[TensorExpr] fix a bug in LLVM codegen around empty kernels (#36660)
Summary:
LLVM Codegen assumes that the kernel contains real statements, but that is not guaranteed, especially after IR Simplification. This PR adds a catch for the case where no value is generated after recursing the LLVMCodegen visitor through the kernel.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/36660
Differential Revision: D21044066
Pulled By: nickgg
fbshipit-source-id: e521c766286b1ff4e26befcec7ff4959db8181a4