Loading...

XML

Word

Printable

Type: Enhancement
Resolution: Fixed
Priority: P4
Fix Version/s: 24
Affects Version/s: 24
Component/s: hotspot
Labels:
- c2
- vectorIntrinsics

Subcomponent:
compiler
Resolved In Build:
b26
CPU:

x86_64
OS:

generic

Optimizes LongVector multiplication by emitting VPMULUDQ instruction for following patterns.

       MulVL ( AndV SRC1, 0xFFFFFFFF) ( AndV SRC2, 0xFFFFFFFF)
       MulVL (URShiftVL SRC1 , 32) (URShiftVL SRC2, 32)
       MulVL (URShiftVL SRC1 , 32) ( AndV SRC2, 0xFFFFFFFF)
       MulVL ( AndV SRC1, 0xFFFFFFFF) (URShiftVL SRC2 , 32)
       MulVL (VectorCastI2X SRC1) (VectorCastI2X SRC2)
       MulVL (RShiftVL SRC1 , 32) (RShiftVL SRC2, 32)

relates to

JDK-8219881 [vector] Optimized 32-to-64 bit vectorized multiply

Open

JDK-8342662 C2: Add new phase for backend-specific lowering

Open

links to

Commit(master) openjdk/jdk/dc9a6ef6

Review(master) openjdk/jdk/21244

Assignee:: Jatin Bhateja

Reporter:: Jatin Bhateja

Votes:: 0 Vote for this issue

Watchers:: 5 Start watching this issue

Created:: 2024-09-28 09:09

Updated:: 2024-12-04 22:30

Resolved:: 2024-11-21 10:17

Details

Description

Attachments

Issue Links

Activity

People

Dates