**Motivation:**
Existing `TensorIntrin` has "reduce_init" and "reduce_update" to support the
tensorization of reduce_axis == 0 and reduce_axis > 0 specifically, which is
already well suited for many cases. However, the support for activation fusion
is still missing, because it lacks of facili
Hi @tqchen and @zxybach,
cc : @mbaret
What is a Composite Target ?
TVM being a multi-target compiler, it would be a bit confusing to use a Array
of Targets as another Composite Target -- I think its the terminology what is
confusing here.
A composite target sounds like a target that codegen
https://discuss.tvm.apache.org/t/rfc-composite-target/7744
---
[Visit
Topic](https://discuss.tvm.apache.org/t/pre-rfc-compilation-configuration-representation/11372/7)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here
Thanks for the discussions. To begin with, I am not that attached to the
particular choice of name. We can for example, decide to introduce another
target kind
("hetero-target", "myawesome-target", "platform", "CompilationOption").
I think our discussion boils down to the following quenstion
> Usage of te.AXIS_SEPARATOR: It seems this is only used in the API side but
> not in BufferTransform, would be good to get some clarification.
That's correct, the `te.AXIS_SEPARATOR` only appears in the API for the TE
schedules, and not in the TIR graph generated from the TE schedule. I've
up
Thanks for adding the discussion points.
I understand the difficulty implementing it as eager transform in TE, mainly
because most other schedule primitives were not done eagerly as in TIR. So
adding a rewrite pass for `BufferTransform` makes sense to me.
> Should BufferTransform apply only to
I agree with @tqchen that improving composite targets could be more beneficial
and general. We (with @junrushao1994 and @zhiics) previously attempted to
improve the target system to allow more flexible attributes, such as a pass
sequence / runtime / etc specifically for the target, which is ve
Thank you @Mousius for the RFC! It's great to read about potential user
experience issues of the current Target system, and happy to discuss about
potential ways to improve it.
## Proposeds API in the RFC
`CompilationConfig`, as proposed in this RFC, aims to improve UX by wrapping a
list of
> Since Option2 suggests the transform is global, shall we consider
> BufferTransform being part of function attribute?
I had initially placed `BufferTransform` as a statement so that it could be
possible to extended it to have a transformation defined by references to
variables within the func
> > Should we wait for PyTorch TVM PR #8777? It should be merged soon.
>
> @masahi we can wait for it if this PR could get in this week
Does this mean we will update v0.8 branch again this week, I merged a new pull
request this week early https://github.com/apache/tvm/pull/9428 , will this be
@jiangjiajun Yes, we will update v0.8 branch and cut a release candidate on Nov
8, 2021. After the cut, we will ask the community and PMC members to test to
release, and if there is no regression we will make the release official
--
You are receiving this because you are subscribed to this thre
@jiangjiajun Yes, we will update v0.8 branch and cut a release candidate on Nov
8, 2021. After the cut, we will ask the community and PMC members to test to
release, and if there is no regression we will make the release official
--
You are receiving this because you are subscribed to this thre
12 matches
Mail list logo
