RFR: 8302673: [SuperWord] MaxReduction and MinReduction should vectorize for int [v2]

[Emanuel Peter]

On Wed, 31 May 2023 07:14:18 GMT, Roberto Castañeda Lozano <rcastanedalo at openjdk.org> wrote:

>> The canonicalization of MinI/MaxI chains into right-spline graphs within `MinINode/MaxINode::Ideal()` inhibits the vectorization of reductions of these nodes. This changeset reworks `MinINode/MaxINode::Ideal()` to perform the same algebraic optimizations without the need for canonicalization, re-enabling auto-vectorization of MinI/MaxI reductions. This is achieved by handling all four permutations of the targeted Ideal subgraph induced by the commutativity of MinI/MaxI directly. The algorithm (for the MaxI case, the MinI case is analogous) tries to apply two Ideal graph rewrites in the following order, where `c0` and `c1` are constants and `MAX` is a compile-time operation:
>> 1. `max(x + c0, max(x + c1, z))` (or a permutation of it) to `max(x + MAX(c0, c1), z)`.
>> 2. `max(x + c0, x + c1)` (or a permutation of it) to `x + MAX(c0, c1)`.
>> 
>> Here is an example of the four permutations handled in step 1 with `x = RShiftI`, `c0 = 100` or `150`, `c1 = 150` or `100`, and `z = ConI (#int:200)`:
>> 
>> ![two-level-idealization](https://github.com/openjdk/jdk/assets/8792647/bf60a2c3-39cd-4f0d-965d-c711723e374c)
>> 
>> Here is an example of the two permutations handled in step 2 with `x = RShiftI`, `c0 = 10` or `11`, and `c1 = 11` or `10`:
>> 
>> ![one-level-idealization](https://github.com/openjdk/jdk/assets/8792647/0a1fe85b-3f30-46bc-8817-d90b3eff946c)
>> 
>> The changeset implements `MinINode/MaxINode::Ideal()` in a common method `MaxNode::IdealI()`, since the algorithm is symmetric for both node types. The changeset also extends the existing MinI/MaxI Idealization tests with positive tests for all targeted permutations and negative tests, and adds a new test (contributed by @jbhateja) to assert that MinI/MaxI reductions are vectorized.
>> 
>> #### Testing
>> 
>> ##### Functionality
>> 
>> - tier1-5, stress test, fuzzing (windows-x64, linux-x64, linux-aarch64, macosx-x64, macosx-aarch64; release and debug mode).
>> 
>> ##### Performance
>> 
>> - Tested performance on a set of standard benchmark suites (DaCapo, SPECjbb2015, SPECjvm2008). No significant change was observed.
>
> Roberto Castañeda Lozano 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 22 additional commits since the last revision:
> 
>  - Merge branch 'master' into JDK-8302673
>  - Defer op(x, x) to constant/identity propagation early
>  - Merge branch 'master' into JDK-8302673
>  - Refactor idealization and extracted Identity transformation for clarity
>  - Make auxiliary add operand extraction function return a tuple
>  - Randomize array values in min/max test computation
>  - Merge branch 'master' into JDK-8302673
>  - Merge branch 'master' into JDK-8302673
>  - Refine comments
>  - Update copyright header
>  - ... and 12 more: https://git.openjdk.org/jdk/compare/ec8ac687...a6db3cc4

src/hotspot/share/opto/addnode.cpp line 1182:

> 1180:       jint inner_off = inner_add_operands.second;
> 1181:       // Try to extract the inner add.
> 1182:       Node* add_extracted = extract_add(phase, inner, inner_off, outer, outer_off);

Optional: You could also leave `outer_add_operands` and `inner_add_operands` packed in the `Pair`, and pass it as such into `extract_add`. Could reduce the number of lines a bit here.

-------------

PR Review Comment: https://git.openjdk.org/jdk/pull/13924#discussion_r1211516982