Skip to content

seams

Benchmarks of ordito.seams against every library that computes the same thing. Each chart shows the time of every library relative to ordito on CUDA (1x, in green): a longer bar took longer. The table under each chart lists every input the function was measured on. See Benchmarks for how to read and reproduce these numbers.

Measured on GPU: NVIDIA GeForce RTX 5090 · CPU: Intel Xeon w7-2495X

Summary

0.1x1x10x100x1000xordito (CUDA): the reference, 1xordito (CUDA)1xMeshLib: 4.1x ordito's time, geometric mean over 1 functions; slower than ordito in 1MeshLib4.1x (1)libigl: 57x ordito's time, geometric mean over 1 functions; slower than ordito in 1libigl57x (1)MeshLab: 217x ordito's time, geometric mean over 4 functions; slower than ordito in 4MeshLab217x (4)PyVista: 365x ordito's time, geometric mean over 1 functions; slower than ordito in 1PyVista365x (1)
Time relative to ordito (CUDA), geometric mean over the seams functions both implement; in parentheses, the number of functions. Log scale. Runs stopped at the time limit are left out.
Values
Library Time relative to ordito Functions compared ordito faster in
MeshLib 4.1x 1 1
libigl 57x 1 1
MeshLab 217x 4 4
PyVista 365x 1 1

crease_edges

0.1x1x10x100x1000x10000xordito (CUDA): 311.9 µs, 1x ordito's timeordito (CUDA)1x · 311.9 µsMeshLib: 2.28 ms, 7.3x ordito's timeMeshLib7.3x · 2.28 msPyVista: 302.15 ms, 969x ordito's timePyVista969x · 302.15 msMeshLab: 347.65 ms, 1115x ordito's timeMeshLab1115x · 347.65 ms
dragon (871 414 faces) · time relative to ordito, log scale
Values
Library Median Relative to ordito
ordito (CUDA) 311.9 µs 1x
MeshLib 2.28 ms 7.3x
PyVista 302.15 ms 969x
MeshLab 347.65 ms 1115x
All inputs
Input ordito (CUDA) MeshLab MeshLib PyVista
sphere_small 145.5 µs
bunny_decimated 142.9 µs 5.06 ms 61.2 µs 6.17 ms
bunny 146.7 µs 22.62 ms 167.5 µs 20.93 ms
dragon 311.9 µs 347.65 ms 2.28 ms 302.15 ms
happy_buddha 368.6 µs 430.73 ms 3.23 ms 382.53 ms
lucy 9.17 ms 13.883 s 354.58 ms 9.524 s

cut_along_edges

0.1x1x10x100x1000xordito (CUDA): 342.9 µs, 1x ordito's timeordito (CUDA)1x · 342.9 µslibigl: 56.88 ms, 166x ordito's timelibigl166x · 56.88 msMeshLab: 309.57 ms, 903x ordito's timeMeshLab903x · 309.57 ms
sphere_large (327 680 faces) · cut_fraction=1.0 · time relative to ordito, log scale
Values
Library Median Relative to ordito
ordito (CUDA) 342.9 µs 1x
libigl 56.88 ms 166x
MeshLab 309.57 ms 903x
All inputs
Input ordito (CUDA) libigl MeshLab
sphere_small cut_fraction=0.25 187.5 µs 9.68 ms
sphere_small cut_fraction=1.0 197.1 µs 3.14 ms 2.87 ms
sphere_med cut_fraction=0.25 207.5 µs 10.20 ms
sphere_med cut_fraction=1.0 277.4 µs 13.69 ms 50.28 ms
sphere_large cut_fraction=0.25 321.3 µs 34.15 ms
sphere_large cut_fraction=1.0 342.9 µs 56.88 ms 309.57 ms

uv_seam_edges

0.1x1x10x100x1000x10000xordito (CUDA): 240.3 µs, 1x ordito's timeordito (CUDA)1x · 240.3 µsMeshLab: 251.98 ms, 1048x ordito's timeMeshLab1048x · 251.98 ms
sphere_large (327 680 faces) · time relative to ordito, log scale
Values
Library Median Relative to ordito
ordito (CUDA) 240.3 µs 1x
MeshLab 251.98 ms 1048x
All inputs
Input ordito (CUDA) MeshLab
sphere_small 315.7 µs 2.82 ms
sphere_med 212.7 µs 50.32 ms
sphere_large 240.3 µs 251.98 ms

uv_seam_vertex_mask

0.1x1x10x100x1000x10000xordito (CUDA): 111.3 µs, 1x ordito's timeordito (CUDA)1x · 111.3 µsMeshLab: 253.29 ms, 2276x ordito's timeMeshLab2276x · 253.29 ms
sphere_large (327 680 faces) · time relative to ordito, log scale
Values
Library Median Relative to ordito
ordito (CUDA) 111.3 µs 1x
MeshLab 253.29 ms 2276x
All inputs
Input ordito (CUDA) MeshLab
sphere_small 93.9 µs 3.43 ms
sphere_med 138.9 µs 51.34 ms
sphere_large 111.3 µs 253.29 ms

Without a reference

No other library computes these, so they have no comparison. ordito (CUDA)'s median time on the largest input it was measured on:

Function Input ordito (CUDA)
seam_edge_vertices sphere_large 17.8 µs