YJIT Benchmarks

2022-08-14 20:13:53

As of 2022-08-14 20:13:53:

Overall YJIT is 34.8% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 34.2% faster than CRuby!

The basic "faster" measurement is the geomean of all "headlining" benchmarks on this page.

Headlining Benchmarks

These are "headlining" because the "overall" speedup above is based on these benchmarks specifically.

0.0 0.2 0.4 0.6 0.8 1.0 1.2 1.4 No JIT MJIT YJIT activerecord hexapdf liquid-render mail psych-load railsbench Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

MicroBenchmarks

0.0 1.0 2.0 3.0 4.0 5.0 6.0 7.0 No JIT MJIT YJIT 30k_ifelse 30k_methods cfunc_itself fib getivar keyword_args respond_to setivar str_concat Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

Other Benchmarks

0.0 0.5 1.0 1.5 2.0 No JIT MJIT YJIT binarytrees chunky_png erubi erubi_rails fannkuchredux lee nbody optcarrot rubykon Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

Want Raw Graphs and CSV?

Benchmarks Speed Details

The y axis is CRuby's pure-interpreter time for the benchmark divided by the named interpreter's time (YJIT, MJIT, TruffleRuby). Taller bars mean better performance. Each benchmark is scaled to the CRuby's interpreter's mean result, so CRuby's results are always exactly 1.0.

bench No JIT (ms) No JIT RSD MJIT (ms) MJIT RSD YJIT (ms) YJIT RSD MJIT spd MJIT spd RSD YJIT spd YJIT spd RSD % in YJIT
activerecord 156.3 0.42% 153.7 0.27% 102.5 0.58% 1.02x 0.50% 1.52x 0.72% 85.96%
hexapdf 3182.7 0.90% 2412.8 1.97% 1.32x 2.17% 83.88%
liquid-render 195.1 1.01% 172.6 1.68% 128.1 1.77% 1.13x 1.96% 1.52x 2.04% 85.90%
mail 175.0 0.14% 174.6 1.76% 155.2 0.18% 1.00x 1.76% 1.13x 0.23% 99.34%
psych-load 2447.0 0.02% 2141.3 0.04% 1892.6 0.04% 1.14x 0.04% 1.29x 0.04% 88.89%
railsbench 2772.7 0.82% 2800.6 0.50% 2065.9 1.14% 0.99x 0.96% 1.34x 1.40% 86.54%
binarytrees 466.0 0.09% 325.9 2.20% 369.1 0.11% 1.43x 2.20% 1.26x 0.14% 84.27%
chunky_png 970.0 0.04% 775.9 0.05% 733.1 0.05% 1.25x 0.07% 1.32x 0.07% 99.95%
erubi 374.3 0.71% 342.1 0.68% 324.5 0.61% 1.09x 0.98% 1.15x 0.94% 100.00%
erubi_rails 27.1 2.60% 27.2 2.45% 19.3 3.48% 1.00x 3.58% 1.41x 4.35% 86.41%
fannkuchredux 5483.9 0.08% 2492.0 0.29% 2364.9 0.22% 2.20x 0.30% 2.32x 0.23% 77.42%
lee 1274.9 0.69% 1060.7 0.42% 973.0 0.05% 1.20x 0.81% 1.31x 0.69% 99.97%
nbody 139.4 0.12% 75.9 0.23% 94.9 0.10% 1.84x 0.26% 1.47x 0.16% 100.00%
optcarrot 6279.6 0.42% 2803.4 0.60% 3733.0 0.56% 2.24x 0.73% 1.68x 0.70% 96.16%
rubykon 12545.1 0.66% 8453.7 0.57% 6945.7 1.10% 1.48x 0.87% 1.81x 1.29% 99.74%
30k_ifelse 2408.5 0.04% 3683.3 3.55% 353.5 0.08% 0.65x 3.55% 6.81x 0.09% 100.00%
30k_methods 6239.3 0.15% 10063.2 16.98% 870.8 0.02% 0.62x 16.98% 7.16x 0.15% 100.00%
cfunc_itself 105.0 0.24% 71.6 0.57% 46.5 0.55% 1.47x 0.62% 2.26x 0.61% 100.00%
fib 235.6 0.05% 86.2 0.21% 64.1 0.05% 2.73x 0.22% 3.67x 0.07% 100.00%
getivar 106.8 0.57% 32.3 53.58% 44.3 0.08% 3.31x 53.58% 2.41x 0.58% 99.03%
keyword_args 281.3 0.11% 233.2 1.59% 56.6 0.14% 1.21x 1.59% 4.97x 0.18% 100.00%
respond_to 281.4 0.53% 226.8 1.14% 189.4 0.53% 1.24x 1.25% 1.49x 0.75% 100.00%
setivar 83.4 0.26% 20.2 60.97% 50.1 0.24% 4.14x 60.97% 1.67x 0.35% 99.17%
str_concat 83.2 1.12% 53.2 1.41% 44.8 1.64% 1.57x 1.80% 1.86x 1.98% 99.86%

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 and the yjit-extra-benchmarks Github repo.
Our benchmark-runner and reporting code is in the yjit-metrics Github repo.

