RFR: 8261492: Shenandoah: reconsider forwardee accesses memory ordering [v2]

[Aleksey Shipilev]

On 6/23/21 11:35 AM, Andrew Haley wrote:
> On 6/23/21 10:22 AM, Andrew Haley wrote:
>> On 2/15/21 2:06 PM, Andrew Haley wrote:
>>> On 15/02/2021 12:00, Martin Doerr wrote:
>>>> I'd prefer using load-consume with comment in assembly code and acquire in C++ code. That would be consistent with other code. But that's just my opinion. I'll leave the aarch64 maintainers free to decide.
>>>
>>> That sounds right to me too. One day we'll get memory_order_consume
>>> for HotSpot C++ code, but until then acquire will have to do.
>>
>> Sorry, I missed this. Is it just acquire and release you need?
> 
> Just to be clear: in a CAS you can have all 4 combinations: none,
> acq, rel, acq_rel. I don't want to populate all possibilities if they
> won't be used.

The only CAS in those patches uses memory_order_acq_rel.

-- 
Thanks,
-Aleksey