Dynamic Automatic Differentiation of GPU Broadcast Kernels (opens in new tab)

(arxiv.org)

5 pointsjrevels7y ago1 comments

1 comments

One of the author here. Working on this paper was fun, one of the most interesting lessons I learned was that divergence on GPUs has dramatically fallen in cost on modern architectures.

j / k navigate · click thread line to collapse

Dynamic Automatic Differentiation of GPU Broadcast Kernels (opens in new tab)

(arxiv.org)

5 pointsjrevels7y ago1 comments

1 comments

wallnuss7y ago

One of the author here. Working on this paper was fun, one of the most interesting lessons I learned was that divergence on GPUs has dramatically fallen in cost on modern architectures.

j / k navigate · click thread line to collapse