-
Sub-task
-
Resolution: Fixed
-
P4
-
25
-
b19
-
x86_64
-
generic
1. C2 compiler New Vector IR creation.
2. Auto-vectorization support.
3. x86 backend implimentation.
4. Add IR verification tests for each newly supported vector operation.
- relates to
-
JDK-8356537 TestFloat16VectorOperations wastes CPU time
-
- Closed
-
-
JDK-8345298 RISC-V: Add riscv backend for Float16 operations - scalar
-
- Resolved
-
-
JDK-8350960 RISC-V: Add riscv backend for Float16 operations - vectorization
-
- Resolved
-
-
JDK-8366845 C2 SuperWord: wrong VectorCast after VectorReinterpret with swapped src/dst type
-
- Resolved
-
-
JDK-8365967 C2 compiler support for HalffloatVector operations supported by auto-vectorization flow
-
- Open
-
- links to
-
Commit(master) openjdk/jdk/9a3f9997
-
Review(master) openjdk/jdk/22755