Shenandoah WB and tableswitch

[Roman Kennke]

Am 22.12.2017 um 14:29 schrieb Aleksey Shipilev:
> On 12/22/2017 01:44 PM, Roland Westrelin wrote:
>> Here is a WIP patch if you want to give it a try:
>>
>> http://cr.openjdk.java.net/~roland/shenandoah/predicate%2btableswitch.patch
> Very good! Our most targeted benchmark:
>
> # WriteBarrierTableSwitch.separate
> Parallel:                  1227 ± 9 ns/op
> Shenandoah baseline, -WB:  1663 ± 1 ns/op
> Shenandoah patched,  -WB:  1081 ± 5 ns/op
> Shenandoah baseline, +WB:  1839 ± 1 ns/op
> Shenandoah patched,  +WB:  1169 ± 1 ns/op   // +57% better
>
> ...which was the minimized version of:
>
> # ObjectInputStream read test
> Parallel:                 10981 ±  32 ns/op
> Shenandoah baseline, -WB: 10256 ± 206 ns/op
> Shenandoah patched,  -WB: 10589 ± 247 ns/op
> Shenandoah baseline, +WB: 12890 ± 414 ns/op
> Shenandoah patched,  +WB: 11153 ± 209 ns/op  // +15% better
>
> ...which was the minimized version of:
>
> # Serial
> Parallel:                  2646 ±  2  ops/s
> Shenandoah baseline, -WB:  2591 ± 32  ops/s
> Shenandoah patched,  -WB:  2553 ± 33  ops/s
> Shenandoah baseline, +WB:  2269 ± 30  ops/s
> Shenandoah patched,  +WB:  2355 ± 35  ops/s  // +4% better
>
> -Aleksey
>
>
Great! :-)

Wasn't xml benchmarks also affected by this, or am I confusing things?

How do we look vs ZGC now?

Roman