On Mon, Dec 1, 2025 at 9:54 AM Zack Rusin <[email protected]> wrote:
>
> Did lowering the VMW_RES_HT_ORDER affect any of the benchmarks? e.g.
> unigine heaven or valley ?
>
> z

The size was a hold over from when this was an open hash map, we
didn't change it when we moved to the node based kernel
implementation. I didn't notice any performance changes in GLmark or
Supertuxkart. This is the largest value that can be stored on the
stack without hitting the stackframe size compiler warning/error.

Attachment: smime.p7s
Description: S/MIME Cryptographic Signature

Reply via email to