Questions around codeheaps, codeblobs and code locality

[Tobias Hartmann]

On 07.06.19 18:20, keita abdoul-kader wrote:
>     Those are nice improvements indeed. Do you expect the remaining work item to (cumulatively)
>     bring comparable gain ? Or have we reach the point of diminishing returns? 

It's hard to say but I'm afraid that the cost/complexity of the implementation overweights the
potential performance benefits.

>     Would you mind expanding on how you obtained the heat map on slide 13 and 19 of your
>     presentation ? I would like to reproduce those on our internal workloads.
I've simply added some code that prints the hotness value for every nmethod in the code cache at VM
exit and then plotted these values as heatmap with Plotly [1]. Unfortunately, I don't have the code
anymore.

Best regards,
Tobias

[1] https://plot.ly/python/