On Fri, 26 Sep 2025 22:13:00 GMT, Chen Liang <[email protected]> wrote:

> Hotspot profiles by bytecode; as a result, some shared methods become 
> polluted and suffer in type profiling, as described in depth in [this 
> essay](https://cr.openjdk.org/~jrose/jvm/equals-profile.html) by John Rose. 
> The record methods generated by `ObjectMethods::bootstrap` just proved itself 
> another victim in this RFE.
> 
> To bypass this issue, I naively generated distinct bytecode to allow distinct 
> profiles for now. If hotspot adds any kind of split profiles exposed via 
> internal APIs, we can migrate to such split profile and throw away these 
> extra copies of bytecode.
> 
> In particular, in a method handle tree, each leaf method handle seems not 
> separately profiled - for example, all DMH to Object.hashCode share the same 
> profile regardless of their position in a MH tree, making MH trees less 
> useful than explicitly rolled bytecode, unfortunately.
> 
> The attached benchmark should be a good demonstration of the effect of type 
> profiling.

This pull request has now been integrated.

Changeset: 43e036ba
Author:    Chen Liang <[email protected]>
URL:       
https://git.openjdk.org/jdk/commit/43e036ba89dc8a09129313705f61354463d2c266
Stats:     367 lines in 2 files changed: 317 ins; 18 del; 32 mod

8366424: Missing type profiling in generated Record Object methods

Reviewed-by: jvernee

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

PR: https://git.openjdk.org/jdk/pull/27533

Reply via email to