RFR: 8341781: Improve Min/Max node identities

[Jasmine Karthikeyan]

On Thu, 10 Oct 2024 05:57:09 GMT, Christian Hagedorn <chagedorn at openjdk.org> wrote:

>> Hi all,
>> This patch implements some missing identities for Min/Max nodes. It adds static type-based operand choosing for MinI/MaxI, such as the ones that MinL/MaxL use. In addition, it adds simplification for patterns such as `Max(A, Max(A, B))` to `Max(A, B)` and `Max(A, Min(A, B))` to `A`. These simplifications stem from the [lattice identity rules](https://en.wikipedia.org/wiki/Lattice_(order)#As_algebraic_structure). The main place I've seen this pattern is with MinL/MaxL nodes created during loop optimizations. Some examples of where this occurs include BigInteger addition/subtraction, and regex code. I've run some of the existing benchmarks and found some nice improvements:
>> 
>>                                                                 Baseline                    Patch
>> Benchmark                                 Mode  Cnt       Score       Error  Units    Score       Error  Units  Improvement
>> BigIntegers.testAdd                       avgt   15      25.096 ±     3.936  ns/op   19.214  ±    0.521  ns/op  (+ 26.5%)
>> PatternBench.charPatternCompile           avgt    8     453.727 ±   117.265  ns/op   370.054 ±   26.106  ns/op  (+ 20.3%)
>> PatternBench.charPatternMatch             avgt    8     917.604 ±   121.766  ns/op   810.560 ±   38.437  ns/op  (+ 12.3%)
>> PatternBench.charPatternMatchWithCompile  avgt    8    1477.703 ±   255.783  ns/op  1224.460 ±   28.220  ns/op  (+ 18.7%)
>> PatternBench.longStringGraphemeMatches    avgt    8     860.909 ±   124.661  ns/op   743.729 ±   22.877  ns/op  (+ 14.6%)
>> PatternBench.splitFlags                   avgt    8     420.506 ±    76.252  ns/op   321.911 ±   11.661  ns/op  (+ 26.6%)
>> 
>> I've added some IR tests, and tier 1 testing passes on my linux machine. Reviews would be appreciated!
>
> test/hotspot/jtreg/compiler/c2/irTests/TestMinMaxIdentities.java line 116:
> 
>> 114: 
>> 115:     @Test
>> 116:     @IR(applyIfPlatform = { "riscv64", "false" }, phase = { CompilePhase.BEFORE_MACRO_EXPANSION }, counts = { IRNode.MIN_L, "1" })
> 
> Can you add a comment here why we cannot apply the rules for riscv?

This is a good call, the IR rules don't apply to RISC-V because it doesn't have support for CMoves so the MinL/MaxL nodes aren't made at all. Since `Math.min/max(LL)` isn't intensified it first needs to be matched into CMove, then Min/Max, and then the identity needs to be called. Since #20098 implements the intrinsic we could remove the special casing after it's merged. I've added a comment to the source code as well.

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

PR Review Comment: https://git.openjdk.org/jdk/pull/21439#discussion_r1796408365