RFR: 8317976: Optimize SIMD sort for AMD Zen 4 [v2]

Mon Mar 17 17:33:07 UTC 2025

On Mon, 17 Mar 2025 17:26:04 GMT, Srinivas Vamsi Parasa <sparasa at openjdk.org> wrote:

>> The above condition will hold for all AMD processors. Only for Zen4, even though AVX512 is supported, we want to pick AVX2 version of SIMD sort (due to the regression) which is handled by the code below:
>> 
>> snprintf(ebuf_, sizeof(ebuf_), **VM_Version::supports_avx512_simd_sort()** ? "avx512_sort" : "avx2_sort");
>
> Thanks for the clarification!

Also, please update the PR description summarizing the main high-level changes in this PR. Will make it easy for others.

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

PR Review Comment: https://git.openjdk.org/jdk/pull/24053#discussion_r1999302156