveBaumann said:
They are all R300 chips.

Even the 4-pipeline ones? (assuming that ATi is or is going to produce 4-pipe derivative rather then the crippled R300)

R9500Pro / R9700 / R9700Pro all share Device ID 4E45. This is because they are the same chip and the driver(s) can behave in the same manner on each of them. The R9500 has Device ID 4E44, so ultimately it must be a little different from the rest of the R300 family else ATI would not have differentiated the Device ID.
 
This hole Nvidia - ATI argument is just stupid.

But of the utmost importance is WHEN both IHVs (and the other IHVs out there) will have full market spread of at least notable DX9 capabilities (i.e the sub <$200 as well as high-end) to help migrate the user base in that direction.

The sooner ATI, NVIDIA and the others can get reasonably priced, low-end, middle-end and high-end DX9 shader-ready products on the shelf, the sooner developers can assume good returns on more effective quality DX9 games.
 
Joe DeFuria said:
* ATI is trying to continue its "revolutionary" tech / product introduction on a 12 month cycle, with a "kicker" in between (at about the 6 month point.)

Well at least they're still claiming a yearly product cycle, unlike nVidia who uses that exact same "six month" cycle... :LOL:
 
Doesnt seem to effect investors much. I'm pretty amazed at their mirror trend with all similar markets... unlike other contenders in this arena..

http://finance.yahoo.com/q?d=c&c=ATYT&k=c1&t=1y&s=nvda&a=v&p=s&l=on&z=m&q=l&x=on&y=on&w=on

Lol, funny inference. Of course its based on a distorted devaluation of NVDA that should have occured last year.

Looking at 5 year we see NVDA well out performing the indexes, unlike other contenders in this arena...

http://finance.yahoo.com/q?s=NVDA&d=c&k=c1&c=ATYT,^gspc,^ixic,^dji&a=v&p=s&t=5y&l=on&z=m&q=l
Looking at the last three months we see NVDA well out performing the other contenders in this arena...

http://finance.yahoo.com/q?s=NVDA&d=c&k=c1&c=ATYT,^gspc,^ixic,^dji&a=v&p=s&t=3m&l=on&z=m&q=l

Of course, the question wasnt about investor sentiment, it was about returning to profitability. Since when has share price reflected market reality?
 
Waltc
I picked up some info yesterday night... in a club (if you were over there you know what I'm talking about ): it seems R350 is just an overclocked R300 with no ddr2.
Dunno but previously I expected ddr2 - well, we'll see...

This information is false. Yes To DDR no to just an overclocked R300.

Several new Features, important features....
 
Hellbinder[CE said:
]Waltc
I picked up some info yesterday night... in a club (if you were over there you know what I'm talking about ): it seems R350 is just an overclocked R300 with no ddr2.
Dunno but previously I expected ddr2 - well, we'll see...

This information is false. Yes To DDR no to just an overclocked R300.

Several new Features, important features....

I didn't say it's true or not - decide yourself. Actually, today I believe this...

BTW, I'm curious to know that can you provide anything to back up your statement?
 
king_iron_fist said:
IMO to get an idea what to expect in the r400 we should look at the innovations found on the gamecube ;).

http://www.anandtech.com/showdoc.html?i=1566&p=1

i.e. things like embedded ram, and large Z and texture buffers

Not necessarily. While I will agree that embedded RAM is an excellent idea, it's still quite hard to fabricate, meaning the chips will generally have a much lower clock speed with embedded RAM than without. It makes more sense, to me, to see embedded RAM first in a laptop part, not in a high-performance desktop part. Later on, well, embedded RAM may become necessary to fully harness the power of the GPU (and CPU!).
 
Back
Top