frozenleaves/pytorch
1
0
Fork 0
mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updated Codegen and Structured Kernels (markdown)

ananthsub
2022-04-27 10:53:54 -07:00
parent 431a0c31ca
commit 694dd97dec
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Codegen-and-Structured-Kernels.md

@ -162,7 +162,7 @@ These are all codegen’d and live in `torch/csrc/autograd/generated/python_torc
#19: at::Tensor::add
#18: at::_ops::add_Tensor::call
The next stop is the C++ method API, which is one of the top-level API’s for calling into the dispatcher. The dispatcher then looks at all of the arguments + any thread-local state to figure out which kernel to dispatch to. https://fb.quip.com/crnrAjLMKVbs has some more details about the dispatcher key-calculation process.
The next stop is the C++ method API, which is one of the top-level API’s for calling into the dispatcher. The dispatcher then looks at all of the arguments + any thread-local state to figure out which kernel to dispatch to. https://github.com/pytorch/pytorch/wiki/PyTorch-dispatcher-walkthrough has some more details about the dispatcher key-calculation process.
In `build/aten/src/ATen/TensorBody.h`: