[TorchToLinalg] Casting float to integer should round to nearest for AtenPowTensorTensorOp.

[cats-marin]

Fixes #4091. I assume this will also need to be fixed for AtenPowScalarOp and AtenPowTensorScalarOp as well. I'm putting up a PR to ensure the initial approach is correct (new contributor :D ) before I put up another fix for AtenPowScalarOp and AtenPowTensorScalarOp.

[cats-marin]

It'd be great if you could review this @zjgarvey!

[zjgarvey]

Hey, this generally looks like good work, but I have a few notes:

1. The issue TorchToLinalg: casting float to integer should round to nearest #4091 really pertains to the behavior of the TorchOnnxToTorch lowering.
2. Note the comment here , which indicates that the torch op only has an integer result type when both the base and exponent dtypes are integer types. This means that if we properly generate IR for AtenPowTensorTensorOp, we will never be in the situation covered by your current changes.
3. A proper resolution to the issue is likely to edit

   torch-mlir/lib/Conversion/TorchOnnxToTorch/DefaultDomainGtoP.cpp

   Lines 3074 to 3076 in 866786c

   	rewriter.replaceOpWithNewOp<Torch::AtenToDtypeOp>(
   	binder.op, resultType, pow, outTyConst, cstFalse, cstFalse, none);

   to also include something like:

pow = rewriter.create<AtenRoundOp>(loc, pow.getType(), pow);

(Note: AtenRoundOp lowers to an elementwise application of math::RoundEvenOp).

[zjgarvey]

This conversion still doesn't support non-float/non-int dtypes. E.g. complex dtypes.

I'd recommend still computing the dtype and adding a check on dtype.isIntOrFloat().