From our front-page news:
In the tech world, bigger is better, right? Wrong, according to AMD. When asked by a C|Net blog as to why they are not building huge chips like NVIDIA, they responded, "We believe this is [building smaller chips] is a much stronger strategy than going for a huge, monolithic chip that is very expensive and eats a lot of power and really can only be used for a small portion of the market."
Tu shay, AMD, tu shay. That's a valid point, though. Why build a massive power-sucking processor rather than pairing two efficient processors together for the same performance? It can be argued though, that this is a needless argument, because the fact of the matter is, dual-GPU cards are still watt-suckers. This will always be the case unless the architecture is redesigned to allow one GPU to be shut off while it's not needed.
The other argument that can be brought up is that one massive GPU is better than two mid-range offerings, because it will increase performance in all games, not only those that can properly take advantage of a multi-GPU setup. One GPU would deliver the full load of power, while a multi-GPU card may only deliver one-half of its available power. It all varies from game to game, however, and many today will indeed handle multi-GPU setups well.
One things for sure though, with AMD's next-gen dual-GPU offering and NVIDIA's massive single-GPU card en route, next month is going to be incredibly interesting.
<table align="center"><tbody><tr><td>
</td></tr></tbody></table>
"We believe this is a much stronger strategy than going for a huge, monolithic chip that is very expensive and eats a lot of power and really can only be used for a small portion of the market," he said. "Scaling that large chip down into the performance segment doesn't make sense--because of the power and because of the size."
Source: C|Net Blog
Tu shay, AMD, tu shay. That's a valid point, though. Why build a massive power-sucking processor rather than pairing two efficient processors together for the same performance? It can be argued though, that this is a needless argument, because the fact of the matter is, dual-GPU cards are still watt-suckers. This will always be the case unless the architecture is redesigned to allow one GPU to be shut off while it's not needed.
The other argument that can be brought up is that one massive GPU is better than two mid-range offerings, because it will increase performance in all games, not only those that can properly take advantage of a multi-GPU setup. One GPU would deliver the full load of power, while a multi-GPU card may only deliver one-half of its available power. It all varies from game to game, however, and many today will indeed handle multi-GPU setups well.
One things for sure though, with AMD's next-gen dual-GPU offering and NVIDIA's massive single-GPU card en route, next month is going to be incredibly interesting.
<table align="center"><tbody><tr><td>
</td></tr></tbody></table>
"We believe this is a much stronger strategy than going for a huge, monolithic chip that is very expensive and eats a lot of power and really can only be used for a small portion of the market," he said. "Scaling that large chip down into the performance segment doesn't make sense--because of the power and because of the size."
Source: C|Net Blog
