torch-mlir/lib
Sean Silva 5227d52c26 [RefBackend] Use std.global_memref instead of homegrown thing
This vastly simplifies our code, allowing deleting multiple ops,
simplifying multiple passes, and removing a whole pass.

Now `refback` dialect is down to one op (refback.alloc_memref, which
simplifies allocations to just take a shape instead of individual
extents).
2020-11-13 18:43:50 -08:00
..
Backend Repurpose numpy-compiler compiler/runtime flow for PyTorch. 2020-11-11 10:38:13 -08:00
CAPI Add remaining pieces to capture full example models. 2020-10-19 22:16:59 -07:00
Conversion Make some passes run on FuncOp so they can run in parallel. 2020-11-13 16:12:18 -08:00
Dialect [RefBackend] Use std.global_memref instead of homegrown thing 2020-11-13 18:43:50 -08:00
Python Add missing dependency on NPCOMPCAPI from NPCOMPPythonCommon 2020-10-22 22:44:18 -07:00
RefBackend [RefBackend] Use std.global_memref instead of homegrown thing 2020-11-13 18:43:50 -08:00
Typing Start reworking towards a shared library build. 2020-10-09 16:02:58 -07:00
CMakeLists.txt Start reworking towards a shared library build. 2020-10-09 16:02:58 -07:00
InitAll.cpp NFC: Transition ATen passes to tablegen registration. 2020-10-22 17:12:44 -07:00