Java primitive arrays with non-native ByteOrder?

[Rado Smogura]

Hi,


I hope you have a good day.


Strcitfp math is going to be only one supported 
https://openjdk.java.net/jeps/306.


BR,

Rado

On 14.08.2021 11:08, Uwe Schindler wrote:
> Hi,
>
> Other question: is it possible to load wrong IEEE-754 bytes with Float#intBitsToFloat() ? If this works, i see no problems with MemoryAccess, too.
>
> Uwe
>
> Am 14. August 2021 09:03:26 UTC schrieb Uwe Schindler <uschindler at apache.org>:
>> Hi,
>>
>> You can try it out and see what happens. From Lucene's point of view i already copied data from a mapped file using MemoryAccess (previously MemoryCopy) with wrong byte order into a float array. Nothing crashed, just bullshit came out.
>>
>> You may possibly create exceptions on StrictMath methods or strictfp, but we don't use that.
>>
>> Uwe
>>
>> Am 14. August 2021 04:38:57 UTC schrieb leerho <leerho at gmail.com>:
>>> All,
>>>
>>> Can anyone think of cases where it would be desirable to load a Java
>>> primitive array with non-native byte order values?  Assume that all reading
>>> and writing to such an array by the user would always use the non-native
>>> byte order.
>>>
>>> The integral types should always be valid, but doubles and floats could
>>> become illegal IEEE 754 bit layouts if something in the JVM were to examine
>>> them.  Assume that the user would not use any of the built-in static
>>> methods like isNaN(double), etc.
>>>
>>> Would this cause any problems in the JVM?
>>>
>>> Has anyone done this?
>>>
>>> Cheers,
>>>
>>> Lee.