RFR: 8333890: Fatal error in auto-vectorizer with float16 kernel.

[Jatin Bhateja]

Hi,

This bug fix patch fixes an assertion failure seen while auto-vectorizing conversion chain involving float16 type.
Constraining the container type for ConvF2HF IR to short type upfront , as relying on backpropagating narrow
type from memory operation  may not be sufficient if IR is succeeded by ConvHF2F as depicted by the include test case.

Best Regards,
Jatin

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

Commit messages:
 - Spell fix
 - 8333890: Fatal error in auto-vectorizer with float16 kernel.

Changes: https://git.openjdk.org/jdk/pull/20062/files
  Webrev: https://webrevs.openjdk.org/?repo=jdk&pr=20062&range=00
  Issue: https://bugs.openjdk.org/browse/JDK-8333890
  Stats: 71 lines in 2 files changed: 71 ins; 0 del; 0 mod
  Patch: https://git.openjdk.org/jdk/pull/20062.diff
  Fetch: git fetch https://git.openjdk.org/jdk.git pull/20062/head:pull/20062

PR: https://git.openjdk.org/jdk/pull/20062