@masahi FromTupleType is the one you probably want it takes a Type representing
the layout of `expr` and returns a sequence of expressions which correspond to
the linearized view of the tuple, i.e it will handle projecting nested tuples
out.
---
[Visit
Topic](https://discuss.tvm.apache.o
There is a C++ helper called Linearize or FlattenTuple (can look later)
---
[Visit
Topic](https://discuss.tvm.apache.org/t/graph-plan-memory-doesnt-support-nested-tuples/8278/6)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [c
@masahi there is code for doing this mapping inside of the VM, if you message
me on Slack we can probably figure out how to update the code, might require a
bit of debugging
---
[Visit
Topic](https://discuss.tvm.apache.org/t/graph-plan-memory-doesnt-support-nested-tuples/8278/4)
to respo
Further help might be that the word "lanes" in English refers to the separate
streams of traffic on the road (https://en.wikipedia.org/wiki/Lane) in SIMD
terminology it often refers to the "width" of a vector instruction's inputs
(i.e 4 element vector in Tianqi's example) and by extension the
Relay is used to do "graph" (or full program level optimization) and TIR is
used to do imperative loop optimization for (mostly) dense linear algebra
kernels.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/ir-level-or-hierarchical-relationship/7869/6)
to respond.
You are receiving t
I think someone just needs to expose this in Python you could probably do so
with
```
TVM_REGISTER_GLOBAL("SimplifyStmt").set_body_typed([](tir::Stmt stmt) {
arith::Analyzer analyzer;
return arith::StmtSimplifier(&analyzer).Simplify(stmt);
});
```
and in Python
```
tvm.get_global_fun
