🔥 Super-Simple Includes Benchmark Results

Performance profiling and flamegraphs for the Rust implementation of SSI.

How to read flamegraphs: The width of each box represents the time spent in that function. Click on any box to zoom in and explore the call stack. The y-axis shows the call stack depth.

Generated using cargo-flamegraph and Linux perf.

Benchmark System: AMD Ryzen Threadripper PRO 3945WX 12-Cores

📈 Profiling Analysis

Performance regression analysis comparing current profiling data to the baseline version.

Comparing baseline 0.244.10 to current 0.244.25

Performance Change Summary

Metric Value Interpretation
Total Change -1.4% Overall performance vs baseline 0.244.10
Concentration 8.7% Change concentrated in top 3 functions
Type diffuse Distribution pattern of changes

What This Means

This analysis compares profiling data from baseline 0.244.10 to current 0.244.25 to identify which functions changed and by how much.

Top Contributors

Functions contributing most to performance changes from baseline 0.244.10 to current 0.244.25:

See the Differential flamegraphs for a visual breakdown of which call paths changed between versions.

Aggregate Flamegraphs

Methodology

Profiling data collected using Linux perf record --call-graph=fp at 18,181 Hz sample rate with -C force-frame-pointers=yes on the profiling binary. Frame-pointer mode relies on Fedora's frame-pointer-enabled glibc to produce complete call stacks through library code.

Flamegraphs generated using inferno-flamegraph with Rust symbols demangled via rustfilt to preserve full crate paths.