Tested Ruby version for YJIT and No-JIT: ruby 3.2.0dev (2022-08-14T10:45:55Z master cb12d7c71b) +YJIT [x86_64-linux]
Tested Ruby version for Ruby latest MJIT: ruby 3.2.0dev (2022-08-14T10:45:55Z master cb12d7c71b) +MJIT [x86_64-linux]

Benchmark Memory Usage Details

bench No JIT mem (MiB) MJIT mem (MiB) YJIT mem (MiB)
activerecord 65 65 77
hexapdf 291 382
liquid-render 30 35 37
mail 49 53 56
psych-load 35 45 40
railsbench 103 106 133
binarytrees 28 32 30
chunky_png 40 43 46
erubi 98 122 95
erubi_rails 102 103 123
fannkuchredux 24 27 27
lee 32 39 41
nbody 24 26 27
optcarrot 63 70 69
rubykon 51 60 57
30k_ifelse 66 169 123
30k_methods 58 180 79
cfunc_itself 24 27 27
fib 24 27 26
getivar 24 26 27
keyword_args 24 27 26
respond_to 24 27 26
setivar 24 26 27
str_concat 103 110 109

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 No JIT warmups No JIT iters MJIT warmups MJIT iters YJIT warmups YJIT iters
activerecord 5 189 75 189 20 189
hexapdf 5 15 20 15
liquid-render 5 146 75 146 20 146
mail 5 126 75 126 20 126
psych-load 5 15 75 15 20 15
railsbench 5 15 75 15 20 15
binarytrees 5 60 75 60 20 60
chunky_png 5 30 75 30 20 30
erubi 5 62 75 62 20 62
erubi_rails 5 1024 75 1024 20 1024
fannkuchredux 5 15 75 15 20 15
lee 5 20 75 20 20 20
nbody 5 263 75 263 20 263
optcarrot 5 15 75 15 20 15
rubykon 5 15 35 15 20 15
30k_ifelse 5 55 75 55 20 55
30k_methods 5 22 29 22 20 22
cfunc_itself 5 429 75 429 20 429
fib 5 315 75 315 20 315
getivar 5 618 75 618 20 618
keyword_args 5 368 75 368 20 368
respond_to 5 107 75 107 20 107
setivar 5 993 75 993 20 993
str_concat 5 446 75 446 20 446

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 column headings for descriptions of each statistic.

bench Exit Report Inline Outlined Comp iSeqs Comp Blocks Inval Inval Ratio Bind Alloc Bind Set Const Bumps
activerecord (click) 1035419 778963 131 1273 0 0% 0 0 0
hexapdf (click) 1150299 923940 682 8006 9 0% 0 0 0
liquid-render (click) 519643 404523 150 1678 2 0% 0 0 0
mail (click) 901019 651039 374 5350 17 0% 0 0 0
psych-load (click) 347035 263130 68 480 1 0% 0 0 0
railsbench (click) 2653787 1965628 1436 10000 16 0% 0 0 0
binarytrees (click) 171867 128248 13 58 0 0% 0 0 0
chunky_png (click) 386267 289306 88 996 0 0% 0 0 0
erubi (click) 322779 245939 10 79 0 0% 0 0 0
erubi_rails (click) 1960539 1427664 300 2035 4 0% 0 0 0
fannkuchredux (click) 185819 138016 10 196 0 0% 0 0 0
lee (click) 385179 290709 58 632 0 0% 0 0 0
nbody (click) 182491 137443 12 171 0 0% 0 0 0
optcarrot (click) 513883 442610 207 3588 20 0% 0 0 0
rubykon (click) 323419 258847 144 1595 1 0% 0 0 0
30k_ifelse (click) 5560923 4348716 9265 57804 0 0% 0 0 0
30k_methods (click) 2176091 1657178 5784 19361 0 0% 0 0 0
cfunc_itself (click) 170395 127021 10 49 0 0% 0 0 0
fib (click) 168859 126629 10 38 0 0% 0 0 0
getivar (click) 170587 128716 10 65 0 0% 0 0 0
keyword_args (click) 170779 127366 11 51 0 0% 0 0 0
respond_to (click) 172507 128475 10 64 0 0% 0 0 0
setivar (click) 170267 127251 10 38 0 0% 0 0 0
str_concat (click) 170075 127572 12 62 0 0% 0 0 0

YJIT stats correspond to the YJIT stats exit report.

Raw JSON data files

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