On Tue, 5 Aug 2025 11:39:43 GMT, Galder Zamarreño <[email protected]> wrote:
>> I've added support to vectorize `MoveD2L`, `MoveL2D`, `MoveF2I` and
>> `MoveI2F` nodes. The implementation follows a similar pattern to what is
>> done with conversion (`Conv*`) nodes. The tests in
>> `TestCompatibleUseDefTypeSize` have been updated with the new expectations.
>>
>> Also added a JMH benchmark which measures throughput (the higher the number
>> the better) for methods that exercise these nodes. On darwin/aarch64 it
>> shows:
>>
>>
>> Benchmark (seed) (size) Mode Cnt
>> Base Patch Units Diff
>> VectorBitConversion.doubleToLongBits 0 2048 thrpt 8
>> 1168.782 1157.717 ops/ms -1%
>> VectorBitConversion.doubleToRawLongBits 0 2048 thrpt 8
>> 3999.387 7353.936 ops/ms +83%
>> VectorBitConversion.floatToIntBits 0 2048 thrpt 8
>> 1200.338 1188.206 ops/ms -1%
>> VectorBitConversion.floatToRawIntBits 0 2048 thrpt 8
>> 4058.248 14792.474 ops/ms +264%
>> VectorBitConversion.intBitsToFloat 0 2048 thrpt 8
>> 3050.313 14984.246 ops/ms +391%
>> VectorBitConversion.longBitsToDouble 0 2048 thrpt 8
>> 3022.691 7379.360 ops/ms +144%
>>
>>
>> The improvements observed are a result of vectorization. The lack of
>> vectorization in `doubleToLongBits` and `floatToIntBits` demonstrates that
>> these changes do not affect their performance. These methods do not
>> vectorize because of flow control.
>>
>> I've run the tier1-3 tests on linux/aarch64 and didn't observe any
>> regressions.
>
> Galder Zamarreño has updated the pull request incrementally with one
> additional commit since the last revision:
>
> Check at the very least that auto vectorization is supported
src/hotspot/share/opto/superword.cpp line 1635:
> 1633: } else if (VectorNode::is_convert_opcode(opc)) {
> 1634: retValue = VectorCastNode::implemented(opc, size,
> velt_basic_type(p0->in(1)), velt_basic_type(p0));
> 1635: } else if (VectorNode::is_reinterpret_opcode(opc)) {
How does this affect `Op_ReinterpretHF2S` that is also in
`VectorNode::is_reinterpret_opcode`?
I'm afraid that we need to test this with hardware or Intel's SDE, to make sure
we have it running on a VM that actually supports Float16. Otherwise these
instructions may not be used, and hence not tested right.
@galderz Can you run the relevant tests?
-------------
PR Review Comment: https://git.openjdk.org/jdk/pull/26457#discussion_r2265119804
