Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw src/cpu/ppc/vm/assembler_ppc.hpp

rev 13389 : PPC: Implement MulAdd and SquareToLen intrinsics

This implementation is based on the algorithm implemented in java. It
yields a performance speedup of:
JDK8 - 23%
JDK9 - 5%
JDK10 - 5%

1 line changed: 1 ins; 0 del; 0 mod; 2337 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw src/cpu/ppc/vm/assembler_ppc.inline.hpp

rev 13389 : PPC: Implement MulAdd and SquareToLen intrinsics

This implementation is based on the algorithm implemented in java. It
yields a performance speedup of:
JDK8 - 23%
JDK9 - 5%
JDK10 - 5%

1 line changed: 1 ins; 0 del; 0 mod; 1048 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw src/cpu/ppc/vm/macroAssembler_ppc.cpp

rev 13390 : Fix issues pointed out by Martin Doerr.

http://mail.openjdk.java.net/pipermail/hotspot-compiler-dev/2017-August/026850.html

34 lines changed: 34 ins; 0 del; 0 mod; 5559 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw src/cpu/ppc/vm/macroAssembler_ppc.hpp

rev 13389 : PPC: Implement MulAdd and SquareToLen intrinsics

This implementation is based on the algorithm implemented in java. It
yields a performance speedup of:
JDK8 - 23%
JDK9 - 5%
JDK10 - 5%

2 lines changed: 2 ins; 0 del; 0 mod; 943 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw src/cpu/ppc/vm/stubGenerator_ppc.cpp

rev 13392 : Clear int to long as Martin suggested

http://mail.openjdk.java.net/pipermail/hotspot-compiler-dev/2017-August/027009.html

264 lines changed: 264 ins; 0 del; 0 mod; 3533 unchg

Cdiffs Udiffs Wdiffs Sdiffs Frames Old New Patch Raw src/cpu/ppc/vm/vm_version_ppc.cpp

rev 13391 : Fix other issues pointed by Martin Doerr.

http://mail.openjdk.java.net/pipermail/hotspot-compiler-dev/2017-August/026899.html

Also took this chance to remove 1 register usage on squaretolen.

8 lines changed: 8 ins; 0 del; 0 mod; 793 unchg

This code review page was prepared using webrev.ksh (vers 25.16-hg+openjdk.java.net).