RFR: 8332163: C2 SuperWord: refactor PacksetGraph and SuperWord::output into VTransformGraph [v15]
Emanuel Peter
epeter at openjdk.org
Thu Jul 4 10:35:45 UTC 2024
> The original PR was [here](https://github.com/openjdk/jdk/pull/19261), it got too chaotic.
>
> I added some extra tests for this in: https://github.com/openjdk/jdk/pull/19558
> I extracted some refactorings to: https://github.com/openjdk/jdk/pull/19573
>
> We used to have:
> - `PacksetGraph`: this detects cycles introduces by packs, and schedules/reorders the memops.
> - `SuperWord::apply_vectorization`: creates `VectorNodes` directly from the `PackSet`.
>
> In my blog, I have published lots of ideas for SuperWord / AutoVectorization improvements:
> https://eme64.github.io/blog/2023/11/03/C2-AutoVectorizer-Improvement-Ideas.html
>
> Many ideas are based on the "VectorTransform IR": cost-model, if-conversion, direct widening of scalars to vectors, additional optimizations/features with shuffle/pack/extract, handling more reduction patterns, etc.
>
> I now decided to name it `VTransform`, which is essencially a graph `VtransformGraph` of nodes `VTransformNodes` that resemble the C2 Node on purpose, because the `VTransform` models the C2 graph after vectorization. We can now model the transformation from scalar-loop to vectorized-loop without modifying the C2 graph yet.
>
> The new code has these steps:
> - Given the `PackSet` from `SuperWord`, we create a `VTransformGraph` with `SuperWordVTransformBuilder`.
> - [Not yet: all sorts of optimizations / checks on the `VTransformGraph`, in future RFE's]
> - We then schedule the `VTransformGraph`, and check for cycles.
> - Once we are ready to commit to vectorization, we call `VTransformGraph::apply_vectorization` which lets each individual `VTransformNode::apply` generate the new vectorized C2 nodes.
>
> **Testing**
>
> Regression testing passed.
>
> Performance testing: no significant change in performance (as expected).
Emanuel Peter has updated the pull request with a new target base due to a merge or a rebase. The incremental webrev excludes the unrelated changes brought in by the merge/rebase. The pull request contains 17 additional commits since the last revision:
- Merge branch 'master' into JDK-8332163-VTransformGraph-v2
- More updates for Christian
- Apply suggestions from code review
Co-authored-by: Christian Hagedorn <christian.hagedorn at oracle.com>
- Apply suggestions from code review
Co-authored-by: Christian Hagedorn <christian.hagedorn at oracle.com>
- rm newline
- tabs and includes
- vtransform comments
- move some code over to graph
- VTransformTrace
- split graph out from VTransform, wip
- ... and 7 more: https://git.openjdk.org/jdk/compare/e6460909...18f95141
-------------
Changes:
- all: https://git.openjdk.org/jdk/pull/19719/files
- new: https://git.openjdk.org/jdk/pull/19719/files/c813a989..18f95141
Webrevs:
- full: https://webrevs.openjdk.org/?repo=jdk&pr=19719&range=14
- incr: https://webrevs.openjdk.org/?repo=jdk&pr=19719&range=13-14
Stats: 38238 lines in 902 files changed: 25674 ins; 8412 del; 4152 mod
Patch: https://git.openjdk.org/jdk/pull/19719.diff
Fetch: git fetch https://git.openjdk.org/jdk.git pull/19719/head:pull/19719
PR: https://git.openjdk.org/jdk/pull/19719
More information about the hotspot-compiler-dev
mailing list