jdk9 : forcing inlining in src/share/vm/oops/instanceKlass.inline.hpp for xlc

[Volker Simonis]

Hi Matthias,

thanks for reporting this. I've opened "8151593: AIX: add support for
xlC 'always_inline' compiler attribute"
(https://bugs.openjdk.java.net/browse/JDK-8151593) to track this
issue.

Regards,
Volker

On Wed, Mar 9, 2016 at 6:01 PM, Baesken, Matthias
<matthias.baesken at sap.com> wrote:
> Hello ,
>
> CR 8075955: "Replace the macro based implementation of oop_oop_iterate with
> a template based solution"
>
>
>
> changed src/share/vm/oops/instanceKlass.inline.hpp
>
>
>
> and replaced macro based oop iteration by templates.
>
> For performance reason, the change (and a follow up change for Oracle
> Studio) introduced forcing of inlining for some places in
>
> src/share/vm/oops/instanceKlass.inline.hpp  , see
>
>
>
>
>
> http://hg.openjdk.java.net/jdk9/dev/hotspot/file/797e6aac6d53/src/share/vm/oops/instanceKlass.inline.hpp
>
>
>
> ....
>
> // The iteration over the oops in objects is a hot path in the GC code.
>
> // By force inlining the following functions, we get similar GC performance
>
> // as the previous macro based implementation.
>
> #ifdef TARGET_COMPILER_visCPP
>
> #define INLINE __forceinline
>
> #elif defined(TARGET_COMPILER_sparcWorks)
>
> #define INLINE __attribute__((always_inline))
>
> #else
>
> #define INLINE inline
>
> #endif
>
> ....
>
>
>
> (which is compiler dependent)
>
> Should we do this for the AIX port too ?
>
>
>
> http://www.ibm.com/support/knowledgecenter/SSGH2K_12.1.0/com.ibm.xlc121.aix.doc/language_ref/function_attributes.html?lang=en
>
>
>
>
>
> describes the function attributes of xlc which can be used.
>
> Diff to instanceKlass.inline.hpp  :
>
>
>
> 43,44d42
>
> < #elif defined(TARGET_COMPILER_xlc)
>
> < #define INLINE __attribute__((always_inline))
>
>
>
>
>
> Regards, Matthias