YJIT Benchmarks

Details for Benchmarks at 2024-06-11 19:08:14 GMT

YJIT metrics from the yjit-bench suite using Ruby 0a6b1a4d9d.

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 68.9% faster than CRuby 3.4.0dev
  • 7.1% faster than YJIT 3.3.1
On railsbench it is
  • 79.2% faster than CRuby 3.4.0dev
  • 7.6% faster than YJIT 3.3.1

Performance on Headline Benchmarks

Select Platform
0.0 0.5 1.0 1.5 2.0 2.5 CRuby 3.3.1 CRuby 3.4.0dev YJIT 3.3.1 YJIT 3.4.0dev activerecord chunky-png erubi-rails hexapdf liquid-c liquid-compile liquid-render lobsters mail psych-load railsbench rubocop ruby-lsp sequel geomean* 1.09 2.11 2.36 0.94 1.66 1.76 1.03 1.79 1.90 1.07 1.61 1.93 1.01 1.40 1.44 1.02 1.41 1.49 1.04 2.46 2.61 0.99 1.48 1.53 1.01 1.40 1.45 1.09 1.52 1.83 1.02 1.70 1.82 1.01 1.67 1.94 1.15 1.66 1.50 1.02 1.29 1.32 1.03 1.63 1.75
Speed of each Ruby implementation relative to the baseline CRuby measurement. Higher is better.

Memory Usage on Headline Benchmarks

Select Platform
0.0 0.2 0.4 0.6 0.8 1.0 1.2 1.4 1.6 1.8 CRuby 3.3.1 CRuby 3.4.0dev YJIT 3.3.1 YJIT 3.4.0dev activerecord chunky-png erubi-rails hexapdf liquid-c liquid-compile liquid-render lobsters mail psych-load railsbench rubocop ruby-lsp sequel geomean* 1.10 1.27 1.21 1.42 1.12 1.64 1.08 1.08 1.14 0.94 1.23 1.87 1.04 1.13 1.13 1.05 1.09 1.12 1.04 1.15 1.14 1.08 1.17 1.20 1.40 1.09 1.45 1.05 1.05 1.16 1.11 1.16 1.18 1.03 1.34 1.36 1.04 1.04 0.89 1.05 1.09 1.12 1.09 1.14 1.24
Memory usage of each Ruby implementation relative to the baseline CRuby measurement. Lower is better.

Performance on Other Benchmarks

Select Platform
0.0 1.0 2.0 3.0 4.0 CRuby 3.3.1 CRuby 3.4.0dev YJIT 3.3.1 YJIT 3.4.0dev binarytrees blurhash erubi etanni fannkuchredux fluentd graphql graphql-native lee matmul nbody nqueens optcarrot protoboeuf rack ruby-json rubykon sudoku tinygql geomean* 1.02 1.83 2.12 0.95 1.99 2.26 1.08 1.22 1.32 0.53 1.13 0.56 1.05 2.54 2.90 1.13 1.07 1.21 1.08 1.18 1.27 0.75 1.12 1.18 1.10 1.38 1.59 0.89 1.62 1.77 0.96 2.18 2.41 0.94 1.01 3.89 1.14 3.69 4.20 1.02 3.12 3.57 1.12 1.77 2.09 1.05 1.16 1.24 1.03 2.00 2.16 0.98 2.54 2.85 1.07 1.82 1.99 0.98 1.68 1.92
Speed of each Ruby implementation relative to the baseline CRuby measurement. Higher is better.

Memory Usage on Other Benchmarks

Select Platform
0.0 0.2 0.4 0.6 0.8 1.0 1.2 CRuby 3.3.1 CRuby 3.4.0dev YJIT 3.3.1 YJIT 3.4.0dev binarytrees blurhash erubi etanni fannkuchredux fluentd graphql graphql-native lee matmul nbody nqueens optcarrot protoboeuf rack ruby-json rubykon sudoku tinygql geomean* 0.97 0.94 0.98 1.04 1.01 1.06 1.02 1.06 1.07 1.07 1.01 1.08 1.05 1.01 1.07 1.00 1.04 1.08 1.02 1.06 1.10 1.18 1.06 1.14 0.98 1.05 1.05 0.96 1.01 0.97 1.05 1.01 1.07 1.06 1.01 1.12 1.00 1.02 1.09 1.18 1.03 1.20 1.06 1.06 1.12 1.06 1.01 1.07 1.03 1.02 1.09 1.05 1.02 1.07 1.05 1.07 1.12 1.04 1.03 1.08
Memory usage of each Ruby implementation relative to the baseline CRuby measurement. Lower is better.

