projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 2c78469) | patch
[TF] Improve verification for integer and floating-point tensor types
authorLei Zhang <antiagainst@google.com>
Fri, 8 Mar 2019 19:12:32 +0000 (11:12 -0800)
committerjpienaar <jpienaar@google.com>
Sat, 30 Mar 2019 00:07:20 +0000 (17:07 -0700)
commit999a0c8736dffdd51483144f9f09be39675504cf
treeb996d70c45e95bd2d17769506bd45e6fbf14d034tree | snapshot
parent2c78469a93d06238701f071904c373d5a1c98d3acommit | diff
[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
mlir/include/mlir/IR/OpBase.td diff | blob | history
Domain: System / Toolchain;