[TIR] Support affine expressions as indices in reverse compute inline #11317
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
requested review from
junrushao,
masahi,
spectrometerHBH and
tqchen
vinx13
force-pushed
the
feat/reverse-compute-inline-reshape
branch
2 times, most recently
from
5186f7c to
8fa122d
Compare
vinx13
force-pushed
the
feat/reverse-compute-inline-reshape
branch
from
8fa122d to
7b5a2d6
Compare
shtinsa
pushed a commit
to Deelvin/tvm
that referenced
this pull request
May 17, 2022
…apache#11317) * [TIR] Support affine expressions as indices in reverse compute inline * fix trivial iterators
shingjan
pushed a commit
to shingjan/tvm
that referenced
this pull request
May 17, 2022
…apache#11317) * [TIR] Support affine expressions as indices in reverse compute inline * fix trivial iterators
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
ReverseComputeInline requires the consumer body to be
B[...] = g(i, j, k, A[f(i, j, k, ...)] ...), previouslyfcan only be a permutation function over variablei, j, k, .... This PR allows f to be a bijective affine function.After
ReverseComputeInline,f^-1will be applied the LHS buffer store indices in the producer site, to find the corresponding buffer store location in the consumer site.This allows reshape operation to be inlined.
cc @junrushao1994 @spectrometerHBH @masahi @tqchen @tqchen