Implement libfunc profiler.

[azteca1998]

Implementation of a libfunc profiler.

For each executed libfunc, generates:

• Number of samples.
• Total number of ticks.
• Average number of ticks.
• Standard deviation.
• Quartiles (0%, 25%, 50%, 75%, 100%).

Also implements an outlier detection system to filter out operating system noise.

Note: The x86_64 architecture handles context switches between cores correctly, but in aarch64 this is impossible. Results may not be reliable in aarch64.

Output Example:

[2]
    Total Samples:          281
    Total Execution Time:   111
    Average Execution Time: 0.39501779359430605
    Standard Deviation:     0.23897873633819258
    Quartiles:              [0, 0, 0, 1, 1]

Where [2] refers to the libfunc id.

Checklist

• Linked to Github Issue
• Unit tests added
• Integration tests added.
• This change requires new documentation.
  • Documentation has been added/updated.

[github-actions]

Benchmarking results

Benchmark for program dict_insert

Open benchmarks

Command	Mean [s]	Min [s]	Max [s]	Relative
Cairo-vm (Rust, Cairo 1)	11.388 ± 0.061	11.329	11.498	2.27 ± 0.02
cairo-native (embedded AOT)	5.014 ± 0.021	4.980	5.050	1.00
cairo-native (embedded JIT using LLVM's ORC Engine)	5.113 ± 0.032	5.069	5.174	1.02 ± 0.01

Benchmark for program dict_snapshot

Open benchmarks

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
Cairo-vm (Rust, Cairo 1)	810.6 ± 8.0	798.6	822.4	1.00
cairo-native (embedded AOT)	4914.7 ± 27.8	4865.0	4957.1	6.06 ± 0.07
cairo-native (embedded JIT using LLVM's ORC Engine)	5027.0 ± 30.3	4987.5	5087.9	6.20 ± 0.07

Benchmark for program factorial_2M

Open benchmarks

Command	Mean [s]	Min [s]	Max [s]	Relative
Cairo-vm (Rust, Cairo 1)	5.259 ± 0.019	5.229	5.290	1.00
cairo-native (embedded AOT)	5.305 ± 0.024	5.268	5.348	1.01 ± 0.01
cairo-native (embedded JIT using LLVM's ORC Engine)	5.374 ± 0.041	5.316	5.465	1.02 ± 0.01

Benchmark for program fib_2M

Open benchmarks

Command	Mean [s]	Min [s]	Max [s]	Relative
Cairo-vm (Rust, Cairo 1)	5.116 ± 0.011	5.103	5.132	1.06 ± 0.01
cairo-native (embedded AOT)	4.835 ± 0.021	4.809	4.866	1.00
cairo-native (embedded JIT using LLVM's ORC Engine)	4.878 ± 0.024	4.835	4.910	1.01 ± 0.01

Benchmark for program linear_search

Open benchmarks

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
Cairo-vm (Rust, Cairo 1)	832.8 ± 4.6	824.3	838.6	1.00
cairo-native (embedded AOT)	4984.5 ± 19.6	4948.1	5011.7	5.99 ± 0.04
cairo-native (embedded JIT using LLVM's ORC Engine)	5110.3 ± 33.6	5069.3	5163.4	6.14 ± 0.05

Benchmark for program logistic_map

Open benchmarks

Command	Mean [ms]	Min [ms]	Max [ms]	Relative
Cairo-vm (Rust, Cairo 1)	539.1 ± 3.4	534.3	545.7	1.00
cairo-native (embedded AOT)	5025.6 ± 31.4	4965.9	5058.4	9.32 ± 0.08
cairo-native (embedded JIT using LLVM's ORC Engine)	5209.6 ± 24.5	5178.4	5257.8	9.66 ± 0.08

[github-actions]

Benchmark results Main vs HEAD.

