On Mon, 16 Sep 2024 02:58:41 GMT, Jatin Bhateja <[email protected]> wrote:
>> Hi All,
>>
>> As per the discussion on panama-dev mailing list[1], patch adds the support
>> for following new two vector permutation APIs.
>>
>>
>> Declaration:-
>> Vector<E>.selectFrom(Vector<E> v1, Vector<E> v2)
>>
>>
>> Semantics:-
>> Using index values stored in the lanes of "this" vector, assemble the
>> values stored in first (v1) and second (v2) vector arguments. Thus, first
>> and second vector serves as a table, whose elements are selected based on
>> index value vector. API is applicable to all integral and floating-point
>> types. The result of this operation is semantically equivalent to
>> expression v1.rearrange(this.toShuffle(), v2). Values held in index vector
>> lanes must lie within valid two vector index range [0, 2*VLEN) else an
>> IndexOutOfBoundException is thrown.
>>
>> Summary of changes:
>> - Java side implementation of new selectFrom API.
>> - C2 compiler IR and inline expander changes.
>> - In absence of direct two vector permutation instruction in target ISA, a
>> lowering transformation dismantles new IR into constituent IR supported by
>> target platforms.
>> - Optimized x86 backend implementation for AVX512 and legacy target.
>> - Function tests covering new API.
>>
>> JMH micro included with this patch shows around 10-15x gain over existing
>> rearrange API :-
>> Test System: Intel(R) Xeon(R) Platinum 8480+ [ Sapphire Rapids Server]
>>
>>
>> Benchmark (size) Mode Cnt
>> Score Error Units
>> SelectFromBenchmark.rearrangeFromByteVector 1024 thrpt 2 2041.762
>> ops/ms
>> SelectFromBenchmark.rearrangeFromByteVector 2048 thrpt 2 1028.550
>> ops/ms
>> SelectFromBenchmark.rearrangeFromIntVector 1024 thrpt 2 962.605
>> ops/ms
>> SelectFromBenchmark.rearrangeFromIntVector 2048 thrpt 2 479.004
>> ops/ms
>> SelectFromBenchmark.rearrangeFromLongVector 1024 thrpt 2 359.758
>> ops/ms
>> SelectFromBenchmark.rearrangeFromLongVector 2048 thrpt 2 178.192
>> ops/ms
>> SelectFromBenchmark.rearrangeFromShortVector 1024 thrpt 2 1463.459
>> ops/ms
>> SelectFromBenchmark.rearrangeFromShortVector 2048 thrpt 2 727.556
>> ops/ms
>> SelectFromBenchmark.selectFromByteVector 1024 thrpt 2 33254.830
>> ops/ms
>> SelectFromBenchmark.selectFromByteVector 2048 thrpt 2 17313.174
>> ops/ms
>> SelectFromBenchmark.selectFromIntVector 1024 thrpt 2 10756.804
>> ops/ms
>> S...
>
> Jatin Bhateja has updated the pull request incrementally with one additional
> commit since the last revision:
>
> Disabling VectorLoadShuffle bypassing optimization to comply with rearrange
> semantics at IR level.
src/jdk.incubator.vector/share/classes/jdk/incubator/vector/X-Vector.java.template
line 561:
> 559: for (int i = 0; i < vlen; i++) {
> 560: int index = ((int)vecPayload1[i]);
> 561: res[i] = index >= vlen ? vecPayload3[index & (vlen - 1)] :
> vecPayload2[index];
This is incorrect as the index could be negative. You need to wrap in the range
`[0, 2 * vlen - 1]` before the comparison and selection.
int index = ((int)vecPayload1[i]) & ((vlen << 1) - 1));
res[i] = index < vlen ? vecPayload2[index] : vecPayload3[index - vlen];
src/jdk.incubator.vector/share/classes/jdk/incubator/vector/X-Vector.java.template
line 2974:
> 2972: final $abstractvectortype$ selectFromTemplate(Class<? extends
> Vector<$Boxbitstype$>> indexVecClass,
> 2973: $abstractvectortype$
> v1, $abstractvectortype$ v2) {
> 2974: int twoVectorLen = length() * 2;
We should assert that the length is a power of two.
-------------
PR Review Comment: https://git.openjdk.org/jdk/pull/20508#discussion_r1761663646
PR Review Comment: https://git.openjdk.org/jdk/pull/20508#discussion_r1761667602
