Ashadian said:
Did they now? The latency is nowhere near where your suggesting at all. Maybe about 20-25% max. You also forget the advantages of the unified GDDR5? Both CPU and GPU can access it at the same time. Once the developers get their heads round this was the machine fly. No need to send information back and forth between memories.Everything the GPU needs from the CPU, it can access. Everything the CPU needs from the GPU, it also can access. There is NO need for it to copy data from the main ram to a different pool of RAM. That along with the huge bandwidth advantage, will put it ahead of the X1. |
latency will still play a big role in the CPU getting the information it needs fast enough for it to perform its calculations. The CPU works on smaller sets of data so it crunches those pretty fast but if its dealing with latency issues with the ram, it will have an effect. No matter how fast one part is, the complete system will always be hampered by its slowest component.