[master] RFR: Load narrowKlass from header, AArch64 assembler implementation [v3]

[Andrew Haley]

On Fri, 28 Jan 2022 10:01:51 GMT, Roman Kennke <rkennke at openjdk.org> wrote:

>>> I believe that wouldn't work either. The fast path that is following this code requires that the upper 32 bits (the narrowKlass) of tmp remain intact: it shifts them to the right by 32bits and decodes the narrowKlass.
>> 
>> So what? tmp is untouched.
>
>> > I believe that wouldn't work either. The fast path that is following this code requires that the upper 32 bits (the narrowKlass) of tmp remain intact: it shifts them to the right by 32bits and decodes the narrowKlass.
>> 
>> So what? tmp is untouched.
> 
> We don't guarantee that tmp != dst. We only guarantee that tmp != src to avoid clobbering src.

OK, I give up. Please document 'clobbers flags' very clearly.

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

PR: https://git.openjdk.java.net/lilliput/pull/36