Skip to content

Name the GPU a benchmark used; add an Arm data point #13

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jacotay7 merged 1 commit into from
Oct 7, 2026
Merged

Name the GPU a benchmark used; add an Arm data point #13

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,20 @@ All notable changes to `makewfs` are documented here.

## [Unreleased]

### Fixed

- **Benchmark artifacts named the wrong GPU on multi-GPU hosts.**
`benchmarks/run.py` recorded the first line of `nvidia-smi`, which ignores
`CUDA_VISIBLE_DEVICES`. It now asks CuPy for the device the run used. On
Arm hosts, whose `/proc/cpuinfo` has no model name, it reads the CPU model
from `lscpu` (e.g. `Neoverse-N1`) instead of reporting `aarch64`.

### Added

- **Arm benchmark data point** (`benchmarks/device-results-neoverse-n1.*`): the
device table on an Ampere Neoverse-N1 host (16 pinned cores) with an RTX
4060 and an RTX A400.

## [2.0.0] - 2026-10-07

### Breaking
Expand Down
357 changes: 357 additions & 0 deletions benchmarks/device-results-neoverse-n1-rtx4060.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,357 @@
{
"schema_version": 2,
"generated_at_utc": "2026-10-07T07:11:47.632479+00:00",
"command": "/home/jtaylor/miniforge3/envs/aosim-bench/bin/python benchmarks/run.py --device both --frames 100 --config benchmarks/configs/pyramid_40_float32.toml --config benchmarks/configs/pyramid_60_mod8_float32.toml --config benchmarks/configs/pyramid_80_mod32_float64.toml --config benchmarks/configs/shack_hartmann_20x20_float32.toml --config benchmarks/configs/shack_hartmann_60x60_float64.toml --config benchmarks/configs/shack_hartmann_quadrature_9sample.toml --output /home/jtaylor/aosim-bench-logs/artifacts/makewfs-device-table-rtx4060.json",
"revision": "74b53697569dc8b2b5ce93f0b66e39a1de3b303d",
"source_dirty": true,
"python": "3.13.15 | packaged by conda-forge | (main, Sep 2 2026, 22:02:03) [GCC 15.3.0]",
"platform": "Linux-6.17.9-76061709-generic-aarch64-with-glibc2.39",
"processor": "aarch64",
"cpu": "Neoverse-N1",
"gpu": "NVIDIA GeForce RTX 4060",
"dependencies": {
"makewfs": "2.0.0",
"numpy": "2.5.3",
"scipy": "1.18.1",
"cupy": "14.2.0",
"getframes": "2.4.0",
"pyturb": "2.2.0"
},
"methodology": {
"frames_per_cell": 100,
"persistent_sensor": true,
"warmup_frames": 1,
"device_resident_opd_rate_and_output": true,
"include_detector_truth": true,
"rng": "a distinct deterministic per-frame seed",
"cuda_synchronization": "before and after each timed region",
"construction_included_in_throughput": false,
"host_transfers_included": false
},
"results": [
{
"config": "benchmarks/configs/pyramid_40_float32.toml",
"sensor": "pyramid",
"device": "cpu",
"shape": [
54,
54
],
"source_states": 1,
"wavelength_samples": 1,
"range_samples": 1,
"modulation_samples": 1,
"modulation_radius_lambda_over_d": 0.0,
"dtype": "float32",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.7629785779863596,
"warm_optical_total_s": 0.06306239901459776,
"warm_optical_frame_s": 0.0006306239901459775,
"warm_detector_total_s": 0.10588375400402583,
"warm_detector_frame_s": 0.0010588375400402584,
"warm_optical_frames_per_s": 1585.7309833210102,
"warm_detector_frames_per_s": 944.4319474751327,
"warm_detector_only_frame_s": 0.00022277187992585822,
"warm_detector_only_frames_per_s": 4488.896894584786,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/pyramid_40_float32.toml",
"sensor": "pyramid",
"device": "gpu",
"shape": [
54,
54
],
"source_states": 1,
"wavelength_samples": 1,
"range_samples": 1,
"modulation_samples": 1,
"modulation_radius_lambda_over_d": 0.0,
"dtype": "float32",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.2768877709750086,
"warm_optical_total_s": 0.13808018100098707,
"warm_optical_frame_s": 0.0013808018100098707,
"warm_detector_total_s": 0.24444962001871318,
"warm_detector_frame_s": 0.0024444962001871316,
"warm_optical_frames_per_s": 724.2168953941706,
