torch-mlir/external/iree-dialects/test/python/smoketest.py

# RUN: %PYTHON %s

import mlir.ir
from mlir.dialects import iree

with mlir.ir.Context() as ctx:
  iree.register_iree_dialect(ctx)
Initial import of iree-dialects. We plan on using these dialects "natively" as part of the npcomp backend contract, and provide feedback to evolve them in IREE. Roughly speaking, we can consider these dialects as "what's missing from upstream that we think belongs in the general abstraction layer that npcomp's backend contract targets". We integrate them by just copying the relevant directory from the IREE source tree (with `build_tools/update_iree_dialects.sh`). This avoids adding IREE as a submodule, which is way too heavyweight (including IREE itself, another copy of LLVM, TensorFlow, ...) and would give the false impression of a source dependency rather than the lightweight (and eventually versioned/stabilized) IR-level compatibility that we strive for. 2021-08-12 02:56:25 +08:00			`# RUN: %PYTHON %s`

			`import mlir.ir`
			`from mlir.dialects import iree`

			`with mlir.ir.Context() as ctx:`
			`iree.register_iree_dialect(ctx)`