What do you expect for R650

What do you expect for HD Radeon X2950XTX

  • Faster then G80Ultra about 25-35% percent overall

    Votes: 23 16.4%
  • Faster then G80Ultra about 15-20% percent overall

    Votes: 18 12.9%
  • Faster then G80Ultra about 5-10% percent overall

    Votes: 18 12.9%
  • About same as G80Ultra

    Votes: 16 11.4%
  • Slower thenll G80Ultra about 5-10% percent overall

    Votes: 10 7.1%
  • Slower then G80Ultra about 15-25% percent overall

    Votes: 9 6.4%
  • I cannot guess right now

    Votes: 46 32.9%

  • Total voters
    140
So has anyone heard any rumors re. R650 tape-out? In the (somewhat extreme) case of R600 it seems to have been a year tapeout-to-retail gap.
 
Which to me means one of two things: Either they have gotten much better at information control or the new hardware is ways off.
 
I think its kind of sad that half of the info Fudzilla posts seems to come right from the beyond3d forums.

That's fine and dandy, IF they gave some props out to the site and forums.
 
My hope for R650: The excellent image quality that ATI is known for, at competitive speeds.

R600 is a bust strictly on image quality. The performance isn't stunning, and it looks like they tried to make up for that by playing around with the IQ. I don't know whether it is due to software or hardware, but it looks terrible. I don't even have to guess which card screen shots are taken on when I look at 1900XT vs. 2900XT or 2900XT vs. 8800GTS. I just point to the one that looks the worst to me out of the bunch and it's the 2900XT.

Bring back excellent image quality and get rid of the blurry mess. Competitive performance is next in line to IQ - it doesn't have to be the absolute fastest, but it does need to be competitive provided that it looks great. It would be a bonus if it was power efficient.
 
jesus christ...i cant take another one of these threads where people speculate for far far too long about what AMD will screw up next......sheesh!
 
As of this point, R650 is still mysteries what is really going to be.
If you look back in history; Nvidia Geforce 3 NV20 was updated to Geforce 4 NV25.
NV20 ---> NV25 to me was big improvement what Nvidia did back then. Also take a look at NV40/NV45 (GF6) was updated to NV47 (GF7).

Well if we go back to ATI: R300 ----> R350 was very small core tweak, R520 ----> R580 was added 3:1 ratio for pixel shader processors.

R650 will be @ 65nm which means not only the core be capable increasing frequency, but ATI should be able to add more horsepower since @ 65nm their will be availaible more space. (Example how Intel bump from Pentium4 90nm 1MB-L2 cache to ----> Pentium4 65nm 2MB-L2 cache)
 
I expect a stupidly highly clocked GPU with high power usage. It will also use a HSF combo that everyone complains is too loud. Really, what was the last top end ATI/AMD card that people haven't complained about the noise or power usage.

As far as performance, I'm going to say general case about the same as the Ultra some benches slightly faster, some slightly slower. Contrived ideal cases will be much faster, and contrived worse cases much slower.

Filtering and AA will remain unchanged though performance of AA should be much improved.
 
I see two possibilities for R650 (assuming it's 65nm or smaller):

1. R600 die shrinked and bugs fixed, higher clocks, GDDR4 (aka 'simple' version).

2. R600 with increased number of units (but not drasctically; i'd expect something like 64->80 shader processors, 16->20 TMUs (40 filtering units this time maybe?), 16->24 ROPs, bugs fixed, higher clocks, GDDR4 (aka 'complex' version).

I'd vote for the second one simply because i like complex versions more than simple 8)
 
Will it? If, and that's a fairly decent sized if, another big R6 chip shows up, don't automatically expect it to be 65nm.

Are you suggesting that we aren't going to see another big chip from AMD Rys? Instead, are they looking at multi-chip boards to fill the high-end, ala 3dfx??
 
I expect it to be cooler and faster and to have really beefed up shaders.

Before you say they don't need to beef up the shaders I agree totally, but history is on my side :D

It's probably a medical condition they have.
 
Are you suggesting that we aren't going to see another big chip from AMD Rys? Instead, are they looking at multi-chip boards to fill the high-end, ala 3dfx??

Or maybe people ought to spend more time considering what the second 1/2 of his formulation might be suggesting.
 
Adding more ALUs is rather pointless at this time, although it's the easiest path to take on. It is evident, that the bottleneck is not there, as the numerous vertex/geometry benchies are showing considerable headway to G80.
 
Back
Top