[vectorIntrinsics] RFR: 8266720: Wrong implementation in LibraryCallKit::inline_vector_shuffle_iota

[Sandhya Viswanathan]

On Wed, 12 May 2021 09:20:47 GMT, Wang Huang <whuang at openjdk.org> wrote:

> Because JDK-8266317 has not been merged into jdk/jdk. So I fix this bug here.
> * This comparsion should be a unsigned cmp
> *  `x86` is not wrong because `x86` does not have 1024-bits vl here. 
>   ```c++
> 
>     ConINode* pred_node = (ConINode*)gvn().makecon(TypeInt::make(BoolTest::ge)); // should BoolTest::ugt
>     Node * lane_cnt  = gvn().makecon(TypeInt::make(num_elem));
>     Node * bcast_lane_cnt = gvn().transform(VectorNode::scalar2vector(lane_cnt, num_elem, type_bt));
>     // should BoolTest::ugt
>     Node* mask = gvn().transform(new VectorMaskCmpNode(BoolTest::ge, bcast_lane_cnt, res, pred_node, vt));

src/hotspot/share/opto/vectorIntrinsics.cpp line 456:

> 454:     res = gvn().transform(VectorNode::make(Op_AndI, res, bcast_mod, num_elem, elem_bt));
> 455:   } else {
> 456:     ConINode* pred_node = (ConINode*)gvn().makecon(TypeInt::make(BoolTest::ugt));

Unsigned comparison adds overhead and is not supported on all architectures.

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

PR: https://git.openjdk.java.net/panama-vector/pull/81