Graviton3 c7g.8xlarge, 360 GSE165845 arrays: 360/360 GTCs identical between the Rust kernels and the pure-Python paths; 1 worker 78-80 samples/min (pure Python 29.6). Scaling 1->8 workers efficiency 0.87-0.90; above that the 125 MB/s gp3 disk caps the run (~620 samples/min) and, on a RAM disk, a fixed per-worker start-up cost limits a 360-sample batch to efficiency 0.48 at 32 workers (K-025). Worker state is pickled once. docs/validation/P9.md, result JSONs, guide/README/CHANGELOG updates.
74 lines
1.4 KiB
JSON
74 lines
1.4 KiB
JSON
{
|
|
"samples": 360,
|
|
"backend": "rust 1.0.0",
|
|
"cpu_count": 32,
|
|
"machine": "aarch64",
|
|
"runs": [
|
|
{
|
|
"threads": 1,
|
|
"rc": 0,
|
|
"wall_s": 299.1,
|
|
"setup_s": 6.9,
|
|
"per_sample_phase_s": 276.63,
|
|
"samples_per_min": 78.1,
|
|
"samples_per_min_per_core": 78.1,
|
|
"speedup_vs_first": 1.0,
|
|
"efficiency": 1.0
|
|
},
|
|
{
|
|
"threads": 2,
|
|
"rc": 0,
|
|
"wall_s": 166.5,
|
|
"setup_s": 7.1,
|
|
"per_sample_phase_s": 143.78,
|
|
"samples_per_min": 150.2,
|
|
"samples_per_min_per_core": 75.1,
|
|
"speedup_vs_first": 1.92,
|
|
"efficiency": 0.96
|
|
},
|
|
{
|
|
"threads": 4,
|
|
"rc": 0,
|
|
"wall_s": 96.9,
|
|
"setup_s": 6.8,
|
|
"per_sample_phase_s": 74.58,
|
|
"samples_per_min": 289.6,
|
|
"samples_per_min_per_core": 72.4,
|
|
"speedup_vs_first": 3.71,
|
|
"efficiency": 0.927
|
|
},
|
|
{
|
|
"threads": 8,
|
|
"rc": 0,
|
|
"wall_s": 61.9,
|
|
"setup_s": 6.8,
|
|
"per_sample_phase_s": 39.56,
|
|
"samples_per_min": 546.0,
|
|
"samples_per_min_per_core": 68.3,
|
|
"speedup_vs_first": 6.99,
|
|
"efficiency": 0.874
|
|
},
|
|
{
|
|
"threads": 16,
|
|
"rc": 0,
|
|
"wall_s": 57.4,
|
|
"setup_s": 6.9,
|
|
"per_sample_phase_s": 34.98,
|
|
"samples_per_min": 617.5,
|
|
"samples_per_min_per_core": 38.6,
|
|
"speedup_vs_first": 7.91,
|
|
"efficiency": 0.494
|
|
},
|
|
{
|
|
"threads": 32,
|
|
"rc": 0,
|
|
"wall_s": 57.4,
|
|
"setup_s": 6.9,
|
|
"per_sample_phase_s": 34.91,
|
|
"samples_per_min": 618.8,
|
|
"samples_per_min_per_core": 19.3,
|
|
"speedup_vs_first": 7.92,
|
|
"efficiency": 0.247
|
|
}
|
|
]
|
|
} |