Performance on MicroBenchmarks

Select Platform
0.0 5.0 10.0 15.0 20.0 CRuby 3.3.1 CRuby 3.4.0dev YJIT 3.3.1 YJIT 3.4.0dev 30k_ifelse 30k_methods cfunc_itself fib getivar keyword_args respond_to ruby-xor setivar setivar_object setivar_young str_concat throw geomean* 1.00 6.78 6.83 0.98 8.06 8.07 0.92 4.28 4.70 1.00 5.48 5.49 0.92 4.95 5.30 1.03 7.66 10.02 0.99 18.42 22.91 0.90 2.64 3.81 0.97 5.68 8.64 1.16 2.10 3.24 1.13 2.19 3.21 0.90 1.92 1.74 0.91 1.28 1.15 0.98 4.26 4.99
Speed of each Ruby implementation relative to the baseline CRuby measurement. Higher is better.

Memory Usage on MicroBenchmarks

Select Platform
0.0 0.5 1.0 1.5 2.0 2.5 CRuby 3.3.1 CRuby 3.4.0dev YJIT 3.3.1 YJIT 3.4.0dev 30k_ifelse 30k_methods cfunc_itself fib getivar keyword_args respond_to ruby-xor setivar setivar_object setivar_young str_concat throw geomean* 2.42 1.51 2.55 1.89 1.20 1.96 1.05 1.02 1.06 1.05 1.01 1.06 1.05 1.02 1.06 1.05 1.02 1.06 1.05 1.02 1.07 1.05 1.01 1.06 1.05 1.02 1.06 1.05 1.01 1.06 1.05 1.01 1.06 1.04 1.00 1.36 1.04 1.01 1.05 1.17 1.06 1.21
Memory usage of each Ruby implementation relative to the baseline CRuby measurement. Lower is better.

Want Raw Graphs and CSV?

