diff options
| author | Asko Nõmm <asko@nmm.ee> | 2026-04-10 15:55:56 +0300 |
|---|---|---|
| committer | Asko Nõmm <asko@nmm.ee> | 2026-04-10 15:55:56 +0300 |
| commit | eb6f23ab6138cc132154145720c503d2509ede1f (patch) | |
| tree | 4751b3c6c128073af662b8e7de1210d58744c775 /BENCHMARKS.md | |
| parent | c98df5a044bbca27a3f5d4a7ad124c4656ce8693 (diff) | |
Update Jank benchmark baseline and timer interop
Refresh Jank benchmark numbers with the latest run and fix the Jank clock helper interop in the benchmark harness so future benchmark runs complete successfully.
Diffstat (limited to 'BENCHMARKS.md')
| -rw-r--r-- | BENCHMARKS.md | 32 |
1 files changed, 16 insertions, 16 deletions
diff --git a/BENCHMARKS.md b/BENCHMARKS.md index c6e7053..799186c 100644 --- a/BENCHMARKS.md +++ b/BENCHMARKS.md @@ -193,20 +193,20 @@ Each benchmark: 2s warmup, 5s measurement window. | Scenario | Ops/sec | ns/op | |---|---:|---:| -| Small (5) — literal first | 91,466 | 10,932 | -| Small (5) — literal middle | 63,483 | 15,752 | -| Small (5) — param match | 29,092 | 34,373 | -| Small (5) — nested params | 24,136 | 41,430 | -| Small (5) — wildcard | 23,772 | 42,065 | -| Small (5) — miss (404) | 94,463 | 10,586 | -| Medium (52) — match first | 95,493 | 10,471 | -| Medium (52) — match middle | 27,171 | 36,803 | -| Medium (52) — match last | 26,904 | 37,168 | -| Medium (52) — catch-all wildcard | 32,048 | 31,203 | -| Large (202) — match first | 94,151 | 10,621 | -| Large (202) — match middle | 26,602 | 37,590 | -| Large (202) — match last | 26,916 | 37,152 | -| Large (202) — miss (404) | 68,021 | 14,701 | +| Small (5) — literal first | 962,079 | 1,039 | +| Small (5) — literal middle | 442,877 | 2,257 | +| Small (5) — param match | 223,006 | 4,484 | +| Small (5) — nested params | 146,768 | 6,813 | +| Small (5) — wildcard | 182,129 | 5,490 | +| Small (5) — miss (404) | 655,948 | 1,524 | +| Medium (52) — match first | 899,823 | 1,111 | +| Medium (52) — match middle | 181,990 | 5,494 | +| Medium (52) — match last | 181,771 | 5,501 | +| Medium (52) — catch-all wildcard | 272,411 | 3,670 | +| Large (202) — match first | 875,741 | 1,141 | +| Large (202) — match middle | 178,075 | 5,615 | +| Large (202) — match last | 176,088 | 5,678 | +| Large (202) — miss (404) | 482,470 | 2,072 | ## Analysis @@ -229,8 +229,8 @@ Each benchmark: 2s warmup, 5s measurement window. - Peak throughput: ~1.1M ops/sec (miss/404 — fast trie rejection) ### Jank -- Peak throughput: ~95K ops/sec (literal match / miss) -- Performance is roughly 8–10x slower than Babashka, expected for an alpha interpreted runtime +- Peak throughput: ~962K ops/sec (literal match) +- Performance is now close to Babashka peak throughput on this benchmark suite ### Key insight |