D_o_S
Moderator
- Joined
- Aug 27, 2005
- Messages
- 954 (0.14/day)
Processor | AMD Opteron 144 |
---|---|
Motherboard | DFI Lanparty nF4 SLI-DR Expert |
Cooling | Watercooled - Alphacool Nexxxos XP, BIX2, Eheim HPPS |
Memory | 2x 512MB OCZ PC 3200EL Platinum Rev.2 (TCCD) |
Video Card(s) | 2x Gainward GeForce 6800 Ultra (430/1200) |
Storage | 4x WD Raptor 740GD in RAID 0 |
Display(s) | Eizo FlexScan L768 |
Case | CM Stacker |
Audio Device(s) | Audigy 2 |
Power Supply | Silverstone Zeus ST65ZF |
The GPUs that we are used to today comprise of several parts that are all joined together by a high speed interconnect. Now, imagine separating the core out into several chips, again connecting all of them by an interconnect. The great advantage would be that to increase performance you would simply increase the number of cores, design of GPUs could also be simplified.
For example, low end cards could have 2 of these "cores", middle range cards would utilize 4, and high end cards would boast 8 processing units.
The Inquirer reports that this is exactly what we can expect from the AMD/ATI R700 chip, and perhaps NVIDIA's G90.
View at TechPowerUp Main Site
For example, low end cards could have 2 of these "cores", middle range cards would utilize 4, and high end cards would boast 8 processing units.
The Inquirer reports that this is exactly what we can expect from the AMD/ATI R700 chip, and perhaps NVIDIA's G90.
View at TechPowerUp Main Site