"warm_detector_frames_per_s": 409.08224767273015,
"warm_detector_only_frame_s": 0.0006185778399230912,
"warm_detector_only_frames_per_s": 1616.6114197112713,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/pyramid_60_mod8_float32.toml",
"sensor": "pyramid",
"device": "cpu",
"shape": [
80,
80
],
"source_states": 1,
"wavelength_samples": 1,
"range_samples": 1,
"modulation_samples": 8,
"modulation_radius_lambda_over_d": 2.0,
"dtype": "float32",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.07376596701215021,
"warm_optical_total_s": 0.5042883460118901,
"warm_optical_frame_s": 0.005042883460118901,
"warm_detector_total_s": 0.5606069839850534,
"warm_detector_frame_s": 0.005606069839850534,
"warm_optical_frames_per_s": 198.29924841777367,
"warm_detector_frames_per_s": 178.37808457032378,
"warm_detector_only_frame_s": 0.00035893032007152216,
"warm_detector_only_frames_per_s": 2786.056078518904,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/pyramid_60_mod8_float32.toml",
"sensor": "pyramid",
"device": "gpu",
"shape": [
80,
80
],
"source_states": 1,
"wavelength_samples": 1,
"range_samples": 1,
"modulation_samples": 8,
"modulation_radius_lambda_over_d": 2.0,
"dtype": "float32",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.012662593013374135,
"warm_optical_total_s": 0.1342540149926208,
"warm_optical_frame_s": 0.0013425401499262079,
"warm_detector_total_s": 0.2391750770038925,
"warm_detector_frame_s": 0.002391750770038925,
"warm_optical_frames_per_s": 744.8566808634844,
"warm_detector_frames_per_s": 418.10376420772525,
"warm_detector_only_frame_s": 0.0006130585700157099,
"warm_detector_only_frames_per_s": 1631.1655181239448,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/pyramid_80_mod32_float64.toml",
"sensor": "pyramid",
"device": "cpu",
"shape": [
108,
108
],
"source_states": 1,
"wavelength_samples": 1,
"range_samples": 1,
"modulation_samples": 32,
"modulation_radius_lambda_over_d": 3.0,
"dtype": "float64",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.08048216797760688,
"warm_optical_total_s": 8.533555491012521,
"warm_optical_frame_s": 0.0853355549101252,
"warm_detector_total_s": 8.6366516520211,
"warm_detector_frame_s": 0.086366516520211,
"warm_optical_frames_per_s": 11.718444920797582,
"warm_detector_frames_per_s": 11.578561232882254,
"warm_detector_only_frame_s": 0.0006370968700502999,
"warm_detector_only_frames_per_s": 1569.620017001572,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/pyramid_80_mod32_float64.toml",
"sensor": "pyramid",
"device": "gpu",
"shape": [
108,
108
],
"source_states": 1,
"wavelength_samples": 1,
"range_samples": 1,
"modulation_samples": 32,
"modulation_radius_lambda_over_d": 3.0,
"dtype": "float64",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.025755188980838284,
"warm_optical_total_s": 0.4056679999921471,
"warm_optical_frame_s": 0.004056679999921471,
"warm_detector_total_s": 0.4848081910167821,
"warm_detector_frame_s": 0.004848081910167821,
"warm_optical_frames_per_s": 246.50699587331462,
"warm_detector_frames_per_s": 206.26714204285878,
"warm_detector_only_frame_s": 0.0005712536702048964,
"warm_detector_only_frames_per_s": 1750.5357989933289,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/shack_hartmann_20x20_float32.toml",
"sensor": "shack_hartmann",
"device": "cpu",
"shape": [
160,
160
],
"source_states": 1,
"wavelength_samples": 1,
"range_samples": 1,
"modulation_samples": 1,
"modulation_radius_lambda_over_d": 0.0,
"dtype": "float32",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.08199134599999525,
"warm_optical_total_s": 2.28855264998856,
"warm_optical_frame_s": 0.0228855264998856,
"warm_detector_total_s": 2.4490860599908046,
"warm_detector_frame_s": 0.024490860599908047,
"warm_optical_frames_per_s": 43.695739313884644,
"warm_detector_frames_per_s": 40.831558201909594,
"warm_detector_only_frame_s": 0.0010764133499469608,
