[RFC] UMA: Universal Modular Accelerator Interface

[MJKlaiber]

Andrew, thanks for the summary .

Thanks everyone for the great discussion @cgerum @paulpb @philippvk @r.stahl @areusch @jroesch @mbs-octoml!

@areusch

Partitioning: UMA is using the standard TVM partitioner, registering patterns using the pattern-table infrastructure, and invoking the same 3 passes used elsewhere to partition. This is a reuse of existing infrastructure so no further discussion is needed here. Should UMA choose to use any different partitioning scheme, we would need to ensure we are agreed on how it marks the end result of partitioning on the IRModule (e.g. which attribute and how does that correspond to target, etc).

Correct! Sounds good!

@areusch

Codegen: UMA would like to provide a wrapper class which affords users the ability to implement a TIR-to-runtime Hook (NOTE: RFC’d but not yet landed in the codebase cc @Mousius) for their target. @MJKlaiber let me know if this is not correct, but I think the overlap is pretty close to my understanding here.

This seems to be already in main:

Implementation of relay_to_tir target hook

@areusch

These last two bits are a bit complex and may be better discussed in a high-bandwidth setting. I’ll organize a community meeting so we can discuss them in an open forum sometime in the next few weeks.

We agree. Let’s discuss point 2 and 3 in the next community meeting.

CC @cgerum @paulpb @Mousius @jroesch @mbs-octoml @aca88 @SebastianBoblestETAS