This came up in:
https://mail.openjdk.org/pipermail/panama-dev/2024-March/020327.html

"But then why does this one:

    public void scalarSegmentArray(Data state) {
        final MemorySegment input = state.inputSegment;
        final double[] output = state.outputArray;
        for(int i = 0; i < SIZE; i++) {
            output[i] += input.getAtIndex(JAVA_DOUBLE, i);
        }
    }

not vectorize? input and output can't overlap because one is off heap
and the other is on heap. It seems for doubles the MemorySegment API
reads a double in 2 steps: use getLongUnaligned() and then convert the
result to double with Double.longBitsToDouble(). The vectorizer doesn't
support vectorization of that long to double move."

"MemorySegment reads double in the same way as other (pre-existing)
VarHandles - e.g. as longs which are then converted to doubles (w/o
using Unsafe::getDouble directly)."

"I prefer to see vectorizer handling "MoveX2Y (LoadX mem)"
=> "VectorReinterpret (LoadVector mem)" well and then introduce rules to
strength-reduce it to mismatched access."