Executed in Nanoseconds
Sub-microsecond execution times across 55 operations. Real benchmarks from real hardware.
Last run: January 1, 2026 at 12:24 AM UTC
Execution Performance
Average execution times across key operation categories.
Compiler Operations
Circuit canonicalization and compilation
Backend Execution
ISA instructions and Unit Group operations
Speed Comparison
Direct visual comparison against common reference times.
Compiler Operations
Circuit canonicalization and compilation
Backend Execution
ISA instructions and Unit Group operations
Throughput Capacity
Operations per second at average execution times. Higher throughput enables real-time processing at scale.
Compiler Operations
Circuit canonicalization and compilation
Backend Execution
ISA instructions and Unit Group operations
Speed in Context
Nanoseconds are abstract. Here's what they mean.
Human neural processing: ~13ms. Homgram O(1) lookup: ~734.0 ns.
One blink (300ms) = 408,719 Homgram lookups.
Homgram lookups possible in a single 50ms heartbeat interval.
Light travels 220m during one Homgram lookup.
Algorithmic Advantage
Homgram O(1) lookup vs traditional O(n²)/O(n³) approaches (logarithmic scale)
What We Benchmark
Comprehensive testing across all Homgram subsystems. Each category measures specific performance characteristics.
Compiler
2 benchmarks
Measures time to normalize circuits via 96-class geometric system and compile them for execution.
Buffer Operations
2 benchmarks
Buffer allocation and memory operations
Other
51 benchmarks
Cache analysis, character products, orbit operations, address computation, and type dispatch benchmarks.
Performance Visualized
Side-by-side comparison of execution times. Shorter bars = faster operations.
Compiler Operations
Circuit canonicalization and compilation via the 96-class geometric system. These operations enable O(1) lookup times for circuit transformations.
Backend Execution
ISA instruction execution and Unit Group operations across multiple precision types (i8, f16, f32, f64). These form the computational foundation for Homgram.
All Benchmarks
Detailed statistics by category. Click any card for confidence intervals and throughput data.
Compiler
Circuit compilation and canonicalization
Buffer Operations
Buffer allocation and memory operations
Other
Uncategorized benchmarks
Methodology
Transparent, reproducible, verifiable. All benchmarks run with criterion.rs using 100 sample iterations with 10 warmup iterations excluded.
44a2366See For Yourself
Clone the repo. Run the benchmarks. Verify the numbers. The speed is real.