Final version for thomaswue

[thomaswue]

Check List:

• You have run ./mvnw verify and the project builds successfully
• Tests pass (./test.sh <username> shows no differences between expected and actual outputs)
• All formatting changes by the build are committed
• Your launch script is named calculate_average_<username>.sh (make sure to match casing of your GH user name) and is executable
• Output matches that of calculate_average_baseline.sh
• For new entries, or after substantial changes: When implementing custom hash structures, please point to where you deal with hash collisions (line number)

• Execution time: 0.39
• Execution time of reference implementation: 120.37

Added detailed comments for the used native image flags, some code clean up for better naming, some minor tuning. This translates to around 2% faster on my machine, but let's see if this also holds up for the reference machine.

[gunnarmorling]

Nice!

Benchmark 1: timeout -v 300 ./calculate_average_thomaswue.sh 2>&1
  Time (mean ± σ):      1.830 s ±  0.011 s    [User: 0.002 s, System: 0.004 s]
  Range (min … max):    1.798 s …  1.836 s    10 runs

  Warning: Statistical outliers were detected. Consider re-running this benchmark on a quiet system without any interferences from other programs. It might help to use the '--warmup' or '--prepare' options.

Summary
  thomaswue: trimmed mean 1.832794623615, raw times 1.7984286922400001,1.83378488024,1.8358817772400002,1.8351058012400001,1.8321136482400002,1.83353322124,1.83313856524,1.8319531362400001,1.83227779624,1.83044994024

Leaderboard

| # | Result (m:s.ms) | Implementation     | JDK | Submitter     | Notes     |
|---|-----------------|--------------------|-----|---------------|-----------|
|   | 00:01.832 | [link](https://github.com/gunnarmorling/1brc/blob/main/src/main/java/dev/morling/onebrc/CalculateAverage_thomaswue.java)| 21.0.2-graal | [Thomas Wuerthinger](https://github.com/thomaswue) | GraalVM native binary, uses Unsafe |

[Alex-Cheng]

I just want to learn it. Why dividing the workload into 3 parts and process them simuteneously benifits performance? I am curious about the programming skill?

Thank you.

[thomaswue]

This way the x86 processor is able to better use its processing units to execute more instructions per cycle. I am preparing some more information and blog post about this.

[Alex-Cheng]

Thank you. I am looking forward your blog. I didn't find it in the resource list. Is it in progress? I don't want to miss the great blog.