On Mon, 3 Aug 2026 05:52:53 GMT, Jatin Bhateja <[email protected]> wrote:
>> Patch optimizes Float16 to integral conversion operations. Currently, its a >> two step process where by first a Float16 value is >> converted to a single precision floating point value followed by a >> conversion to an integral value. >> >> x86 targets supporting AVX512-FP16 feature (Intel Sapphire Rapids+ and >> upcoming AMD Zen6) provides direct instruction to convert a Float16 value to >> integral value. >> >> Following are the performance numbers of micro benchmark included with the >> patch on Granite Rapids with and without auto-vectorization. >> >> <img width="1125" height="636" alt="image" >> src="https://github.com/user-attachments/assets/ca6e6757-1579-475f-8307-9454c7c025c1"; >> /> >> >> 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). > > Jatin Bhateja has updated the pull request with a new target base due to a > merge or a rebase. The incremental webrev excludes the unrelated changes > brought in by the merge/rebase. The pull request contains seven additional > commits since the last revision: > > - Merge branch 'master' of http://github.com/openjdk/jdk into JDK-8382523 > - Review comments resolution > - Review comments resolution > - Review comments resolution > - Review comments resolution > - Review comments resolution > - 8382523: Optimize Float16 to integral conversion operations for > AVX512-FP16 targets I ran the new tests and micros on machine that supports AVX512-FP16. All runs went through without issue. Once minor code updates are made, I'll add my approval to PR. src/hotspot/cpu/x86/assembler_x86.cpp line 2375: > 2373: } > 2374: > 2375: void Assembler::evcvttph2dq(XMMRegister dst, XMMRegister src, int > vector_len) { Please move evcvttph2dq and evcvttph2qq definitions to be just after vcvttps2dq definition. That way the two evcvttps2dqs definitions stay next to each other. src/hotspot/cpu/x86/assembler_x86.hpp line 1328: > 1326: void evcvttsd2sisq(Register dst, Address src); > 1327: > 1328: void evcvttsh2sil(Register dst, XMMRegister src); Please add a comment above these declarations that is similar to other ones (e.g., "//Convert with Truncation Scalar Half-Precision Floating-Point Value to Doubleword Integer"). ------------- Changes requested by missa (Author). PR Review: https://git.openjdk.org/jdk/pull/30928#pullrequestreview-4857832909 PR Review Comment: https://git.openjdk.org/jdk/pull/30928#discussion_r3715296357 PR Review Comment: https://git.openjdk.org/jdk/pull/30928#discussion_r3715269859
