On Mon, 28 Apr 2025 14:06:49 GMT, Emanuel Peter <epe...@openjdk.org> wrote:
>> erifan 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 four additional commits since
>> the last revision:
>>
>> - Addressed some review comments
>>
>> 1. Call VectorNode::Ideal() only once in XorVNode::Ideal.
>> 2. Improve code comments.
>> - Merge branch 'master' into JDK-8354242
>> - Merge branch 'master' into JDK-8354242
>> - 8354242: VectorAPI: combine vector not operation with compare
>>
>> This patch optimizes the following patterns:
>> For integer types:
>> ```
>> (XorV (VectorMaskCmp src1 src2 cond) (Replicate -1))
>> => (VectorMaskCmp src1 src2 ncond)
>> (XorVMask (VectorMaskCmp src1 src2 cond) (MaskAll m1))
>> => (VectorMaskCmp src1 src2 ncond)
>> ```
>> cond can be eq, ne, le, ge, lt, gt, ule, uge, ult and ugt, ncond is the
>> negative comparison of cond.
>>
>> For float and double types:
>> ```
>> (XorV (VectorMaskCast (VectorMaskCmp src1 src2 cond)) (Replicate -1))
>> => (VectorMaskCast (VectorMaskCmp src1 src2 ncond))
>> (XorVMask (VectorMaskCast (VectorMaskCmp src1 src2 cond)) (MaskAll m1))
>> => (VectorMaskCast (VectorMaskCmp src1 src2 ncond))
>> ```
>> cond can be eq or ne.
>>
>> Benchmarks on Nvidia Grace machine with 128-bit SVE2:
>> With option `-XX:UseSVE=2`:
>> ```
>> Benchmark Unit Before Score Error After
>> Score Error Uplift
>> testCompareEQMaskNotByte ops/s 7912127.225 2677.289518
>> 10266136.26 8955.008548 1.29
>> testCompareEQMaskNotDouble ops/s 884737.6799 446.963779
>> 1179760.772 448.031844 1.33
>> testCompareEQMaskNotFloat ops/s 1765045.787 682.332214
>> 2359520.803 896.305743 1.33
>> testCompareEQMaskNotInt ops/s 1787221.411 977.743935
>> 2353952.519 960.069976 1.31
>> testCompareEQMaskNotLong ops/s 895297.1974 673.44808
>> 1178449.02 323.804205 1.31
>> testCompareEQMaskNotShort ops/s 3339987.002 3415.2226
>> 4712761.965 2110.862053 1.41
>> testCompareGEMaskNotByte ops/s 7907615.16 4094.243652
>> 10251646.9 9486.699831 1.29
>> testCompareGEMaskNotInt ops/s 1683738.958 4233.813092
>> 2352855.205 1251.952546 1.39
>> testCompareGEMaskNotLong ops/s 854496.1561 8594.598885
>> 1177811.493 521.1229 1.37
>> testCompareGEMaskNotShort ops/s 3341860.309 1578.975338
>> 4714008.434 1681.10365 1.41
>> testCompareGTMaskNotByte ops/s 7910823.674 2993.367032
>> 10245063.58 9774.75138 1.29
>> testCompareGTMaskNotInt ops/s 1673393...
>
> test/hotspot/jtreg/compiler/vectorapi/VectorMaskCompareNotTest.java line 237:
>
>> 235: public static void testCompareEQMaskNotByte() {
>> 236: testCompareMaskNotByte(VectorOperators.EQ);
>> 237: }
>
> Another comment: you now only have "negative" tests, where you check for
> count `=0`. It would be good if you also had a positive rule here, one where
> you do see an XOR in a similar case, where your optimization does apply.
>
> This would basically be a "control" that checks that your are testing the
> right thing.
Also: this test should vectorize on some plarforms, right? A compare, correct?
Would it not be good to actively check that with an IR rule?
-------------
PR Review Comment: https://git.openjdk.org/jdk/pull/24674#discussion_r2063749337
