RFR: 8291600: [vectorapi] vector cast op check is not always needed for vector mask cast

[Quan Anh Mai]

On Thu, 4 Aug 2022 06:08:44 GMT, Xiaohong Gong <xgong at openjdk.org> wrote:

> Recently we found the performance of "`FIRST_NONZERO`" for double type is largely worse than the other types on x86 when `UseAVX=2`. The main reason is the "`VectorCastL2X`" op is not supported by the backend when the dst element type is `T_DOUBLE`. This makes the check of `VectorCast` op fail before intrinsifying "`VectorMask.cast()`" which is used in the
> "`FIRST_NONZERO`" java implementation (see [1]). However, the compiler will not generate the `VectorCast `op for `VectorMask.cast()` if:
> 
>  1) the current platform supports the predicated feature
>  2) the element size (in bytes) of the src and dst type is the same
> 
> So the check of "`VectorCast`" op is needless for such cases. To fix it, this patch:
> 
>  1) limits the specified vector cast op check to vectors
>  2) adds the relative mask cast op check for VectorMask.cast()
>  3) cleans up the unnecessary codes
> 
> Here is the performance of "`FIRST_NONZERO`" benchmark [2] on a x86 machine with `UseAVX=2`:
> 
> Benchmark                          (size) Mode Cnt Before  After   Units
> DoubleMaxVector.FIRST_NONZERO       1024  thrpt 15 49.266 2460.886 ops/ms
> DoubleMaxVector.FIRST_NONZEROMasked 1024  thrpt 15 49.554 1892.223 ops/ms
> 
> [1] https://github.com/openjdk/jdk/blob/master/src/jdk.incubator.vector/share/classes/jdk/incubator/vector/DoubleVector.java#L770
> [2] https://github.com/openjdk/panama-vector/blob/vectorIntrinsics/test/micro/org/openjdk/bench/jdk/incubator/vector/operation/DoubleMaxVector.java#L246

Yes you are right, the code would be mostly the same, which means we can reuse the existing match rules to additionally match `VectorMaskCast` for those cases. For other cases, in particular, narrowing cast to subword types, since avx < 3 does not support truncation cast and only provides saturation cast instructions. We need to truncate the upper bits ourselves. For example, a cast from `int` to `byte` is done as follow

    vpand dst, src, [external address mask]
    vpackusdw dst, dst
    vpermq dst, dst, 0x08
    vpackuswb dst, dst

For vector mask cast, we can get rid of the first masking and use the `vpackss`s instead, which removes the need to reference memory. Thanks.

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

PR: https://git.openjdk.org/jdk/pull/9737