"warm_detector_only_frames_per_s": 929.0111461821558,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/shack_hartmann_20x20_float32.toml",
"sensor": "shack_hartmann",
"device": "gpu",
"shape": [
160,
160
],
"source_states": 1,
"wavelength_samples": 1,
"range_samples": 1,
"modulation_samples": 1,
"modulation_radius_lambda_over_d": 0.0,
"dtype": "float32",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.01180534201557748,
"warm_optical_total_s": 0.08716972899856046,
"warm_optical_frame_s": 0.0008716972899856046,
"warm_detector_total_s": 0.19479694298934191,
"warm_detector_frame_s": 0.0019479694298934192,
"warm_optical_frames_per_s": 1147.187230576929,
"warm_detector_frames_per_s": 513.3550787060933,
"warm_detector_only_frame_s": 0.0006126053698244505,
"warm_detector_only_frames_per_s": 1632.372240365053,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/shack_hartmann_60x60_float64.toml",
"sensor": "shack_hartmann",
"device": "cpu",
"shape": [
360,
360
],
"source_states": 1,
"wavelength_samples": 1,
"range_samples": 1,
"modulation_samples": 1,
"modulation_radius_lambda_over_d": 0.0,
"dtype": "float64",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.08440429499023594,
"warm_optical_total_s": 8.684691948990803,
"warm_optical_frame_s": 0.08684691948990803,
"warm_detector_total_s": 9.488772381999297,
"warm_detector_frame_s": 0.09488772381999297,
"warm_optical_frames_per_s": 11.514513190260066,
"warm_detector_frames_per_s": 10.538771083781636,
"warm_detector_only_frame_s": 0.005910381099965889,
"warm_detector_only_frames_per_s": 169.19382745146018,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/shack_hartmann_60x60_float64.toml",
"sensor": "shack_hartmann",
"device": "gpu",
"shape": [
360,
360
],
"source_states": 1,
"wavelength_samples": 1,
"range_samples": 1,
"modulation_samples": 1,
"modulation_radius_lambda_over_d": 0.0,
"dtype": "float64",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.026143675000639632,
"warm_optical_total_s": 0.4227883660059888,
"warm_optical_frame_s": 0.004227883660059888,
"warm_detector_total_s": 0.4985939179896377,
"warm_detector_frame_s": 0.004985939179896377,
"warm_optical_frames_per_s": 236.52495678791573,
"warm_detector_frames_per_s": 200.5640189178527,
"warm_detector_only_frame_s": 0.0005747833198984153,
"warm_detector_only_frames_per_s": 1739.7860469867767,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/shack_hartmann_quadrature_9sample.toml",
"sensor": "shack_hartmann",
"device": "cpu",
"shape": [
64,
64
],
"source_states": 9,
"wavelength_samples": 3,
"range_samples": 3,
"modulation_samples": 1,
"modulation_radius_lambda_over_d": 0.0,
"dtype": "float32",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.06993808099650778,
"warm_optical_total_s": 1.8203168570180424,
"warm_optical_frame_s": 0.018203168570180422,
"warm_detector_total_s": 1.8593171660031658,
"warm_detector_frame_s": 0.018593171660031656,
"warm_optical_frames_per_s": 54.93549082647914,
"warm_detector_frames_per_s": 53.78318547715153,
"warm_detector_only_frame_s": 0.00024450053984764964,
"warm_detector_only_frames_per_s": 4089.9705195870265,
"python_peak_memory_mib": null
},
{
"config": "benchmarks/configs/shack_hartmann_quadrature_9sample.toml",
"sensor": "shack_hartmann",
"device": "gpu",
"shape": [
64,
64
],
"source_states": 9,
"wavelength_samples": 3,
"range_samples": 3,
"modulation_samples": 1,
"modulation_radius_lambda_over_d": 0.0,
"dtype": "float32",
"fft_workers": 1,
"frames": 100,
"construction_s": 0.014552935026586056,
"warm_optical_total_s": 0.4028777669882402,
"warm_optical_frame_s": 0.004028777669882402,
"warm_detector_total_s": 0.5134580160083715,
"warm_detector_frame_s": 0.005134580160083715,
"warm_optical_frames_per_s": 248.2142431128967,
"warm_detector_frames_per_s": 194.75789038683465,
"warm_detector_only_frame_s": 0.0006140789898927323,
"warm_detector_only_frames_per_s": 1628.4549975804912,
"python_peak_memory_mib": null
}
]
}
Loading
Loading