RFR: 8342095: Add autovectorizer support for subword vector casts [v5]
Jasmine Karthikeyan
jkarthikeyan at openjdk.org
Mon Feb 17 05:00:52 UTC 2025
> Hi all,
> This patch adds initial support for the autovectorizer to generate conversions between subword types. Currently, when superword sees two packs that have different basic types, it discards them and bails out of vectorization. This patch changes the behavior to ask the backend if a cast between the conflicting types is supported, and keeps the pack if it is. Later, when the `VTransform` graph is built, a synthetic cast is emitted when packs requiring casts are detected. Currently, only narrowing casts are supported as I wanted to re-use existing `VectorCastX2Y` logic for the initial version, but adding more conversions is simple and can be done with a subsequent RFE. I have attached a JMH benchmark and got these results on my Zen 3 machine:
>
>
> Baseline Patch
> Benchmark (SIZE) Mode Cnt Score Error Units Score Error Units Improvement
> VectorSubword.intToByte 1024 avgt 12 200.049 ± 19.787 ns/op 56.228 ± 3.535 ns/op (3.56x)
> VectorSubword.intToShort 1024 avgt 12 179.826 ± 1.539 ns/op 43.332 ± 1.166 ns/op (4.15x)
> VectorSubword.shortToByte 1024 avgt 12 245.580 ± 6.150 ns/op 29.757 ± 1.055 ns/op (8.25x)
>
>
> I've also added some IR tests and they pass on my linux x64 machine. Thoughts and reviews would be appreciated!
Jasmine Karthikeyan has updated the pull request incrementally with one additional commit since the last revision:
Address comments from review, refactor test
-------------
Changes:
- all: https://git.openjdk.org/jdk/pull/23413/files
- new: https://git.openjdk.org/jdk/pull/23413/files/6daa8ace..8920454d
Webrevs:
- full: https://webrevs.openjdk.org/?repo=jdk&pr=23413&range=04
- incr: https://webrevs.openjdk.org/?repo=jdk&pr=23413&range=03-04
Stats: 355 lines in 4 files changed: 89 ins; 263 del; 3 mod
Patch: https://git.openjdk.org/jdk/pull/23413.diff
Fetch: git fetch https://git.openjdk.org/jdk.git pull/23413/head:pull/23413
PR: https://git.openjdk.org/jdk/pull/23413
More information about the hotspot-compiler-dev
mailing list