soiferj commented on issue #4879: [Relay][Pass] Fix bug in re-processing call node in MergeComposite pass URL: https://github.com/apache/incubator-tvm/pull/4879#issuecomment-586412142 @mbarrett97 @comaniac I just pushed a test where "result" creates an incorrect graph, and "expected" is correct. Even those these two graphs are different, and "result" generated an incorrect function, they are computationally equivalent. This means that the test actually passes `alpha_equal` both with and without the bug. Here are the Relay outputs. The pattern I am trying to match is `add -> add -> add`. Result: ``` v0.0.4 fn (%a: Tensor[(10, 10), float32], %b: Tensor[(10, 10), float32]) -> Tensor[(10, 10), float32] { %0 = subtract(%a, %b) /* ty=Tensor[(10, 10), float32] */; %4 = fn (%x: Tensor[(10, 10), float32], %y: Tensor[(10, 10), float32], Primitive=1, Composite="add_add_add") -> Tensor[(10, 10), float32] { %1 = add(%x, %y) /* ty=Tensor[(10, 10), float32] */; %2 = add(%x, %1) /* ty=Tensor[(10, 10), float32] */; %3 = add(%x, %y) /* ty=Tensor[(10, 10), float32] */; add(%2, %3) /* ty=Tensor[(10, 10), float32] */ }; %4(%0, %b) /* ty=Tensor[(10, 10), float32] */ } ``` Expected: ``` v0.0.4 fn (%a: Tensor[(10, 10), float32], %b: Tensor[(10, 10), float32]) -> Tensor[(10, 10), float32] { %0 = subtract(%a, %b) /* ty=Tensor[(10, 10), float32] */; %3 = fn (%in_1: Tensor[(10, 10), float32], %in_2: Tensor[(10, 10), float32]) -> Tensor[(10, 10), float32] { %1 = add(%in_1, %in_2) /* ty=Tensor[(10, 10), float32] */; %2 = add(%in_1, %1) /* ty=Tensor[(10, 10), float32] */; add(%2, %1) /* ty=Tensor[(10, 10), float32] */ }; %3(%0, %b) /* ty=Tensor[(10, 10), float32] */ } ```
---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
