RFR: 8353786: Migrate Vector API math library support to FFM API [v5]

[Paul Sandoz]

On Fri, 11 Apr 2025 21:23:52 GMT, Vladimir Ivanov <vlivanov at openjdk.org> wrote:

>> Migrate Vector API math library (SVML and SLEEF) linkage from native code (in JVM) to Java FFM API.
>> 
>> Since FFM API doesn't support vector calling conventions yet, migration affects only symbol lookup for now. But it still enables significant simplifications on JVM side.
>> 
>> The patch consists of the following parts:
>>   * on-demand symbol lookup in Java code replaces eager lookup from native code during JVM startup;
>>   * 2 new VM intrinsics for vector calls (support unary and binary shapes) (code separated from unary/binary vector operations);
>>   * new internal interface to query supported CPU ISA extensions (`jdk.incubator.vector.CPUFeatures`) used for CPU dispatching.
>> 
>> `java.lang.foreign` API is used to perform symbol lookup in vector math library, then the address is cached and fed into corresponding JVM intrinsic, so C2 can turn it into a direct vector call in generated code.
>> 
>> Once `java.lang.foreign` supports vectors & vector calling conventions, VM intrinsics can go away. 
>> 
>> Performance is on par with original implementation (tested with microbenchmarks on linux-x64 and macosx-aarch64).
>> 
>> Testing: hs-tier1 - hs-tier6, microbenchmarks (on linux-x64 and macosx-aarch64)
>> 
>> Thanks!
>
> Vladimir Ivanov 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 19 additional commits since the last revision:
> 
>  - Merge branch 'master' into vector.math.01.java
>  - RVV and SVE adjustments
>  - Merge branch 'master' into vector.math.01.java
>  - Fix windows-aarch64 build failure
>  - features_string -> cpu_info_string
>  - Reviews and Float64Vector-related fix
>  - Misc fixes and cleanups
>  - CPU features support
>  - Cleanup
>  - TODO list
>  - ... and 9 more: https://git.openjdk.org/jdk/compare/cf1ff745...0ffed12f

src/hotspot/share/opto/vectorIntrinsics.cpp line 488:

> 486: // V binaryOp(long address, Class<? extends V> vClass, Class<E> elementType, int length,
> 487: //            V v1, V v2,
> 488: //            BinaryOperation<V, ?> defaultImpl)

`debugName` parameter is missing

src/hotspot/share/opto/vectorIntrinsics.cpp line 555:

> 553: 
> 554:   const char* debug_name = "<unknown>";
> 555:   const TypeInstPtr* debug_name_oop = gvn().type(argument(8))->isa_instptr();

Should that be:

  const TypeInstPtr* debug_name_oop = gvn().type(argument(6 + arity))->isa_instptr();

?
Placing the `debugName` parameter before the vector parameters makes it easier to reason about IMO.

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

PR Review Comment: https://git.openjdk.org/jdk/pull/24462#discussion_r2045762528
PR Review Comment: https://git.openjdk.org/jdk/pull/24462#discussion_r2045767847