KennyT772
New Member
- Joined
- Dec 21, 2005
- Messages
- 3,572 (0.53/day)
| System Name | Raptor |
|---|---|
| Processor | Intel E8400 Wolfdale @3600 |
| Motherboard | Asus P5Q-Pro LGA775 |
| Cooling | Zalman CNPS9700 |
| Memory | 1024mbx2 Crucial Ballistix DDR800 |
| Video Card(s) | XFX 9600GT |
| Storage | Seagate 7200.11 500GB |
| Display(s) | Acer AL2216Wbd and Acer AL1717 |
| Case | Gigabyte 3DAurora Black |
| Audio Device(s) | Creative X-Fi Extreme Gamer Faitality |
| Power Supply | OCZ GameXStream 500w |
Also note that the memory speeds shown in this demo are at 375x2 or 750mhz 3-3-3-9. There are kits out there today that do over 600x2 at 5-5-5-15, which would give a much better score. SuperPI 1m is rather finnicky about ram timings and speed.
This was built as a ground up, server style CPU. The power settings, independant multiplier, independant voltage, fully interconnected cores, etc. AMD wanted to counter intels greatest problem with current dual die stratagy, intercore latency and scaling. Given the HT speed, and the design of the core, there should be almost a 100% increase in processing power for every core available. With intels quads its around 100% going from single to dual, then about 80% or so iirc from dual to triple and triple to quad. This is due to the cores of one die having to use the FSB to access the other. The latency from that process, and the way windows handles multiple cpus (threads constantly switch which core they are on to dynamically load balance), creates a problem for intel. AMD may not have the architecture, but they do have a plan.
This was built as a ground up, server style CPU. The power settings, independant multiplier, independant voltage, fully interconnected cores, etc. AMD wanted to counter intels greatest problem with current dual die stratagy, intercore latency and scaling. Given the HT speed, and the design of the core, there should be almost a 100% increase in processing power for every core available. With intels quads its around 100% going from single to dual, then about 80% or so iirc from dual to triple and triple to quad. This is due to the cores of one die having to use the FSB to access the other. The latency from that process, and the way windows handles multiple cpus (threads constantly switch which core they are on to dynamically load balance), creates a problem for intel. AMD may not have the architecture, but they do have a plan.
