tree 1ecc0032ceee551cac542bf637b65c1c9116aea5
parent 5e5cbd43802d701ccd62c8dcc0e6042c5f77652b
author Lei Zhang <antiagainst@google.com> 1648066464 -0400
committer GitHub <noreply@github.com> 1648066464 -0400
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsBcBAABCAAQBQJiO3+gCRBK7hj4Ov3rIwAAMAYIAKhl5MVbsS+roClJ63hzGrrX
 gaysG9qZsAyMmAOw01c7/EyKjy4bGwyI7PIo4kD4BYDNDsJBqWZqG9RcIyKC7h9g
 eCUxtN3to8LkdEjLu7tdyOI5Q4IPWulSlRyCQ3siELaaHBFnhT1+Ng0fpstkii38
 t+Yb+cQvArAykHCQzxDQ6zCOMezN3BKijj5tFDrQLT1MTh+kFJ6sQj2nadtmI5n8
 zmKPAi6DizQ+q4Y/JLmr0rTYmITWqwkp7SaL4GmL9mjFel2sZIUbBoxfeypzl0Xo
 +EInPSKeDmm1/pozWTIzTptRmyTO2qF+fb5BeJCNHSqTzcb2xK6bazujEux/71Y=
 =YQBK
 -----END PGP SIGNATURE-----
 

Integrate llvm-project at 9816fada1667ecc3343d285295c95848826693af (#8612)

* Reset third_party/llvm-project: 9816fada1667ecc3343d285295c95848826693af (2022-03-18 10:50:55 +0100): [bazel] Port a954ade8ed41
  * Cherry-picked https://github.com/llvm/llvm-project/commit/3b74aac29c97b587c30d940e00b338af384ede59 additionally to fix bufferization issues
* TensorFlow commit: c9ddfac348b1f423e1463ae78b046514a8b03a48
  * Cherry-picked https://github.com/tensorflow/tensorflow/commit/9642bbdbb6b27443d339b714f233272eb74ca637 additionally to fix leftover `dump()` calls for debugging
* MHLO commit: 467cd37703dc0c4195ce6351617ef320bb60e927
* Updated external model registration
* Updated FuncOp usages
  * The attribute carrying type information now should be `function_type`, instead of `type`.
  * `mlir::FuncOp` is now in `mlir::func::FuncOp`.
  * `builtin.func` in assembly should be `func.func` now.
* Updated MHLO attribute assembly for `comparison_direction`, `precision`, etc.
* Fixed TFL/StripMetadata.cpp to avoid dropping `tf_saved_model` attributes for ABI information