Created
January 11, 2024 21:40
-
-
Save yifuwang/89f2d1964ebc4999880237ddc04ca180 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
num_params=150 world_size=8 mixed=True Param size: 0.059 GB Copy bandwidth: 67.564 GB/s (gpu ms/iter: 0.869, cpu ms/iter 10.460) | |
num_params=54 world_size=8 mixed=True Param size: 1.453 GB Copy bandwidth: 260.373 GB/s (gpu ms/iter: 5.582, cpu ms/iter 0.572) | |
num_params=54 world_size=8 mixed=True Param size: 0.512 GB Copy bandwidth: 239.585 GB/s (gpu ms/iter: 2.135, cpu ms/iter 0.587) | |
num_params=50 world_size=8 mixed=True Param size: 0.200 GB Copy bandwidth: 205.361 GB/s (gpu ms/iter: 0.976, cpu ms/iter 0.534) | |
num_params=3 world_size=8 mixed=True Param size: 0.983 GB Copy bandwidth: 268.397 GB/s (gpu ms/iter: 3.663, cpu ms/iter 0.084) | |
num_params=9 world_size=8 mixed=True Param size: 0.802 GB Copy bandwidth: 265.240 GB/s (gpu ms/iter: 3.024, cpu ms/iter 0.154) | |
num_params=3 world_size=8 mixed=True Param size: 1.573 GB Copy bandwidth: 268.918 GB/s (gpu ms/iter: 5.849, cpu ms/iter 0.087) | |
num_params=9 world_size=8 mixed=True Param size: 2.248 GB Copy bandwidth: 268.141 GB/s (gpu ms/iter: 8.384, cpu ms/iter 0.151) | |
num_params=150 world_size=128 mixed=True Param size: 0.064 GB Copy bandwidth: 73.237 GB/s (gpu ms/iter: 0.874, cpu ms/iter 10.664) | |
num_params=54 world_size=128 mixed=True Param size: 1.458 GB Copy bandwidth: 259.902 GB/s (gpu ms/iter: 5.609, cpu ms/iter 0.584) | |
num_params=54 world_size=128 mixed=True Param size: 0.515 GB Copy bandwidth: 238.703 GB/s (gpu ms/iter: 2.158, cpu ms/iter 0.612) | |
num_params=50 world_size=128 mixed=True Param size: 0.203 GB Copy bandwidth: 205.144 GB/s (gpu ms/iter: 0.987, cpu ms/iter 0.559) | |
num_params=3 world_size=128 mixed=True Param size: 0.983 GB Copy bandwidth: 270.467 GB/s (gpu ms/iter: 3.635, cpu ms/iter 0.073) | |
num_params=9 world_size=128 mixed=True Param size: 0.802 GB Copy bandwidth: 267.700 GB/s (gpu ms/iter: 2.997, cpu ms/iter 0.133) | |
num_params=3 world_size=128 mixed=True Param size: 1.573 GB Copy bandwidth: 268.913 GB/s (gpu ms/iter: 5.849, cpu ms/iter 0.093) | |
num_params=9 world_size=128 mixed=True Param size: 2.248 GB Copy bandwidth: 266.589 GB/s (gpu ms/iter: 8.433, cpu ms/iter 0.207) | |
num_params=150 world_size=1024 mixed=True Param size: 0.202 GB Copy bandwidth: 135.107 GB/s (gpu ms/iter: 1.495, cpu ms/iter 10.904) | |
num_params=54 world_size=1024 mixed=True Param size: 1.524 GB Copy bandwidth: 258.675 GB/s (gpu ms/iter: 5.890, cpu ms/iter 0.996) | |
num_params=54 world_size=1024 mixed=True Param size: 0.575 GB Copy bandwidth: 238.919 GB/s (gpu ms/iter: 2.408, cpu ms/iter 0.765) | |
num_params=50 world_size=1024 mixed=True Param size: 0.246 GB Copy bandwidth: 209.836 GB/s (gpu ms/iter: 1.172, cpu ms/iter 0.611) | |
num_params=3 world_size=1024 mixed=True Param size: 1.007 GB Copy bandwidth: 270.607 GB/s (gpu ms/iter: 3.720, cpu ms/iter 0.100) | |
num_params=9 world_size=1024 mixed=True Param size: 0.818 GB Copy bandwidth: 266.375 GB/s (gpu ms/iter: 3.071, cpu ms/iter 0.176) | |
num_params=3 world_size=1024 mixed=True Param size: 1.611 GB Copy bandwidth: 270.601 GB/s (gpu ms/iter: 5.952, cpu ms/iter 0.099) | |
num_params=9 world_size=1024 mixed=True Param size: 2.248 GB Copy bandwidth: 268.558 GB/s (gpu ms/iter: 8.371, cpu ms/iter 0.207) | |
