gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[GH-PAGES] Updated website

Browse Source
This commit is contained in:
Philippe Tillet
2022-04-10 00:41:56 +00:00
parent 226c24346e
commit be39c1e8bc
156 changed files with 292 additions and 292 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
v1.1.2/_sources/getting-started/tutorials/01-vector-add.rst.txt
View File

@@ -237,7 +237,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
3 32768.0 76.800002 76.800002
4 65536.0 127.999995 127.999995
5 131072.0 219.428568 219.428568
6 262144.0 341.333321 384.000001
6 262144.0 341.333321 341.333321
7 524288.0 472.615390 472.615390
8 1048576.0 614.400016 614.400016
9 2097152.0 722.823517 702.171410
@@ -254,7 +254,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 1 minutes 45.701 seconds)
**Total running time of the script:** ( 1 minutes 39.333 seconds)
.. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

18
v1.1.2/_sources/getting-started/tutorials/02-fused-softmax.rst.txt
View File

@@ -286,17 +286,17 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
softmax-performance:
N Triton Torch (native) Torch (jit)
0 256.0 512.000001 546.133347 192.752942
0 256.0 512.000001 546.133347 186.181817
1 384.0 585.142862 585.142862 151.703707
2 512.0 655.360017 585.142849 156.038096
3 640.0 682.666684 640.000002 160.000000
2 512.0 655.360017 606.814814 156.038096
3 640.0 682.666684 640.000002 158.759699
4 768.0 722.823517 646.736871 163.839992
.. ... ... ... ...
93 12160.0 812.359066 405.755985 198.834951
94 12288.0 814.111783 415.661740 198.995960
95 12416.0 812.498981 412.149375 198.755369
96 12544.0 812.566838 412.971190 198.913776
97 12672.0 812.633240 412.097543 199.069228
93 12160.0 812.359066 406.179533 199.038365
94 12288.0 814.111783 415.661740 199.298541
95 12416.0 812.498981 411.722274 198.954424
96 12544.0 812.566838 412.971190 199.111113
97 12672.0 812.633240 412.097543 199.167004
[98 rows x 4 columns]
@@ -314,7 +314,7 @@ In the above plot, we can see that:
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 3 minutes 22.745 seconds)
**Total running time of the script:** ( 3 minutes 21.436 seconds)
.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

40
v1.1.2/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt
View File

@@ -462,37 +462,37 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
matmul-performance:
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 256.0 2.730667 ... 2.978909 2.978909
0 256.0 2.730667 ... 3.276800 2.978909
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 16.384000 16.384000
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 34.028308 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
6 1024.0 49.932191 ... 52.428801 52.428801
7 1152.0 45.242181 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.888887
9 1408.0 64.138541 ... 67.305878 67.305878
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 80.430545 ... 79.526831 79.526831
11 1664.0 63.372618 ... 62.492442 62.061463
12 1792.0 72.512412 ... 72.047592 71.588687
12 1792.0 72.983276 ... 59.154861 71.588687
13 1920.0 69.120002 ... 70.172588 70.172588
14 2048.0 73.908442 ... 76.959706 76.608294
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.251065 ... 76.563695 76.563695
17 2432.0 71.125224 ... 82.874527 84.115159
18 2560.0 77.833728 ... 81.310171 80.511054
19 2688.0 83.737433 ... 89.676257 89.044730
20 2816.0 83.552120 ... 83.074685 82.602666
21 2944.0 82.237674 ... 82.784108 82.784108
22 3072.0 81.825298 ... 87.651868 86.845249
23 3200.0 82.156612 ... 89.761569 88.275863
24 3328.0 79.548391 ... 80.527177 83.710812
25 3456.0 81.683457 ... 91.511426 91.097818
26 3584.0 85.552231 ... 90.549237 96.683219
27 3712.0 85.455380 ... 88.248537 88.640059
28 3840.0 82.778440 ... 87.252072 88.971840
29 3968.0 93.076994 ... 84.094627 91.335278
30 4096.0 86.590337 ... 86.480498 92.182504
16 2304.0 68.251065 ... 76.563695 76.319081
17 2432.0 71.305746 ... 84.877538 84.621881
18 2560.0 77.833728 ... 81.310171 80.709358
19 2688.0 83.737433 ... 89.464755 89.888756
20 2816.0 83.552120 ... 83.712490 82.916747
21 2944.0 81.967162 ... 80.902653 82.102191
22 3072.0 82.062468 ... 88.197981 87.924073
23 3200.0 84.544253 ... 95.380032 94.955488
24 3328.0 82.939284 ... 84.695641 81.162679
25 3456.0 80.061141 ... 82.183044 87.632137
26 3584.0 87.254137 ... 90.460980 94.349836
27 3712.0 85.601834 ... 89.194055 91.313847
28 3840.0 84.100380 ... 84.972723 88.686451
29 3968.0 93.148045 ... 79.236324 80.971427
30 4096.0 91.647477 ... 83.390136 89.181212
[31 rows x 5 columns]
@@ -502,7 +502,7 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 5 minutes 23.977 seconds)
**Total running time of the script:** ( 5 minutes 18.978 seconds)
.. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

