RFR: 8274242: Implement fast-path for ASCII-compatible CharsetEncoders on x86 [v6]

[Claes Redestad]

On Mon, 27 Sep 2021 12:27:32 GMT, Tobias Hartmann <thartmann at openjdk.org> wrote:

>>> Should we remove the "iso" part from the method/class names?
>> 
>> I'm open to suggestions, but I've not been able to think of anything better. `encodeISOOrASCII` doesn't seem helpful and since ASCII is a subset of the ISO-8859-1 encoding referred to by the "iso" moniker then the ASCII-only variant is technically encoding chars to valid ISO-8859-1.
>
>> > Should we remove the "iso" part from the method/class names?
>> 
>> I'm open to suggestions, but I've not been able to think of anything better. `encodeISOOrASCII` doesn't seem helpful and since ASCII is a subset of the ISO-8859-1 encoding referred to by the "iso" moniker then the ASCII-only variant is technically encoding chars to valid ISO-8859-1.
> 
> Okay, that's fine with me.

Thanks for reviewing, @TobiHartmann 

I also cleaned up the test and made sure it fails when there's a logic bug like the one I introduced in 9800a99 where the ISO array intrinsic would be matched for a case requiring the ASCII-only array intrinsic. The test was (in)conveniently never testing out-of-range characters in the 0x80-0xFF range, which is precisely where the two intrinsics would produce different results. I hope this doesn't require another 24 hour grace period. ��

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

PR: https://git.openjdk.java.net/jdk/pull/5621