Base

Command	Mean [s]	Min [s]	Max [s]	Relative
base dict_insert.cairo (JIT)	5.177 ± 0.039	5.117	5.229	1.02 ± 0.02
base dict_insert.cairo (AOT)	5.084 ± 0.067	4.976	5.149	1.00

Head

Command	Mean [s]	Min [s]	Max [s]	Relative
head dict_insert.cairo (JIT)	5.127 ± 0.019	5.092	5.151	1.01 ± 0.01
head dict_insert.cairo (AOT)	5.075 ± 0.066	5.018	5.230	1.00

Base

Command	Mean [s]	Min [s]	Max [s]	Relative
base dict_snapshot.cairo (JIT)	4.987 ± 0.029	4.922	5.018	1.02 ± 0.01
base dict_snapshot.cairo (AOT)	4.880 ± 0.033	4.824	4.920	1.00

Head

Command	Mean [s]	Min [s]	Max [s]	Relative
head dict_snapshot.cairo (JIT)	5.034 ± 0.025	5.006	5.082	1.02 ± 0.01
head dict_snapshot.cairo (AOT)	4.940 ± 0.023	4.909	4.992	1.00

Base

Command	Mean [s]	Min [s]	Max [s]	Relative
base factorial_2M.cairo (JIT)	5.447 ± 0.016	5.430	5.476	1.03 ± 0.00
base factorial_2M.cairo (AOT)	5.282 ± 0.018	5.252	5.306	1.00

Head

Command	Mean [s]	Min [s]	Max [s]	Relative
head factorial_2M.cairo (JIT)	5.403 ± 0.019	5.379	5.442	1.01 ± 0.01
head factorial_2M.cairo (AOT)	5.355 ± 0.034	5.306	5.403	1.00

Base

Command	Mean [s]	Min [s]	Max [s]	Relative
base fib_2M.cairo (JIT)	4.844 ± 0.024	4.801	4.879	1.01 ± 0.01
base fib_2M.cairo (AOT)	4.791 ± 0.042	4.741	4.876	1.00

Head

Command	Mean [s]	Min [s]	Max [s]	Relative
head fib_2M.cairo (JIT)	4.930 ± 0.030	4.885	4.976	1.01 ± 0.01
head fib_2M.cairo (AOT)	4.895 ± 0.029	4.838	4.928	1.00

Base

Command	Mean [s]	Min [s]	Max [s]	Relative
base linear_search.cairo (JIT)	5.092 ± 0.037	5.010	5.136	1.02 ± 0.01
base linear_search.cairo (AOT)	5.002 ± 0.053	4.913	5.073	1.00

Head

Command	Mean [s]	Min [s]	Max [s]	Relative
head linear_search.cairo (JIT)	5.136 ± 0.024	5.105	5.180	1.03 ± 0.01
head linear_search.cairo (AOT)	5.000 ± 0.022	4.956	5.035	1.00

Base

Command	Mean [s]	Min [s]	Max [s]	Relative
base logistic_map.cairo (JIT)	5.201 ± 0.076	5.109	5.318	1.05 ± 0.02
base logistic_map.cairo (AOT)	4.952 ± 0.038	4.916	5.029	1.00

Head

Command	Mean [s]	Min [s]	Max [s]	Relative
head logistic_map.cairo (JIT)	5.254 ± 0.029	5.202	5.288	1.04 ± 0.01
head logistic_map.cairo (AOT)	5.069 ± 0.052	4.988	5.137	1.00

[codecov-commenter]

Codecov Report

Attention: Patch coverage is 85.04673% with 48 lines in your changes missing coverage. Please review.

Please upload report for BASE (main@b92123c). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
src/libfuncs/starknet.rs	27.27%	32 Missing ⚠️
src/libfuncs/bounded_int.rs	52.94%	8 Missing ⚠️
src/libfuncs/cast.rs	72.72%	3 Missing ⚠️
src/libfuncs/coupon.rs	0.00%	2 Missing ⚠️
src/libfuncs/enum.rs	66.66%	2 Missing ⚠️
src/libfuncs/bytes31.rs	75.00%	1 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #946   +/-   ##
=======================================
  Coverage        ?   80.21%           
=======================================
  Files           ?      112           
  Lines           ?    29880           
  Branches        ?        0           
=======================================
  Hits            ?    23967           
  Misses          ?     5913           
  Partials        ?        0           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[FrancoGiachetta]

All comments were resolved

[JulianGCalderon]

LGTM

[JulianGCalderon]

These changes were squashed in #1253.