RFR: 8350835: C2 SuperWord: assert/wrong result when using Float.float16ToFloat with byte instead of short input

[Sandhya Viswanathan]

Float.float16ToFloat generates wrong vectorized code in product build and asserts in fastdebug/debug when argument is of type byte, int, or long array. The short term solution is to not auto vectorize in these cases.

Review comments are welcome.

Best Regards,
Sandhya

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

Commit messages:
 - whitespace
 - some updates
 - 8350835: C2 SuperWord: assert/wrong result when using Float.float16ToFloat with byte instead of short input

Changes: https://git.openjdk.org/jdk/pull/23939/files
  Webrev: https://webrevs.openjdk.org/?repo=jdk&pr=23939&range=00
  Issue: https://bugs.openjdk.org/browse/JDK-8350835
  Stats: 137 lines in 2 files changed: 136 ins; 0 del; 1 mod
  Patch: https://git.openjdk.org/jdk/pull/23939.diff
  Fetch: git fetch https://git.openjdk.org/jdk.git pull/23939/head:pull/23939

PR: https://git.openjdk.org/jdk/pull/23939