On Fri, 1 May 2026 16:31:38 GMT, Vladimir Kozlov <[email protected]> wrote:

> It could be only performance issue. But we need to test it.

I am not sure I understand how this can only be a perf issue. If the 
instruction encoding is not valid on a platform, it would result in crash, 
right?

> Will it be easier if we record CPU vendor (Intel, AMD, ZX) and don't allow 
> mismatch? Then you don't need to worry about flags settings based on vendor.

Yeah we can do that. But it makes the code cache vendor specific which would 
further reduces the portability.

> For portability we will have to disable address nops >= 12.

I think this makes sense. Its a good trade-off. We get to keep aot code cache 
portable across vendors (provided we don't come across more such issues) 
without sacrificing too much perf.

-------------

PR Comment: https://git.openjdk.org/jdk/pull/30778#issuecomment-4361021441

Reply via email to