RussianSensation
Elite Member
- Sep 5, 2003
- 19,458
- 765
- 126
Some more speculation:
DirectX.Update: Graphics Accelerators: Half a Step Forward
So we get the following most likely picture in the long run:
Code name: R520
Probable name of the product line: RADEON 900 or RADEON 10000
Process 90nm (already known)
Probable time of the announcement: May 2005
Probable number of pipelines 16+8 or 24+8 or 16+8 universal
Shader Model 3.0
Judging from the core complexity, we'll hardly deal with frequencies higher than 600-650 MHz
MMU, storing textures and rendering in PCI-Express memory when necessary
Likely features: fetching and interpolating FP textures, FP blending
512 MB of memory in desktop solutions (already known), 256 bit GDDR3 memory, typical operating frequency (600-750MHz)*2
Rather high price ? the first 512 MB video cards may cost over $600
Why Provide an AGP solution to the market?
"According to my experience, this evolutionary platform replacement used to require and still requires at least 1.5 or even two years, before the volume of accelerators bought for PCI-Express platforms gets equal to the volume of AGP accelerators. Especially as there are decent processors and cost-efficient memory for the old platform so far, which still encourages buying them for new PCs.
There are other fine points as well: like many users have no motivation to replace typical 2.X GHz CPUs in general (they are still quite sufficient for many users) and a more reasonable way to upgrade your accelerator. It can be upgraded to a top AGP solution ? at the same cost it will provide larger gain in games than if you replace the entire platform and buy a new middle end solution for PCI-Express. " - digitlife
Also there are more AGP users than PCIe users who will want to upgrade their graphics card. Certainly anyone with a P4 3.0ghz/A64 3000+ is better off getting R520 than A64 4500+ and 6800GT and it would be unwise for a company to disregard those users, especially given that they already invested money into the RIALTO chip.
DirectX.Update: Graphics Accelerators: Half a Step Forward
So we get the following most likely picture in the long run:
Code name: R520
Probable name of the product line: RADEON 900 or RADEON 10000
Process 90nm (already known)
Probable time of the announcement: May 2005
Probable number of pipelines 16+8 or 24+8 or 16+8 universal
Shader Model 3.0
Judging from the core complexity, we'll hardly deal with frequencies higher than 600-650 MHz
MMU, storing textures and rendering in PCI-Express memory when necessary
Likely features: fetching and interpolating FP textures, FP blending
512 MB of memory in desktop solutions (already known), 256 bit GDDR3 memory, typical operating frequency (600-750MHz)*2
Rather high price ? the first 512 MB video cards may cost over $600
Why Provide an AGP solution to the market?
"According to my experience, this evolutionary platform replacement used to require and still requires at least 1.5 or even two years, before the volume of accelerators bought for PCI-Express platforms gets equal to the volume of AGP accelerators. Especially as there are decent processors and cost-efficient memory for the old platform so far, which still encourages buying them for new PCs.
There are other fine points as well: like many users have no motivation to replace typical 2.X GHz CPUs in general (they are still quite sufficient for many users) and a more reasonable way to upgrade your accelerator. It can be upgraded to a top AGP solution ? at the same cost it will provide larger gain in games than if you replace the entire platform and buy a new middle end solution for PCI-Express. " - digitlife
Also there are more AGP users than PCIe users who will want to upgrade their graphics card. Certainly anyone with a P4 3.0ghz/A64 3000+ is better off getting R520 than A64 4500+ and 6800GT and it would be unwise for a company to disregard those users, especially given that they already invested money into the RIALTO chip.