# CPU scaling study — measured results

- Window (UTC): 2026-10-28T12:09:55.985334+00:00 to 2026-10-28T12:10:04.800373+00:00
- Host: Linux-7.0.0-38-generic-x86_64-with-glibc2.43; logical CPUs: 2
- Workload sizes: 1,000,000, 5,000,000, 25,000,000, 50,000,000; 8 configurations per size; 3 repetitions per configuration.
- Independent reference prime counts matched at every workload size.

## Best measured settings by scale

| Limit | Prime count | Best threads | Best segment | Median seconds | 2-thread speedup vs best 1-thread |
|---:|---:|---:|---:|---:|---:|
| 1,000,000 | 78,498 | 2 | 16,384 B | 0.0036 | 1.545× |
| 5,000,000 | 348,513 | 2 | 16,384 B | 0.0119 | 1.856× |
| 25,000,000 | 1,565,927 | 2 | 16,384 B | 0.0563 | 1.879× |
| 50,000,000 | 3,001,134 | 2 | 16,384 B | 0.1141 | 1.873× |

## Interpretation

- Compare the full results.csv before choosing a default; the best configuration can differ by scale.
- Use these measurements to configure local batch-oriented searches, while keeping thread count and segment size adjustable.
- Repeat the sweep in a separate session before relying on small differences.

## Limits

- This produces host-specific systems knowledge, not a new mathematical theorem.
- Prime counts are checked against known reference values and must match across all configurations.
- No packages were installed and no service or recurring job was created.