|
|
|
|
|
|
by orf
634 days ago
|
|
|
Having a common library function that is either lighting fast or dog slow depending on the hardware, is not a great position to be in. Moreover, this will get worse as more CUDA specific features are added to PyTorch with ad-hoc fallback functions. I guess OP is saying that XLA is more transparent in this regard, because it wouldn’t use functions like these and the generated comparable code would be on-pare performance wise? |
|
|
Perhaps if XLA generated all functions from scratch, this would be more compelling. But XLA relies very heavily on pattern-matching to common library functions (e.g. CuDNN), and these patterns will certainly work better on Nvidia GPUs than AMD GPUs.
In this way, I actually think explicitly calling the common library functions is actually much more transparent.