mirror of
https://github.com/facebookresearch/pytorch3d.git
synced 2025-08-02 20:02:49 +08:00
60f3c4e7d2
Summary: Cpu implementation for packed to padded and added gradients ``` Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- PACKED_TO_PADDED_2_100_300_1_cpu 138 221 3625 PACKED_TO_PADDED_2_100_300_1_cuda:0 184 261 2716 PACKED_TO_PADDED_2_100_300_16_cpu 555 726 901 PACKED_TO_PADDED_2_100_300_16_cuda:0 179 260 2794 PACKED_TO_PADDED_2_100_3000_1_cpu 396 519 1262 PACKED_TO_PADDED_2_100_3000_1_cuda:0 181 274 2764 PACKED_TO_PADDED_2_100_3000_16_cpu 4517 5003 111 PACKED_TO_PADDED_2_100_3000_16_cuda:0 224 397 2235 PACKED_TO_PADDED_2_1000_300_1_cpu 138 212 3616 PACKED_TO_PADDED_2_1000_300_1_cuda:0 180 282 2775 PACKED_TO_PADDED_2_1000_300_16_cpu 565 711 885 PACKED_TO_PADDED_2_1000_300_16_cuda:0 179 264 2797 PACKED_TO_PADDED_2_1000_3000_1_cpu 389 494 1287 PACKED_TO_PADDED_2_1000_3000_1_cuda:0 180 271 2777 PACKED_TO_PADDED_2_1000_3000_16_cpu 4522 5170 111 PACKED_TO_PADDED_2_1000_3000_16_cuda:0 216 286 2313 PACKED_TO_PADDED_10_100_300_1_cpu 251 345 1995 PACKED_TO_PADDED_10_100_300_1_cuda:0 178 262 2806 PACKED_TO_PADDED_10_100_300_16_cpu 2354 2750 213 PACKED_TO_PADDED_10_100_300_16_cuda:0 178 291 2814 PACKED_TO_PADDED_10_100_3000_1_cpu 1519 1786 330 PACKED_TO_PADDED_10_100_3000_1_cuda:0 179 237 2791 PACKED_TO_PADDED_10_100_3000_16_cpu 24705 25879 21 PACKED_TO_PADDED_10_100_3000_16_cuda:0 228 316 2191 PACKED_TO_PADDED_10_1000_300_1_cpu 261 432 1919 PACKED_TO_PADDED_10_1000_300_1_cuda:0 181 261 2756 PACKED_TO_PADDED_10_1000_300_16_cpu 2349 2770 213 PACKED_TO_PADDED_10_1000_300_16_cuda:0 180 256 2782 PACKED_TO_PADDED_10_1000_3000_1_cpu 1613 1929 310 PACKED_TO_PADDED_10_1000_3000_1_cuda:0 183 253 2739 PACKED_TO_PADDED_10_1000_3000_16_cpu 22041 23653 23 PACKED_TO_PADDED_10_1000_3000_16_cuda:0 220 343 2270 PACKED_TO_PADDED_32_100_300_1_cpu 555 750 901 PACKED_TO_PADDED_32_100_300_1_cuda:0 188 282 2661 PACKED_TO_PADDED_32_100_300_16_cpu 7550 8131 67 PACKED_TO_PADDED_32_100_300_16_cuda:0 181 272 2770 PACKED_TO_PADDED_32_100_3000_1_cpu 4574 6327 110 PACKED_TO_PADDED_32_100_3000_1_cuda:0 173 254 2884 PACKED_TO_PADDED_32_100_3000_16_cpu 70366 72563 8 PACKED_TO_PADDED_32_100_3000_16_cuda:0 349 654 1433 PACKED_TO_PADDED_32_1000_300_1_cpu 612 728 818 PACKED_TO_PADDED_32_1000_300_1_cuda:0 189 295 2647 PACKED_TO_PADDED_32_1000_300_16_cpu 7699 8254 65 PACKED_TO_PADDED_32_1000_300_16_cuda:0 189 311 2646 PACKED_TO_PADDED_32_1000_3000_1_cpu 5105 5261 98 PACKED_TO_PADDED_32_1000_3000_1_cuda:0 191 260 2625 PACKED_TO_PADDED_32_1000_3000_16_cpu 87073 92708 6 PACKED_TO_PADDED_32_1000_3000_16_cuda:0 344 425 1455 -------------------------------------------------------------------------------- Benchmark Avg Time(μs) Peak Time(μs) Iterations -------------------------------------------------------------------------------- PACKED_TO_PADDED_TORCH_2_100_300_1_cpu 492 627 1016 PACKED_TO_PADDED_TORCH_2_100_300_1_cuda:0 768 975 652 PACKED_TO_PADDED_TORCH_2_100_300_16_cpu 659 804 760 PACKED_TO_PADDED_TORCH_2_100_300_16_cuda:0 781 918 641 PACKED_TO_PADDED_TORCH_2_100_3000_1_cpu 624 734 802 PACKED_TO_PADDED_TORCH_2_100_3000_1_cuda:0 778 929 643 PACKED_TO_PADDED_TORCH_2_100_3000_16_cpu 2609 2850 192 PACKED_TO_PADDED_TORCH_2_100_3000_16_cuda:0 758 901 660 PACKED_TO_PADDED_TORCH_2_1000_300_1_cpu 467 612 1072 PACKED_TO_PADDED_TORCH_2_1000_300_1_cuda:0 772 905 648 PACKED_TO_PADDED_TORCH_2_1000_300_16_cpu 689 839 726 PACKED_TO_PADDED_TORCH_2_1000_300_16_cuda:0 