[layer8]

CPUs access GPU memory via MMIO (though usually only a small portion), and GPUs can in principle access main memory via DMA. Meaning, both can share an address space and access each other’s memory. However, that wouldn’t be called Unified Memory, because it’s still mediated by an external bus (PCIe) and thus relatively slower.

[bobmcnamara]

Are they cache coherent these days? I feel like any unified memories should be.