[vectorIntrinsics] RFR: 8343689: AArch64: Optimize MulReduction implementation

[Paul Sandoz]

On Tue, 14 Jan 2025 17:21:02 GMT, Mikhail Ablakatov <mablakatov at openjdk.org> wrote:

> Add a reduce_mul intrinsic SVE specialization for >= 256-bit long vectors. It multiplies halves of the source vector using SVE instructions to get to a 128-bit long vector that fits into a SIMD&FP register. After that point, existing ASIMD implementation is used.
> 
> Benchmarks results for an AArch64 CPU with support for SVE with 256-bit vector length:
> 
>   Benchmark                 (size)   Mode      Old        New  Units
>   Byte256Vector.MULLanes      1024  thrpt  502.498  10222.717 ops/ms
>   Double256Vector.MULLanes    1024  thrpt  172.116   3130.997 ops/ms
>   Float256Vector.MULLanes     1024  thrpt  291.612   4164.138 ops/ms
>   Int256Vector.MULLanes       1024  thrpt  362.276   3717.213 ops/ms
>   Long256Vector.MULLanes      1024  thrpt  184.826   2054.345 ops/ms
>   Short256Vector.MULLanes     1024  thrpt  379.231   5716.223 ops/ms
> 
> 
> Benchmarks results for an AArch64 CPU with support for SVE with 512-bit vector length:
> 
>   Benchmark                 (size)   Mode      Old       New   Units
>   Byte512Vector.MULLanes      1024  thrpt  160.129  2630.600  ops/ms
>   Double512Vector.MULLanes    1024  thrpt   51.229  1033.284  ops/ms
>   Float512Vector.MULLanes     1024  thrpt   84.617  1658.400  ops/ms
>   Int512Vector.MULLanes       1024  thrpt  109.419  1180.310  ops/ms
>   Long512Vector.MULLanes      1024  thrpt   69.036   704.144  ops/ms
>   Short512Vector.MULLanes     1024  thrpt  131.029  1629.632  ops/ms

I think it is OK to refer to the benchmarks in panama-vector (IIRC we may have done that before for other PRs to jdk).

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

PR Comment: https://git.openjdk.org/panama-vector/pull/225#issuecomment-2596147866