Benchmarks Speed Details

Select Platform
bench CRuby 3.3.1 (ms) CRuby 3.3.1 RSD CRuby 3.4.0dev (ms) CRuby 3.4.0dev RSD YJIT 3.3.1 (ms) YJIT 3.3.1 RSD YJIT 3.4.0dev (ms) YJIT 3.4.0dev RSD CRuby 3.4.0dev spd CRuby 3.4.0dev spd RSD YJIT 3.3.1 spd YJIT 3.3.1 spd RSD YJIT 3.4.0dev spd YJIT 3.4.0dev spd RSD % in YJIT
activerecord 553.3 0.42% 509.9 0.29% 262.2 0.37% 234.5 0.38% 1.09x 0.51% 2.11x 0.56% 2.36x 0.56% 99.93%
chunky-png 1153.3 0.12% 1222.5 0.22% 695.5 0.19% 654.3 0.27% 0.94x 0.25% 1.66x 0.22% 1.76x 0.30% 99.99%
erubi-rails 1936.1 0.15% 1881.7 0.35% 1082.2 0.27% 1018.7 0.52% 1.03x 0.38% 1.79x 0.30% 1.90x 0.54% 99.84%
hexapdf 3853.3 0.74% 3612.3 1.24% 2386.1 1.21% 1995.2 1.90% 1.07x 1.44% 1.61x 1.42% 1.93x 2.04% 99.45%
liquid-c 87.7 0.65% 87.0 0.60% 62.6 0.90% 60.8 0.68% 1.01x 0.88% 1.40x 1.11% 1.44x 0.94% 99.75%
liquid-compile 88.9 0.47% 87.0 0.45% 63.2 0.69% 59.6 0.67% 1.02x 0.65% 1.41x 0.83% 1.49x 0.82% 99.96%
liquid-render 215.9 0.33% 208.5 0.43% 87.8 0.62% 82.8 0.63% 1.04x 0.55% 2.46x 0.70% 2.61x 0.71% 99.90%
lobsters 1332.7 1.23% 1344.9 0.90% 902.0 1.31% 872.0 1.25% 0.99x 1.52% 1.48x 1.80% 1.53x 1.76% 99.17%
mail 187.9 0.31% 185.6 0.37% 134.6 0.35% 129.3 0.42% 1.01x 0.48% 1.40x 0.47% 1.45x 0.52% 99.88%
psych-load 3109.9 0.05% 2841.9 0.07% 2042.1 0.06% 1702.0 0.09% 1.09x 0.08% 1.52x 0.08% 1.83x 0.10% 99.99%
railsbench 3514.5 0.36% 3451.7 0.15% 2072.2 0.28% 1925.9 0.26% 1.02x 0.39% 1.70x 0.45% 1.82x 0.45% 99.81%
rubocop 213.9 0.93% 211.8 1.05% 127.8 2.28% 110.0 2.78% 1.01x 1.40% 1.67x 2.46% 1.94x 2.93% 99.86%
ruby-lsp 168.9 1.25% 146.9 1.22% 101.9 1.37% 112.6 1.39% 1.15x 1.75% 1.66x 1.86% 1.50x 1.87% 97.57%
sequel 97.1 0.34% 95.6 0.47% 75.2 0.45% 73.7 0.47% 1.02x 0.58% 1.29x 0.57% 1.32x 0.58% 98.76%
binarytrees 527.8 0.21% 517.4 0.15% 289.0 0.16% 248.5 0.17% 1.02x 0.26% 1.83x 0.26% 2.12x 0.27% 99.99%
blurhash 441.4 0.20% 466.8 0.05% 221.9 0.26% 195.0 0.29% 0.95x 0.20% 1.99x 0.33% 2.26x 0.35% 99.99%
erubi 344.2 0.17% 319.5 0.12% 282.4 0.18% 260.4 0.14% 1.08x 0.21% 1.22x 0.24% 1.32x 0.22% 99.97%
etanni 478.8 0.12% 909.1 0.13% 422.2 0.18% 851.2 0.11% 0.53x 0.18% 1.13x 0.22% 0.56x 0.16% 99.94%
fannkuchredux 2397.9 0.11% 2281.9 0.03% 944.1 0.07% 826.3 8.70% 1.05x 0.11% 2.54x 0.13% 2.90x 8.70% 74.28%
fluentd 2959.2 0.71% 2630.3 0.77% 2755.2 1.12% 2443.7 0.71% 1.13x 1.05% 1.07x 1.33% 1.21x 1.00% 99.98%
graphql 4747.4 0.06% 4411.9 0.04% 4022.4 0.08% 3740.5 0.04% 1.08x 0.07% 1.18x 0.10% 1.27x 0.07% 99.44%
