[
https://issues.apache.org/jira/browse/RNG-87?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16801267#comment-16801267
]
Alex D Herbert commented on RNG-87:
-----------------------------------
Your new version (MWC_256C) passes the JUnit test for MWC_256. So now it is
tested!
Here is a quick timing test (on a different machine from the above, that was a
linux workstation, this one is a macbook pro).
{noformat}
java version "1.8.0_131"
Java(TM) SE Runtime Environment (build 1.8.0_131-b11)
Java HotSpot(TM) 64-Bit Server VM (build 25.131-b11, mixed mode)
{noformat}
||numValues||randomSourceName||Method||Score||Error||Median||
|1000000|MWC_256|nextInt|4.45e+03|42.9|4.45e+03|
|1000000|MWC_256B|nextInt|3.89e+03|23.8|3.89e+03|
|1000000|MWC_256C|nextInt|4.28e+03|27.9|4.28e+03|
{noformat}
openjdk version "11.0.2" 2019-01-15
OpenJDK Runtime Environment AdoptOpenJDK (build 11.0.2+9)
OpenJDK 64-Bit Server VM AdoptOpenJDK (build 11.0.2+9, mixed mode)
{noformat}
||numValues||randomSourceName||Method||Score||Error||Median||
|1000000|MWC_256|nextInt|4.5e+03|45.3|4.48e+03|
|1000000|MWC_256B|nextInt|3.99e+03|50.9|3.99e+03|
|1000000|MWC_256C|nextInt|4.1e+03|42.4|4.09e+03|
So your method is faster, but not as fast.
Interesting that the difference to the original is quite large this time. This
shows why benchmarks should be run across lots of platforms.
I am not sure why the version you suggested is slower here. It is still doing
one mask operation, one increment and one store to a variable (itself). It is
nice as it directly works with the {{index}} variable making it clearer than
MWC_256B. Maybe using a local copy for the index (MWC_256B) allows the compiler
to assume it will not change and so avoid index checks into the array second
time around? (The array is final but index is a class level variable so might
be treated differently to a local method level final variable.)
> MultiplyWithCarry256
> --------------------
>
> Key: RNG-87
> URL: https://issues.apache.org/jira/browse/RNG-87
> Project: Commons RNG
> Issue Type: Improvement
> Components: core
> Affects Versions: 1.3
> Reporter: Alex D Herbert
> Assignee: Alex D Herbert
> Priority: Minor
> Labels: performance
> Time Spent: 20m
> Remaining Estimate: 0h
>
> The {{MultiplyWithCarry256}} currently uses a length 256 array for internal
> state. This is cycled through continuously. The current implementation
> refills the state every 256 calls to next:
> {code:java}
> public int next() {
> if (index == Q_SIZE) { // Whole state used up.
> // Refill.
> for (int i = 0; i < Q_SIZE; i++) {
> final long t = A * (state[i] & 0xffffffffL) + carry;
> carry = (int) (t >> 32);
> state[i] = (int) t;
> }
> // Reset current index.
> index = 0;
> }
> return state[index++];
> }
> {code}
> This can be changed to continuously update the state for only a single index
> on each call to next:
> {code:java}
> public int next() {
> // Produce an index in the range 0-255
> final int i = index++ & 0xFF;
> final long t = A * (state[i] & 0xffffffffL) + carry;
> carry = (int) (t >> 32);
> return state[i] = (int) t;
> }
> {code}
> This avoids an {{if}} statement check and *marginally* improves performance.
> It has the advantage of not advancing the state further ahead than necessary.
> MWC_256B is the new version. JMH results from the GenerationPerformance
> benchmark.
> {noformat}
> openjdk version "1.8.0_191"
> OpenJDK Runtime Environment (build 1.8.0_191-8u191-b12-2ubuntu0.16.04.1-b12)
> OpenJDK 64-Bit Server VM (build 25.191-b12, mixed mode)
> {noformat}
> ||numValues||randomSourceName||Method||Score||Error||Median||
> |1|SPLIT_MIX_64|nextInt|0.00478|4.45e-05|0.00477|
> |1|MWC_256|nextInt|0.00521|1.69e-05|0.00521|
> |1|MWC_256B|nextInt|0.00519|0.000321|0.00512|
> |100|SPLIT_MIX_64|nextInt|0.421|0.0131|0.418|
> |100|MWC_256|nextInt|0.452|0.000968|0.452|
> |100|MWC_256B|nextInt|0.443|0.00183|0.442|
> |10000|SPLIT_MIX_64|nextInt|41.7|0.0725|41.7|
> |10000|MWC_256|nextInt|44.5|2.25|43.9|
> |10000|MWC_256B|nextInt|42.6|0.037|42.6|
> |1000000|SPLIT_MIX_64|nextInt|3.77e+03|21.2|3.77e+03|
> |1000000|MWC_256|nextInt|4.16e+03|12.8|4.16e+03|
> |1000000|MWC_256B|nextInt|3.98e+03|120|3.96e+03|
> {noformat}
> java version "11.0.2" 2019-01-15 LTS
> Java(TM) SE Runtime Environment 18.9 (build 11.0.2+9-LTS)
> Java HotSpot(TM) 64-Bit Server VM 18.9 (build 11.0.2+9-LTS, mixed mode)
> {noformat}
> ||numValues||randomSourceName||Method||Score||Error||Median||
> |1|SPLIT_MIX_64|nextInt|0.00469|4.98e-06|0.00469|
> |1|MWC_256|nextInt|0.00553|2.09e-05|0.00553|
> |1|MWC_256B|nextInt|0.00493|4.32e-05|0.00492|
> |100|SPLIT_MIX_64|nextInt|0.435|0.000624|0.435|
> |100|MWC_256|nextInt|0.467|0.00284|0.466|
> |100|MWC_256B|nextInt|0.455|0.00105|0.455|
> |10000|SPLIT_MIX_64|nextInt|43|4.94|41.9|
> |10000|MWC_256|nextInt|45.8|0.132|45.8|
> |10000|MWC_256B|nextInt|43|0.033|43|
> |1000000|SPLIT_MIX_64|nextInt|3.7e+03|7.88|3.7e+03|
> |1000000|MWC_256|nextInt|4.17e+03|45.3|4.15e+03|
> |1000000|MWC_256B|nextInt|4.12e+03|4.76|4.12e+03|
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
