RFR: 8346664: C2: Optimize mask check with constant offset [v12]

Emanuel Peter epeter at openjdk.org
Fri Jan 31 06:19:49 UTC 2025


On Thu, 30 Jan 2025 18:14:21 GMT, Matthias Ernst <duke at openjdk.org> wrote:

>> Fixes [JDK-8346664](https://bugs.openjdk.org/browse/JDK-8346664): extends the optimization of masked sums introduced in #6697 to cover constant values, which currently break the optimization.
>> 
>> Such constant values arise in an expression of the following form, for example from `MemorySegmentImpl#isAlignedForElement`:
>> 
>> 
>> (base + (index + 1) << 8) & 255
>> => MulNode
>> (base + (index << 8 + 256)) & 255
>> => AddNode
>> ((base + index << 8) + 256) & 255
>> 
>> 
>> Currently, `256` is not being recognized as a shifted value. This PR enables further reduction:
>> 
>> 
>> ((base + index << 8) + 256) & 255
>> => MulNode (this PR)
>> (base + index << 8) & 255
>> => MulNode (PR #6697)
>> base & 255 (loop invariant)
>> 
>> 
>> Implementation notes:
>> * I verified that the originating issue "scaled varhandle indexed with i+1"  (https://mail.openjdk.org/pipermail/panama-dev/2024-December/020835.html) is resolved with this PR.
>> * ~in order to stay with the flow of the current implementation, I refrained from solving general (const & mask)==0 cases, but only those where const == _ << shift.~
>> * ~I modified existing test cases adding/subtracting from the index var (which would fail with current C2). Let me know if would like to see separate cases for these.~
>
> Matthias Ernst has updated the pull request incrementally with one additional commit since the last revision:
> 
>   "should never vectorize" only holds for long[] input.

test/hotspot/jtreg/compiler/vectorization/TestPopulateIndex.java line 117:

> 115: 
> 116:     @Test
> 117:     // Currently disabled due to sum-under-mask optimization.

Suggestion:

    // Does not vectorize: due to sum-under-mask optimization.
    // (i+0) & 7, (i+1) & 7 ... (i+8) & 7 ....  -> PopulateIndex
    // becomes
    // (i+0) & 7, (i+1) & 7 ... (i+0) & 7 .... -> pattern broken

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

PR Review Comment: https://git.openjdk.org/jdk/pull/22856#discussion_r1936734215


More information about the hotspot-compiler-dev mailing list