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
..
ATen	Add aten.maximum op and conversions from aten->tcf.	2020-11-04 17:20:54 -08:00
Basicpy	Bump llvm-project to 72ddd559b8aafef402091f8e192e025022e4ebef	2020-10-30 18:12:41 -07:00
Numpy	More progress on PyTorch acap device capture.	2020-10-15 21:43:21 -07:00
Refback	[RefBackend] Use std.global_memref instead of homegrown thing	2020-11-13 18:43:50 -08:00
Refbackrt	[RefBackend] Use std.global_memref instead of homegrown thing	2020-11-13 18:43:50 -08:00
TCF	[RefBackend] Support element-wise multiply op	2020-10-27 19:41:23 -07:00
TCP	[TCP] Replace tcp.matmul with linalg.matmul.	2020-11-10 18:58:28 -08:00
Torch	Add a number of kernels and new patterns.	2020-11-04 14:36:59 -08:00
CMakeLists.txt	[RefBackend] Rename RefBackend dialect to Refback	2020-10-08 09:07:00 -07:00