gunnarmorling
commented
7 months ago Sorry, made things a bit worse:
Benchmark 1: timeout -v 300 ./calculate_average_royvanrijn.sh 2>&1
Time (mean ± σ): 2.559 s ± 0.011 s [User: 0.002 s, System: 0.004 s]
Range (min … max): 2.542 s … 2.569 s 5 runs
Summary
royvanrijn: trimmed mean 2.560535277553333, raw times 2.54156210322,2.55442099422,2.56392523922,2.56325959922,2.56947195822
Leaderboard
| # | Result (m:s.ms) | Implementation | JDK | Submitter | Notes |
|---|-----------------|--------------------|-----|---------------|-----------|
| | 00:02.560 | [link](https://github.com/gunnarmorling/1brc/blob/main/src/main/java/dev/morling/onebrc/CalculateAverage_royvanrijn.java)| 21.0.2-graal | [Roy van Rijn](https://github.com/royvanrijn) | GraalVM native binary, uses Unsafe |
royvanrijn
Trying three readers as well, not faster on my old x86, it is faster on the M2... hard to measure what helps and what hurts now.
On my new MacBook I'm very close to @thomaswue and in front of the others, but measuring on that machine hasn't been very reliable.
Just ran the top entries on my machine:
Let's hope this translates haha, but lately is seems the reference machine isn't close to doing the same as the M2.
Check List:
[X] Tests pass (
./test.sh <username>shows no differences between expected and actual outputs)[X] All formatting changes by the build are committed
[X] Your launch script is named
calculate_average_<username>.sh(make sure to match casing of your GH user name) and is executable[X] Output matches that of
calculate_average_baseline.sh[X] 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:
Execution time of reference implementation: