RFR(XS): JDK-8010941: MinJumpTableSize is set to 18, investigate if that's still optimal

[Niclas Adlertz]

Hi Aleksey, sorry about that.

> What are the different numbers after win/loss? Jump table sizes?
The number of cases in the switch statement and the jump table size. 
For example 
At 3, means three cases:
switch () {
 case
 case 
 case 
}

"Using JumpTable (or Using)" means we set the JumpTableSize to the same number as the number of cases (in the above example MinJumpTableSize=3), which means that we use a jump table. 
"Not" means we are not using a jump table (i.e. setting the MinJumpTableSize to something greater than the number of cases).

Win means we gained performance by using a jump table, loss means we lost performance by using a jump table.

Sorry for the confusion. 

Kind Regards,
Niclas Adlertz


On 5 sep 2013, at 16:11, Aleksey Shipilev <aleksey.shipilev at oracle.com> wrote:

> Hi Niclas,
> 
> I have trouble interpreting the results. What are the different numbers after win/loss? Jump table sizes? What is "Not"? Shouldn't "Not" be the same if they are not using the Jump Table? I am very confused.
> 
> -Aleksey
> 
> On 05.09.2013, at 16:41, Niclas Adlertz <niclas.adlertz at oracle.com> wrote:
> 
>> Hi all.
>> 
>> Sorry for the delay.
>> 
>> I've written a JMH test[0] and the results[1] differs from what I previously got. Because of this, I propose the new MinJumpTableSize number to be 10.
>> 
>> WEBREV: http://cr.openjdk.java.net/~adlertz/JDK-8010941/webrev01/
>> 
>> [0]
>> http://cr.openjdk.java.net/~adlertz/JDK-8010941/MyBenchmark.java
>> 
>> [1]
>> http://cr.openjdk.java.net/~adlertz/JDK-8010941/results.txt
>> 
>> Kind Regards,
>> Niclas Adlertz
>> 
>> 
>> On 22 maj 2013, at 00:48, Aleksey Shipilev <aleksey.shipilev at oracle.com> wrote:
>> 
>>> On 05/21/2013 10:17 PM, Vladimir Kozlov wrote:
>>> 
>>>> We usually do about 20000 iterations and run with -Xbatch to make sure
>>>> tested method is compiled before time measurement.
>>> 
>>> Yeah, that works if the benchmark is the single method call. Anything
>>> more complex require more complex warmup.
>>> 
>>>>> Also, I begin to wonder if after the multiply_by_power_of_ten inlining
>>>>> start to affect how far we unroll the loop, since the jump tables are
>>>>> starting to be larger.
>>>> 
>>>> You can avoid it by
>>>> -XX:CompileCommand=dontinline,Test::multiply_by_power_of_ten
>>> 
>>> Or, (chanting) use JMH:
>>> http://hg.openjdk.java.net/code-tools/jmh/file/tip/jmh-samples/src/main/java/org/openjdk/jmh/samples/JMHSample_16_CompilerControl.java
>>> 
>>> Or, (chanting again) use JMH, because it does not really use indexed
>>> loops, but rather volatile-predicated loop, so the loop unrolling is
>>> ineffective (double ineffective with the source data re-read from the
>>> fields on every iteration).
>>> 
>>> Before you jump on other platforms, look into the assembly to see if
>>> your benchmark are actually generate the code that makes sense (i.e.
>>> trapped on any of the issues Vladimir and me had speculated here):
>>> https://wiki.openjdk.java.net/display/HotSpot/PrintAssembly
>>> 
>>> -Aleksey.
>>