num_params=150 world_size=8 mixed=False Param size: 0.035 GB Copy bandwidth: 43.749 GB/s (gpu ms/iter: 0.797, cpu ms/iter 10.531) | |
num_params=54 world_size=8 mixed=False Param size: 0.961 GB Copy bandwidth: 254.084 GB/s (gpu ms/iter: 3.781, cpu ms/iter 0.752) | |
num_params=54 world_size=8 mixed=False Param size: 0.282 GB Copy bandwidth: 216.792 GB/s (gpu ms/iter: 1.299, cpu ms/iter 0.717) | |
num_params=50 world_size=8 mixed=False Param size: 0.149 GB Copy bandwidth: 188.025 GB/s (gpu ms/iter: 0.793, cpu ms/iter 0.633) | |
num_params=3 world_size=8 mixed=False Param size: 0.655 GB Copy bandwidth: 267.793 GB/s (gpu ms/iter: 2.447, cpu ms/iter 0.107) | |
num_params=9 world_size=8 mixed=False Param size: 0.634 GB Copy bandwidth: 264.232 GB/s (gpu ms/iter: 2.401, cpu ms/iter 0.182) | |
num_params=3 world_size=8 mixed=False Param size: 1.049 GB Copy bandwidth: 268.455 GB/s (gpu ms/iter: 3.906, cpu ms/iter 0.089) | |
num_params=9 world_size=8 mixed=False Param size: 1.711 GB Copy bandwidth: 267.633 GB/s (gpu ms/iter: 6.394, cpu ms/iter 0.177) | |
num_params=150 world_size=128 mixed=False Param size: 0.038 GB Copy bandwidth: 46.698 GB/s (gpu ms/iter: 0.807, cpu ms/iter 10.488) | |
num_params=54 world_size=128 mixed=False Param size: 0.963 GB Copy bandwidth: 253.450 GB/s (gpu ms/iter: 3.799, cpu ms/iter 0.655) | |
num_params=54 world_size=128 mixed=False Param size: 0.283 GB Copy bandwidth: 216.857 GB/s (gpu ms/iter: 1.307, cpu ms/iter 0.671) | |
num_params=50 world_size=128 mixed=False Param size: 0.151 GB Copy bandwidth: 189.059 GB/s (gpu ms/iter: 0.799, cpu ms/iter 0.572) | |
num_params=3 world_size=128 mixed=False Param size: 0.655 GB Copy bandwidth: 269.849 GB/s (gpu ms/iter: 2.429, cpu ms/iter 0.078) | |
num_params=9 world_size=128 mixed=False Param size: 0.634 GB Copy bandwidth: 264.501 GB/s (gpu ms/iter: 2.399, cpu ms/iter 0.149) | |
num_params=3 world_size=128 mixed=False Param size: 1.049 GB Copy bandwidth: 268.426 GB/s (gpu ms/iter: 3.906, cpu ms/iter 0.086) | |
num_params=9 world_size=128 mixed=False Param size: 1.711 GB Copy bandwidth: 267.495 GB/s (gpu ms/iter: 6.398, cpu ms/iter 0.170) | |
num_params=150 world_size=1024 mixed=False Param size: 0.122 GB Copy bandwidth: 101.151 GB/s (gpu ms/iter: 1.211, cpu ms/iter 10.476) | |
num_params=54 world_size=1024 mixed=False Param size: 1.000 GB Copy bandwidth: 252.323 GB/s (gpu ms/iter: 3.963, cpu ms/iter 0.633) | |
num_params=54 world_size=1024 mixed=False Param size: 0.318 GB Copy bandwidth: 218.322 GB/s (gpu ms/iter: 1.455, cpu ms/iter 0.622) | |
num_params=50 world_size=1024 mixed=False Param size: 0.185 GB Copy bandwidth: 196.369 GB/s (gpu ms/iter: 0.944, cpu ms/iter 0.576) | |
num_params=3 world_size=1024 mixed=False Param size: 0.671 GB Copy bandwidth: 269.369 GB/s (gpu ms/iter: 2.491, cpu ms/iter 0.076) | |
num_params=9 world_size=1024 mixed=False Param size: 0.645 GB Copy bandwidth: 264.441 GB/s (gpu ms/iter: 2.439, cpu ms/iter 0.140) | |
num_params=3 world_size=1024 mixed=False Param size: 1.074 GB Copy bandwidth: 269.955 GB/s (gpu ms/iter: 3.978, cpu ms/iter 0.073) | |
num_params=9 world_size=1024 mixed=False Param size: 1.711 GB Copy bandwidth: 267.168 GB/s (gpu ms/iter: 6.405, cpu ms/iter 0.147) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment