Sean Silva 40369c54dc Adjust pass pipeline for changes to `dim` canonicalization. ... This results in cleaner IR. In particular, Mlp2LayerModule e2e test has a dim op that is eliminated by this change: https://gist.github.com/silvasean/734f11a291ae6236c955f65cffae285f		2021-06-17 16:59:55 -07:00
..
AdjustCallingConventions.cpp	Add `!torch.bool` type.	2021-06-16 13:22:00 -07:00
BackendTypeConversion.cpp	Add a !torch.float type.	2021-06-17 09:24:18 -07:00
CMakeLists.txt	Adjust pass pipeline for changes to `dim` canonicalization.	2021-06-17 16:59:55 -07:00
GlobalizeObjectGraph.cpp	Add a !torch.float type.	2021-06-17 09:24:18 -07:00
InlineGlobalSlots.cpp	Add `!torch.bool` type.	2021-06-16 13:22:00 -07:00
MaximizeValueSemantics.cpp	Add `!torch.bool` type.	2021-06-16 13:22:00 -07:00
PassDetail.h	Implement GlobalizeObjectGraph transformation.	2021-02-18 18:18:47 -08:00
Passes.cpp	Adjust pass pipeline for changes to `dim` canonicalization.	2021-06-17 16:59:55 -07:00
PrepareForGlobalizeObjectGraph.cpp	Add `!torch.bool` type.	2021-06-16 13:22:00 -07:00
ReduceOpVariants.cpp	Add `torch.vtensor.literal` op.	2021-06-17 14:37:04 -07:00
RefinePublicReturn.cpp	Introduce `!torch.tensor` / `!torch.vtensor` types.	2021-06-10 10:56:48 -07:00
RefineTypes.cpp	Add `!torch.int` type.	2021-06-17 07:28:23 -07:00