Cookiee235 commented on issue #17247:
URL: https://github.com/apache/tvm/issues/17247#issuecomment-2273333123
@Lunderberg Fixing for fixing the wrong implementation about
`assert_structural_equal`.
For the given IRs in my script, an odd IRs was obtained after using the
`RemoveUnusedOutputs` optimization. It seems function `func` should not be
removed. Can you help me check if this is a bug？
_____________________________________________________________________________________________________
#### Output IRs after the RemoveUnusedOutputs
```
@I.ir_module
class Module:
@R.function
def main(v0_0: R.Tensor((1,), dtype="int32"), v1_0: R.Tensor((42,),
dtype="int32")) -> R.Tuple(R.Prim(value=T.float64("nan")),
R.Prim(value=T.float64("nan")), R.Prim(value=T.float64("nan"))):
R.func_attr({"num_input": 2})
with R.dataflow():
res: R.Tuple(R.Prim(value=T.float64("nan")),
R.Prim(value=T.float64("nan")), R.Prim(value=T.float64("nan"))) =
R.prim_value(T.float64("nan")), R.prim_value(T.float64("nan")),
R.prim_value(T.float64("nan"))
R.output(res)
return res```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