789 1143 635 PACKED_TO_PADDED_TORCH_2_1000_3000_1_cpu 629 735 795 PACKED_TO_PADDED_TORCH_2_1000_3000_1_cuda:0 812 916 616 PACKED_TO_PADDED_TORCH_2_1000_3000_16_cpu 2716 3117 185 PACKED_TO_PADDED_TORCH_2_1000_3000_16_cuda:0 844 1288 593 PACKED_TO_PADDED_TORCH_10_100_300_1_cpu 2387 2557 210 PACKED_TO_PADDED_TORCH_10_100_300_1_cuda:0 4112 4993 122 PACKED_TO_PADDED_TORCH_10_100_300_16_cpu 3385 4254 148 PACKED_TO_PADDED_TORCH_10_100_300_16_cuda:0 3959 4902 127 PACKED_TO_PADDED_TORCH_10_100_3000_1_cpu 2918 3105 172 PACKED_TO_PADDED_TORCH_10_100_3000_1_cuda:0 4054 4450 124 PACKED_TO_PADDED_TORCH_10_100_3000_16_cpu 12748 13623 40 PACKED_TO_PADDED_TORCH_10_100_3000_16_cuda:0 4023 4395 125 PACKED_TO_PADDED_TORCH_10_1000_300_1_cpu 2258 2492 222 PACKED_TO_PADDED_TORCH_10_1000_300_1_cuda:0 3997 4312 126 PACKED_TO_PADDED_TORCH_10_1000_300_16_cpu 3404 3597 147 PACKED_TO_PADDED_TORCH_10_1000_300_16_cuda:0 3877 4227 129 PACKED_TO_PADDED_TORCH_10_1000_3000_1_cpu 2789 3054 180 PACKED_TO_PADDED_TORCH_10_1000_3000_1_cuda:0 3821 4402 131 PACKED_TO_PADDED_TORCH_10_1000_3000_16_cpu 11967 12963 42 PACKED_TO_PADDED_TORCH_10_1000_3000_16_cuda:0 3729 4290 135 PACKED_TO_PADDED_TORCH_32_100_300_1_cpu 6933 8152 73 PACKED_TO_PADDED_TORCH_32_100_300_1_cuda:0 11856 12287 43 PACKED_TO_PADDED_TORCH_32_100_300_16_cpu 9895 11205 51 PACKED_TO_PADDED_TORCH_32_100_300_16_cuda:0 12354 13596 41 PACKED_TO_PADDED_TORCH_32_100_3000_1_cpu 9516 10128 53 PACKED_TO_PADDED_TORCH_32_100_3000_1_cuda:0 12917 13597 39 PACKED_TO_PADDED_TORCH_32_100_3000_16_cpu 41209 43783 13 PACKED_TO_PADDED_TORCH_32_100_3000_16_cuda:0 12210 13288 41 PACKED_TO_PADDED_TORCH_32_1000_300_1_cpu 7179 7689 70 PACKED_TO_PADDED_TORCH_32_1000_300_1_cuda:0 11896 12381 43 PACKED_TO_PADDED_TORCH_32_1000_300_16_cpu 10127 15494 50 PACKED_TO_PADDED_TORCH_32_1000_300_16_cuda:0 12034 12817 42 PACKED_TO_PADDED_TORCH_32_1000_3000_1_cpu 8743 10251 58 PACKED_TO_PADDED_TORCH_32_1000_3000_1_cuda:0 12023 12908 42 PACKED_TO_PADDED_TORCH_32_1000_3000_16_cpu 39071 41777 13 PACKED_TO_PADDED_TORCH_32_1000_3000_16_cuda:0 11999 13690 42 -------------------------------------------------------------------------------- ``` Reviewed By: bottler, nikhilaravi, jcjohnson Differential Revision: D19870575 fbshipit-source-id: 23a2477b73373c411899633386c87ab034c3702a
48 lines
1.1 KiB
Python
48 lines
1.1 KiB
Python
#!/usr/bin/env python3
|
|
# Copyright (c) Facebook, Inc. and its affiliates. All rights reserved.
|
|
|
|
|
|
from itertools import product
|
|
import torch
|
|
from fvcore.common.benchmark import benchmark
|
|
|
|
from test_packed_to_padded import TestPackedToPadded
|
|
|
|
|
|
def bm_packed_to_padded() -> None:
|
|
kwargs_list = []
|
|
backend = ["cpu"]
|
|
if torch.cuda.is_available():
|
|
backend.append("cuda:0")
|
|
|
|
num_meshes = [2, 10, 32]
|
|
num_verts = [100, 1000]
|
|
num_faces = [300, 3000]
|
|
num_ds = [0, 1, 16]
|
|
|
|
test_cases = product(num_meshes, num_verts, num_faces, num_ds, backend)
|
|
for case in test_cases:
|
|
n, v, f, d, b = case
|
|
kwargs_list.append(
|
|
{
|
|
"num_meshes": n,
|
|
"num_verts": v,
|
|
"num_faces": f,
|
|
"num_d": d,
|
|
"device": b,
|
|
}
|
|
)
|
|
benchmark(
|
|
TestPackedToPadded.packed_to_padded_with_init,
|
|
"PACKED_TO_PADDED",
|
|
kwargs_list,
|
|
warmup_iters=1,
|
|
)
|
|
|
|
benchmark(
|
|
TestPackedToPadded.packed_to_padded_with_init_torch,
|
|
"PACKED_TO_PADDED_TORCH",
|
|
kwargs_list,
|
|
warmup_iters=1,
|
|
)
|