tvm-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From aca88 via TVM Discuss <nore...@discuss.tvm.ai>
Subject [TVM Discuss] [Development] Google lasted work: MLIR Primer
Date Thu, 11 Apr 2019 11:09:41 GMT


[quote="grwlf, post:28, topic:1721, full:true"]
Let me stress the attention on the fact, that MLIR doesn’t only offer different IR, it also
offers different approach to scheduling via its Polyhedral dialect. For example, I see affine
transformations as types in the standard.
[/quote]

This is what I meant in my post 

[quote="aca88, post:14, topic:1721"]
1. MLIR seems to (natively?) support descriptions targeted for polyhedral dialects. Since
TVM does not use the polyhedral model, I guess we would be limited in the usage of this information
but could it also be an impairment?
[/quote]

Since the loop transformations which TVM does are a subset of all possible with the polyhedral
modelling, I guess we would be ok.
Obviously, TVM could offload part of scheduling to MLIR and invoque from there the polyhedral
dialect.
That I think is part of the goal of MLIR that the "right" dialect is used for the right part
of the whole compilation task





---
[Visit Topic](https://discuss.tvm.ai/t/google-lasted-work-mlir-primer/1721/31) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/d9b590096a9b5016ef22b5deb029b0e69b0f02aa6cb1ce48a6b1cb3ce7a26a7d).

Tianqi Chen, UW, Seattle, WA, 98105, United States
http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=pl0Z742JX_NcE8WB3Qs-DA2
Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message