On Fri, 17 Apr 2026 19:14:15 GMT, Vladimir Ivanov <[email protected]> wrote:

>> Hi @iwanowww 
>> This pull request performs partial intrinsification of slice API and if it 
>> does not succeed then we attempt inlining vector API based fallback 
>> implementation. moving compiler side change into a new PR will also involve 
>> factoring out Java side changes related to slice.
>> 
>> I agree with you that existing handling in 
>> `CallGenerator::do_late_inline_helper` is somewhat messy, I have cleaned up 
>> the handling for populating _vector_late_lines in the latest patch. Request 
>> your to kindly have a re-look at the change and let me know if this looks 
>> fine now.
>> 
>> Best Regards
>
> I propose to fix the handling of vector operation intrinsification failure 
> first. Then vector slice intrinsic implementation can follow.  
> 
> It's not specific to vector slice and all vector intrinsics are susceptible 
> to the very same problem: when intrinsification fails, fallback 
> implementation is not inlined.

Hi @iwanowww , As suggested I have created a new pull request 
https://github.com/openjdk/jdk/pull/30876 for inlining on intrinsic failure.

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

PR Review Comment: https://git.openjdk.org/jdk/pull/24104#discussion_r3123110656

Reply via email to