I suppose CSE would solve my question earlier where 2 identical adds with the
same tensor shapes where not simplified as 1 add with both tensors added?
---
[Visit Topic](https://discuss.tvm.apache.org/t/rfc-cse-optimization/8130/7) to
respond.
You are receiving this because you enabled ma
I agree with @tqchen. CSE is not hard to implement, and CSE on both sides
provides different benefits. So we can potentially support both variants.
---
[Visit Topic](https://discuss.tvm.apache.org/t/rfc-cse-optimization/8130/6) to
respond.
You are receiving this because you enabled mailin
I think there are two potential ways to think about it. We can either try to
do CSE in the Expr level, or we can do CSE in the TE level. I think both will
bring some of the benefit, so it would be helpful to support both variants
---
[Visit Topic](https://discuss.tvm.apache.org/t/rfc-cse-
@tqchen @junrushao1994 how much of the work do you think we can reuse once we
move to https://discuss.tvm.apache.org/t/rfc-tensorir-a-schedulable-ir-for-tvm?
---
[Visit Topic](https://discuss.tvm.apache.org/t/rfc-cse-optimization/8130/4) to
respond.
You are receiving this because you ena
- The user API looks like the following:
```C++
/*!
* \brief Eliminate common subexpressions among \p in_args and between them
and \p output .
*
* \param output The output tensor.
* \param input_grads The gradients of input tensors.
*/
std::pair >
CSE(const Tensor& output,
Thanks for the RFC. Nice finding and it looks good to me overall. Could you
also provide an example of how the user api looks like? Besides, what
information does Tensor Expression Tree provide in addition to Tensor?
---
[Visit Topic](https://discuss.tvm.apache.org/t/rfc-cse-optimization/8
# [RFC] CSE
## Motivation
**C**ommon **S**ubexpression **E**limination is a compiler optimization that
effectively avoids repeated computation of the same expression. It is needed in
the AutoDiff submodule to improve its performance. As an example, consider a
compute definition that is as simpl
