undefined | Better HN

0 pointskbenson7y ago0 comments

Would they be using mostly CPU for that, or would they offload it to the GPU or a dedicated chip? I would assume you would use your general purpose CPU only if all else wasn't available (and generally there's a GPU available on most end user devices these days).

0 comments

greglindahl7y ago

If possible the GPU, but not all GPUs have either a library or enough documentation to write one. I’ve seen complaints about this issue on mobile GPUs for years, no idea how widespread it is now.

BTW, this is just one example algorithm that I picked because it does (on the cpu) what the person I replied to said was rare.

rbanffy7y ago

Running the model is much easier than training it. On power-constrained environments, DSPs can do it.

j / k navigate · click thread line to collapse

0 pointskbenson7y ago0 comments

0 comments

greglindahl7y ago

If possible the GPU, but not all GPUs have either a library or enough documentation to write one. I’ve seen complaints about this issue on mobile GPUs for years, no idea how widespread it is now.

BTW, this is just one example algorithm that I picked because it does (on the cpu) what the person I replied to said was rare.

rbanffy7y ago

Running the model is much easier than training it. On power-constrained environments, DSPs can do it.

j / k navigate · click thread line to collapse