Lei Zhang 999a0c8736 [TF] Improve verification for integer and floating-point tensor types ...

TensorFlow does not allow integers of random bitwidths. It only accepts 8-,
16-, 32-, and 64-bit integer types. Similarly for floating point types, only
half, single, double, and bfloat16 types.

PiperOrigin-RevId: 237483913

2019-03-29 17:07:20 -07:00

..

bindings/python

Python bindings: introduce loop and loop nest contexts

2019-03-29 17:06:36 -07:00

g3doc

Update the PassManager infrastructure to return Status instead of bool.

2019-03-29 17:05:51 -07:00

include

[TF] Improve verification for integer and floating-point tensor types

2019-03-29 17:07:20 -07:00

lib

Introduce a TypeID class to provide unique identifiers for derived type classes. This removes the need for derived types to define a static typeID field.

2019-03-29 17:07:06 -07:00

test

Add a basic model to set tile sizes + some cleanup

2019-03-29 17:06:51 -07:00

tools

Update the PassManager infrastructure to return Status instead of bool.

2019-03-29 17:05:51 -07:00

unittests

NFC: Remove 'Result' from the analysis manager api to better reflect the implementation. There is no distinction between analysis computation and result.

2019-03-29 17:02:12 -07:00

utils

Automated rollback of changelist 232728977.

2019-03-29 16:21:38 -07:00

.clang-format

…

LICENSE.TXT

…