-
Notifications
You must be signed in to change notification settings - Fork 0
Benchmark Mono against J9 and other runtimes #32
Copy link
Copy link
Open
Labels
area: JITThis issue affects the Mono JITThis issue affects the Mono JITos: aixThis issue affects AIXThis issue affects AIXos: iThis issue affects iThis issue affects ios: linux/ppc64This issue big endian PPC64 Linux tooThis issue big endian PPC64 Linux toopriority; lowThis issue isn't too importantThis issue isn't too importantstatus: triageThis issue requires more information before it can be delivered to upstreamThis issue requires more information before it can be delivered to upstreamtype: questionFurther information is requestedFurther information is requested
Description
We should apply Debian's language shootout and adapt it to use J9. My initial testing by running the C# and Java nbody tests show that Mono is twice as fast as J9 (in AIX on POWER7, J9 8.0 64-bit, assuming both runtimes' defaults) in it, despite not having optimizations for CPUs post-POWER5. We should use the normal benchmark runner, but it's not very well documented; we'll have to play with it further some day.
If we can gather the data, Kyte from upstream is very interested in seeing our data and what tools we can use in AIX or PASE for profiling.
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
area: JITThis issue affects the Mono JITThis issue affects the Mono JITos: aixThis issue affects AIXThis issue affects AIXos: iThis issue affects iThis issue affects ios: linux/ppc64This issue big endian PPC64 Linux tooThis issue big endian PPC64 Linux toopriority; lowThis issue isn't too importantThis issue isn't too importantstatus: triageThis issue requires more information before it can be delivered to upstreamThis issue requires more information before it can be delivered to upstreamtype: questionFurther information is requestedFurther information is requested