Vector API doesn't define an order on reduction. The requires_strict_order flag was recently added as part of JDK-8320725 to identify if a reduction should be ordered or unordered. This flag could be used to implement efficient unordered reduction for vector api floating point add/mul on x86_64.
- relates to
-
JDK-8320725 AArch64: C2: Add "requires_strict_order" flag for floating-point add and mul reduction
-
- Resolved
-
- links to
-
Commit(master)
openjdk/jdk/dc35f3e8
-
Review(master)
openjdk/jdk/20306