graphql-native 731.5 0.09% 976.2 1.06% 654.2 0.10% 620.9 0.11% 0.75x 1.06% 1.12x 0.13% 1.18x 0.14% 99.95%
lee 1641.0 1.05% 1498.6 0.91% 1190.8 1.52% 1029.6 1.02% 1.10x 1.39% 1.38x 1.85% 1.59x 1.46% 99.96%
matmul 2015.0 0.07% 2262.0 0.09% 1245.7 0.11% 1138.1 0.15% 0.89x 0.11% 1.62x 0.13% 1.77x 0.17% 99.64%
nbody 141.1 0.02% 146.7 0.04% 64.7 0.06% 58.6 0.41% 0.96x 0.05% 2.18x 0.06% 2.41x 0.41% 99.78%
nqueens 251.3 0.59% 268.7 0.03% 250.0 0.28% 64.6 0.13% 0.94x 0.59% 1.01x 0.66% 3.89x 0.61% 94.61%
optcarrot 8631.3 0.34% 7583.8 0.39% 2337.7 0.42% 2054.2 0.74% 1.14x 0.52% 3.69x 0.54% 4.20x 0.82% 99.49%
protoboeuf 170.1 0.47% 167.2 0.26% 54.5 0.37% 47.6 0.46% 1.02x 0.53% 3.12x 0.59% 3.57x 0.66% 99.99%
rack 69.1 0.64% 61.9 0.71% 38.9 1.02% 33.1 1.05% 1.12x 0.96% 1.77x 1.20% 2.09x 1.23% 99.87%
ruby-json 4382.6 0.03% 4173.0 0.44% 3782.0 0.06% 3534.0 0.10% 1.05x 0.44% 1.16x 0.07% 1.24x 0.11% 99.98%
rubykon 14852.5 0.46% 14479.5 0.94% 7409.5 2.07% 6870.3 1.06% 1.03x 1.05% 2.00x 2.12% 2.16x 1.16% 99.95%
sudoku 2127.5 0.02% 2166.6 0.12% 839.1 0.04% 746.4 0.03% 0.98x 0.12% 2.54x 0.05% 2.85x 0.04% 99.71%
tinygql 995.2 0.10% 931.4 0.06% 547.6 0.11% 500.0 0.13% 1.07x 0.12% 1.82x 0.15% 1.99x 0.17% 99.98%
30k_ifelse 2454.1 0.09% 2466.3 0.11% 361.8 0.09% 359.1 0.10% 1.00x 0.14% 6.78x 0.12% 6.83x 0.13% 99.94%
30k_methods 6755.3 0.03% 6865.7 0.03% 838.1 0.03% 837.0 0.04% 0.98x 0.05% 8.06x 0.04% 8.07x 0.05% 99.98%
cfunc_itself 114.8 0.18% 124.3 0.16% 26.8 6.76% 24.4 8.17% 0.92x 0.24% 4.28x 6.76% 4.70x 8.17% 95.09%
fib 262.6 0.07% 263.2 0.23% 48.0 0.18% 47.8 0.06% 1.00x 0.24% 5.48x 0.20% 5.49x 0.09% 99.99%
getivar 112.2 0.22% 122.6 0.31% 22.6 48.62% 21.2 57.31% 0.92x 0.39% 4.95x 48.62% 5.30x 57.31% 76.05%
keyword_args 313.3 0.09% 303.9 0.02% 40.9 5.18% 31.3 7.38% 1.03x 0.10% 7.66x 5.19% 10.02x 7.38% 96.25%
respond_to 316.7 0.14% 320.2 0.07% 17.2 7.79% 13.8 11.32% 0.99x 0.16% 18.42x 7.79% 22.91x 11.32% 95.32%
ruby-xor 761.0 0.04% 842.5 0.19% 288.5 0.24% 200.0 0.14% 0.90x 0.20% 2.64x 0.24% 3.81x 0.15% 99.99%
setivar 70.8 0.97% 73.3 0.40% 12.5 42.61% 8.2 58.08% 0.97x 1.05% 5.68x 42.63% 8.64x 58.09% 85.19%
setivar_object 128.3 14.54% 111.1 0.14% 61.2 36.21% 39.6 29.50% 1.16x 14.54% 2.10x 39.02% 3.24x 32.89% 82.09%
setivar_young 126.0 11.75% 111.1 0.51% 57.6 29.87% 39.2 29.85% 1.13x 11.76% 2.19x 32.10% 3.21x 32.08% 82.09%
str_concat 88.8 0.96% 98.8 0.96% 46.3 1.32% 50.9 1.42% 0.90x 1.36% 1.92x 1.63% 1.74x 1.72% 99.89%
throw 32.6 0.19% 35.7 0.29% 25.5 0.25% 28.4 0.22% 0.91x 0.35% 1.28x 0.31% 1.15x 0.29% 99.98%

