Recent content by Mat3

If people feel progress is starting to stagnate and prices are too high, just wait until the next process node (10nm FF). It'll make the 4 years at 28nm seem like it just breezed by.

I thought the point was to take stuff traditionally done on the CPU and do it on the GPU shaders..

Good read, thanks.

Rather than two identical GPUs on an interposer, what about separating different parts of one GPU? Specifically I mean separate the shader array from the rest of the chip. So we'd have 1 processor, the shader array, connected to the second processor (ROPs, memory controllers and interface...