RFR: 8260501: [Vector API] Improve register usage for shift operations on x86
Jie Fu
jiefu at openjdk.java.net
Wed Jan 27 11:56:47 UTC 2021
Hi all,
I found the register usage is less optimized for some shift operations.
For example, vshiftL_imm [1]/vshiftI_imm require dst != src.
But it's actually fine for the register allocator to assign dst == src.
Also, vshiftL [2]/vshiftI/vshiftS require dst != src.
But it's actually required for UseAVX==0 only.
For the most common cases (UseAVX > 0), it's fine to assign dst == src.
The fix splits vshiftS/vshiftI/vshiftL into UseAVX > 0 and UseAVX == 0 cases.
And just removes the unreasonable requirement for vshiftI_imm and vshiftL_imm.
Testing:
- jdk/incubator/vector/ on x64 with UseAVX=3/2/1/0, no regression
Thanks.
Best regards,
Jie
[1] https://github.com/openjdk/jdk/blob/master/src/hotspot/cpu/x86/x86.ad#L6058
[2] https://github.com/openjdk/jdk/blob/master/src/hotspot/cpu/x86/x86.ad#L6037
-------------
Commit messages:
- 8260501: [Vector API] Improve register usage for shift operations on x86
Changes: https://git.openjdk.java.net/jdk/pull/2257/files
Webrev: https://webrevs.openjdk.java.net/?repo=jdk&pr=2257&range=00
Issue: https://bugs.openjdk.java.net/browse/JDK-8260501
Stats: 86 lines in 1 file changed: 46 ins; 22 del; 18 mod
Patch: https://git.openjdk.java.net/jdk/pull/2257.diff
Fetch: git fetch https://git.openjdk.java.net/jdk pull/2257/head:pull/2257
PR: https://git.openjdk.java.net/jdk/pull/2257
More information about the hotspot-compiler-dev
mailing list