RSD is relative standard deviation - the standard deviation divided by the mean, expressed as a percentage.
% in YJIT is the percentage of instructions that complete in YJIT rather than exiting to the non-JITted interpreter. YJIT performs better when this is higher.
Speedup is relative to interpreted CRuby. So an "MJIT speedup" of 1.21x means MJIT runs at 1.21 times the iters/second of CRuby with JIT disabled.

You can find our benchmark code in the yjit-bench Github repo.
Our benchmark-runner and reporting code is in the yjit-metrics Github repo.

Tested Ruby version for development CRuby and YJIT: ruby 3.4.0dev (2024-06-11T18:28:04Z :detached: 0a6b1a4d9d) +YJIT [x86_64-linux]
Tested Ruby version for stable CRuby and YJIT: ruby 3.3.1 (2024-04-23 revision c56cd86388) +YJIT [x86_64-linux]

Benchmark Memory Usage Details

Select Platform
bench CRuby 3.3.1 mem (MiB) CRuby 3.4.0dev mem (MiB) YJIT 3.3.1 mem (MiB) YJIT 3.4.0dev mem (MiB) Inline Code Outlined Code YJIT Mem overhead
activerecord 62 68 79 75 2 2 9.6%
chunky-png 42 60 47 69 1 1 15.9%
erubi-rails 102 110 111 117 2 2 5.9%
hexapdf 140 132 172 263 2 2 98.3%
liquid-c 35 37 40 40 1 1 9.2%
liquid-compile 33 35 36 37 1 1 6.9%
liquid-render 36 37 41 41 1 1 10.4%
lobsters 268 288 314 321 8 6 11.4%
mail 49 69 54 72 1 1 3.3%
psych-load 33 34 34 38 1 1 11.2%
railsbench 98 109 114 116 3 3 7.1%
rubocop 89 92 120 122 6 5 32.4%
ruby-lsp 83 86 86 74 1 1 -13.9%
sequel 36 38 40 41 1 1 6.4%
binarytrees 25 25 24 25 1 1 1.0%
blurhash 21 22 22 23 1 1 2.5%
erubi 29 29 31 31 1 1 5.3%
etanni 23 24 23 25 1 1 1.3%
fannkuchredux 20 21 20 21 1 1 1.5%
fluentd 606 609 631 656 1 1 7.9%
graphql 39 40 42 43 1 1 7.3%
graphql-native 37 44 39 42 1 1 -3.4%
lee 35 34 36 36 1 1 7.4%
matmul 32 31 32 31 1 1 0.7%
nbody 20 21 20 21 1 1 1.5%
nqueens 20 21 20 22 1 1 5.1%
optcarrot 59 59 60 64 1 1 9.1%
protoboeuf 28 34 29 34 1 1 1.8%
rack 30 32 32 34 1 1 6.0%
ruby-json 21 22 21 22 1 1 1.3%
rubykon 47 49 48 52 1 1 6.3%
sudoku 20 21 20 21 1 1 1.7%
tinygql 27 29 29 31 1 1 7.2%
30k_ifelse 60 145 90 153 5 5 5.5%
30k_methods 49 92 58 96 2 2 3.8%
cfunc_itself 20 21 20 21 1 1 1.2%
fib 20 21 20 21 1 1 1.1%
getivar 20 21 20 21 1 1 1.2%
keyword_args 20 21 20 21 1 1 1.2%
respond_to 20 21 20 21 1 1 1.3%
ruby-xor 21 22 21 22 1 1 1.1%
setivar 20 21 20 21 1 1 1.2%
setivar_object 20 21 20 21 1 1 1.1%
setivar_young 20 21 20 21 1 1 1.1%
str_concat 46 48 46 62 1 1 30.7%
throw 20 21 20 21 1 1 1.1%

Memory is shown in mebibytes (1024 * 1024 bytes.)

Older YJIT allocated an additional 256MiB for generated code. Current YJIT allocates executable memory on demand, so this overhead should no longer be present.

Number of Iterations and Warmups Tested

bench CRuby 3.3.1 warmups CRuby 3.3.1 iters CRuby 3.4.0dev warmups CRuby 3.4.0dev iters YJIT 3.3.1 warmups YJIT 3.3.1 iters YJIT 3.4.0dev warmups YJIT 3.4.0dev iters
activerecord 10 45 10 49 10 104 10 118
chunky-png 10 16 10 15 10 34 10 36
erubi-rails 10 10 10 10 10 18 10 20
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 333 10 335 10 469 10 483
liquid-compile 10 328 10 335 10 464 10 493
liquid-render 10 129 10 134 10 332 10 352
lobsters 10 13 10 13 10 22 10 23
mail 10 149 10 151 10 211 10 219
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 128 10 129 10 213 10 246
ruby-lsp 10 168 10 194 10 283 10 255
sequel 10 299 10 304 10 389 10 398
binarytrees 10 47 10 48 10 94 10 111
blurhash 10 58 10 55 10 126 10 144
erubi 10 78 10 84 10 97 10 106
etanni 10 53 10 23 10 62 10 26
fannkuchredux 10 10 10 10 10 14 10 17
fluentd 10 10 10 10 10 10 10 10
graphql 10 10 10 10 10 10 10 10
graphql-native 10 31 10 21 10 36 10 39
lee 10 10 10 11 10 16 10 20
matmul 10 10 10 10 10 15 10 17
nbody 10 203 10 195 10 454 10 502
nqueens 10 110 10 102 10 111 10 445
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 167 10 170 10 540 10 620
rack 10 425 10 475 10 761 10 898
ruby-json 10 10 10 10 10 10 10 10
rubykon 10 10 10 10 10 10 10 10
sudoku 10 10 10 10 10 26 10 31
tinygql 10 21 10 23 10 45 10 50
30k_ifelse 10 10 10 10 10 70 10 70
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 252 10 232 10 1105 10 1212
fib 10 105 10 104 10 616 10 618
getivar 10 258 10 235 10 1276 10 1359
keyword_args 10 86 10 89 10 720 10 945
respond_to 10 85 10 84 10 1728 10 2149
ruby-xor 10 30 10 26 10 94 10 141
setivar 10 414 10 400 10 2350 10 3568
setivar_object 10 226 10 261 10 472 10 730
setivar_young 10 229 10 261 10 501 10 737
str_concat 10 328 10 294 10 638 10 579
throw 10 911 10 832 10 1165 10 1046

Different Ruby configurations want different amounts of warmup. With no JIT, CRuby needs hardly any. YJIT and MJIT 3.0 both warm up quite quickly, while MJIT in 3.1 often slows down for a time as it compiles, after an unpredictable delay.

