RFR: 8371571: Consolidate and enhance bulk memory segment ops benchmarks

[Emanuel Peter]

On Wed, 12 Nov 2025 14:05:29 GMT, Emanuel Peter <epeter at openjdk.org> wrote:

>> Yepp. The idea was to test the impact of alignment, as the hand-rolled version uses unaligned access, and the intrinsics might align its bulk operations.
>
> Ok. But what kind of guarantee do you think you are getting from the byte array? With Lilliput (and maybe without), it may only be a 4 byte alignment, it may actually be unaligned that way for your long accesses. Are you aware of that?

Alternatively, you could just use a long array, that way you get at least the same 8-byte alignment that you have with native memory.

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

PR Review Comment: https://git.openjdk.org/jdk/pull/28260#discussion_r2518446344