[External] : Re: Object to ObjectMonitor mapping using a HashTable to avoid displaced headers

[Axel Boldt-Christmas]

Hi,

> Should we do the usual post a PR, get a review, integrate thing?

Sounds good to me.

> I don’t have an explanation, yet.

Looks like a good benchmark for looking at both the hash table max size and the deflation heuristics. They are probably both playing a role in the difference you are seeing.

> If you have anything that you want me to look at, let me know. I’ll keep looking around and use the problem as a vehicle to familiarize myself with OMWorld.

I will try to get a task list out sometime next week. Not sure where to put it. Could just keep it in the omworld-jdk PR. And keep the OMWorld related discussions, development and results there.

And use the omworld PR  for results and development from testing specifically with CompactObjectHeaders.

Sincerely
// Axel

On 22 Feb 2024, at 15:16, Kennke, Roman <rkennke at amazon.de> wrote:

Renaissance’s philosophers

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.openjdk.org/pipermail/lilliput-dev/attachments/20240223/ba2b818c/attachment-0001.htm>