Benchmark YJIT Stats

Hover your cursor over the benchmark names for descriptions of each benchmark.

bench Exit Report Inline Outlined Comp iSeqs Comp Blocks Inval Inval Ratio Bind Alloc Bind Set Const Bumps Compile Time MS
activerecord (click) 1414891 1206248 214 2184 0 0% 0 0 71.926776
chunky-png (click) 332287 278674 82 1047 1 0% 0 0 33.305314
erubi-rails (click) 1688450 1373839 272 2953 6 0% 0 0 89.534693
hexapdf (click) 1288944 1063907 504 11515 41 0% 0 0 365.667865
liquid-c (click) 521506 397902 119 1754 5 0% 0 0 52.299144
liquid-compile (click) 445855 370620 151 2082 2 0% 0 0 70.393588
liquid-render (click) 618609 509998 136 2292 8 0% 0 0 69.053461
lobsters (click) 7548151 6285195 3108 48874 89 0% 0 0 1792.947095
mail (click) 724854 598767 346 4874 14 0% 0 0 155.744828
psych-load (click) 298577 241884 61 617 3 0% 0 0 21.122848
railsbench (click) 2944765 2613910 1633 15928 57 0% 0 0 495.614531
rubocop (click) 5328642 4578673 2901 48298 112 0% 4 0 1584.717899
ruby-lsp (click) 629117 502974 159 2818 28 0% 0 0 86.248431
sequel (click) 485294 424284 16 117 0 0% 0 0 4.412646
binarytrees (click) 8756 7777 10 70 0 0% 0 0 2.957877
blurhash (click) 50429 43324 31 457 0 0% 0 0 16.881787
erubi (click) 271362 232660 10 112 0 0% 0 0 4.300439
etanni (click) 29692 28216 11 91 0 0% 0 0 3.207123
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.840182
fluentd (click) 379469 309464 4 28 0 0% 0 0 1.163906
graphql (click) 433479 357096 66 644 0 0% 0 0 21.65021
graphql-native (click) 405553 333992 42 278 0 0% 0 0 10.394227
lee (click) 294824 256825 34 528 0 0% 0 0 17.96476
matmul (click) 8300 983 8 85 0 0% 0 0 3.125839
nbody (click) 14798 17933 11 185 0 0% 0 0 5.611897
nqueens (click) 22703 29059 10 261 0 0% 0 0 9.112743
optcarrot (click) 307949 297791 188 4303 34 0% 0 0 111.120843
protoboeuf (click) 146729 137400 17 1410 0 0% 0 0 46.526887
rack (click) 276831 221981 37 408 0 0% 0 0 12.19737
ruby-json (click) 30222 27890 8 167 0 0% 0 0 5.190337
rubykon (click) 127405 128474 137 1461 3 0% 0 0 44.729098
sudoku (click) 42479 58142 8 475 0 0% 0 0 16.427195
tinygql (click) 309618 278070 58 742 5 0% 0 0 23.472531
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1577.646708
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 534.650439
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.342693
fib (click) 4970 5003 8 49 0 0% 0 0 1.814844
getivar (click) 5963 6375 8 74 0 0% 0 0 2.2316
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.749652
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.781727
ruby-xor (click) 5593 5796 5 62 0 0% 0 0 1.914916
setivar (click) 5102 5375 8 54 0 0% 0 0 1.870408
setivar_object (click) 5470 5395 8 54 0 0% 0 0 1.948064
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.170419
str_concat (click) 7774 7946 11 85 0 0% 0 0 3.06726
throw (click) 7895 6377 10 69 0 0% 0 0 2.71884

YJIT stats correspond to the YJIT stats exit report.

Note: currently, all stats are collected on x86_64, not ARM.

Raw JSON data files

All graphs and table data in this page comes from processing these data files, which come from benchmark runs.