On Fri, 16 Oct 2026 16:05:26 GMT, Quan Anh Mai <[email protected]> wrote:
>> Hi All, >> >> Currently, >> [ReplHF_reg](https://github.com/openjdk/jdk/blob/master/src/hotspot/cpu/x86/x86.ad#L18646) >> selection pattern >> which accepts regF src operand, first copies it to a GPR using _evmovw_ >> instruction (which has 3 cycles latency on x86 targets supporting >> AVX512-FP16 feature) and then broadcast it using _vpbroadcastw_ instruction. >> >> On targets supporting AVX512BW feature this sequence can be replaced by a >> single _vpbroadcastw_ instruction which can directly broadcast XMM source >> thus saving costly XMM to GPR move. >> >> This shows 2-3% performance improvement on AVX512-FP16 systems for benchmark >> included with the patch. >> >> >> Baseline:- >> Benchmark Mode Cnt Score Error Units >> ReplHFRegBenchmark.manyBroadcasts thrpt 5 16.587 ± 0.041 ops/ms >> Withchange:- >> Benchmark Mode Cnt Score Error Units >> ReplHFRegBenchmark.manyBroadcasts thrpt 5 16.978 ± 0.033 ops/ms >> >> >> Kindly review and share your feedback. >> >> Best Regards, >> Jatin >> >> --------- >> - [x] I confirm that I make this contribution in accordance with the >> [OpenJDK Interim AI Policy](https://openjdk.org/legal/ai). > > It is green now. Thanks @merykitty and @sviswa7 for approvals. ------------- PR Comment: https://git.openjdk.org/jdk/pull/32938#issuecomment-6260566819
