User model stacking: current status

[Brian Goetz]

Yes, Doug posted some data a while back about sorting, where the 
breakeven between sorting references and taking the indirection hit and 
sorting values and taking the "more memory movement" hit was not 
obvious. Flattening means ... flattening.  Sometimes it means faster, 
but sometimes not.  This is yet another reason why we should focus on 
providing semantic knobs, not "performance-labeled" knobs.

On 5/9/2022 1:34 PM, Remi Forax wrote:
> There is also something we should talk, using non-atomic value classes 
> does not mean automatically better performance.
> It's something i've discovered trying to implement HashMap (more 
> Map.of() in fact) using value classes.
> Updating a value class in the heap requires more writes, more memory 
> traffic than just updating pointers so depending on the algorithm, you 
> may see performance degradation compared to a pointer based 
> implementation.
>
> So even if we provide non-atomic B3, performance can be worst than 
> using atomic B3, sadly gaining more flatness does not necessarily 
> translate into better performance.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.openjdk.java.net/pipermail/valhalla-spec-experts/attachments/20220509/db60ba13/attachment.htm>