[vectorIntrinsics] RFR: 8254826: Add reduction nodes implementation for Arm SVE [v2]

[Ningsheng Jian]

On Wed, 21 Oct 2020 11:52:36 GMT, Dongbo He <dongbohe at openjdk.org> wrote:

>> Contributed-by: <wanghuang3 at huawei.com>, <hexuejin2 at huawei.com>
>> 
>> Add reduction nodes support for Arm SVE. Add the backend codegen for nodes like "AndReductionVNode" "OrReductionVNode" "XorReductionVNode" "MaxReductionVNode" "MinReductionVNode" .
>
> Dongbo He has updated the pull request incrementally with one additional commit since the last revision:
> 
>   fix style problems

src/hotspot/cpu/aarch64/aarch64_sve.ad line 1348:

> 1346:   predicate(UseSVE > 0 && n->in(2)->bottom_type()->is_vect()->length_in_bytes() >= 16 &&
> 1347:             (n->in(2)->bottom_type()->is_vect()->element_basic_type() == T_SHORT ||
> 1348:             (n->in(2)->bottom_type()->is_vect()->element_basic_type() == T_CHAR)));

As Andrew said in my patch review, does it make sense to have T_CHAR here: https://github.com/openjdk/jdk/pull/726#discussion_r507726726?

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

PR: https://git.openjdk.java.net/panama-vector/pull/13