Hacker News Reader

In theory yes, because you wouldn't need to copy the data, in practice it depends on the API and you might end up copying data from RAM to RAM. If the API doesn't allow you to simply pass an address to the GPU then you need to allocate memory on the GPU and copy your data to that memory, even if it's unified memory.

View on HN

For Apple specifically, you have to act as if you do not have unified memory because Apple still supports discrete GPUs in Metal and also Swift is reference counted - the CPU portion of the app has no idea if the GPU portion is still using something (remember that the CPU and GPU are logically different devices even when they are on the same die).

When you are running your code on an M- or A-series processor, most of that stuff probably ends up as no-ops. But worse case is that you copy from RAM to RAM, which is extraordinarily faster than pushing anything across the PCIe bus.

Good to know, thanks!

Reply on news.ycombinator.com