62
v1.1.2/_sources/getting-started/tutorials/05-layer-norm.rst.txt
View File

@@ -38,36 +38,36 @@ Layer Normalization
layer-norm-backward:
N Triton Torch Apex
0 1024.0 307.200008 99.902435 315.076934
1 1536.0 351.085717 134.050910 344.523365
2 2048.0 423.724127 159.067963 334.367350
3 2560.0 458.507457 182.314537 330.322572
4 3072.0 515.580429 191.501303 321.956335
5 3584.0 547.872604 208.271186 309.410081
6 4096.0 568.231237 220.907859 300.623865
7 4608.0 500.416301 232.336141 287.251954
8 5120.0 527.381977 243.809526 286.433562
9 5632.0 542.843364 244.869560 291.939522
10 6144.0 548.163546 251.202731 288.000001
11 6656.0 534.260858 256.000009 286.793541
12 7168.0 516.612607 253.734520 277.919225
13 7680.0 490.212752 266.743841 284.444450
14 8192.0 464.794337 258.694729 278.481578
15 8704.0 416.958106 267.472468 284.987724
16 9216.0 431.157889 272.394084 289.887291
17 9728.0 439.683593 280.278512 288.950501
18 10240.0 446.836366 287.438599 289.811322
19 10752.0 430.079980 246.935876 289.941565
20 11264.0 430.471331 245.536784 286.069848
21 11776.0 420.571432 249.447482 288.981596
22 12288.0 418.909088 254.673582 294.323369
23 12800.0 414.016170 254.094291 289.811310
24 13312.0 411.181478 252.360194 289.129403
25 13824.0 404.604870 257.190689 291.799461
26 14336.0 395.475867 256.190622 289.129416
27 14848.0 384.829370 257.479779 289.012175
28 15360.0 377.318326 258.332158 288.225185
29 15872.0 369.832994 261.626369 290.562936
0 1024.0 307.200008 98.303995 303.407414
1 1536.0 351.085717 133.565214 338.201833
2 2048.0 423.724127 158.554837 321.254900
3 2560.0 458.507457 180.705883 328.556154
4 3072.0 515.580429 190.020625 321.956335
5 3584.0 551.384634 206.769233 310.527060
6 4096.0 568.231237 221.905193 301.546004
7 4608.0 498.162157 232.825259 287.251954
8 5120.0 527.381977 241.414550 283.787523
9 5632.0 542.843364 242.671458 288.820505
10 6144.0 548.163546 250.775512 285.767458
11 6656.0 532.479975 255.182111 285.257135
12 7168.0 508.970395 253.360829 275.692317
13 7680.0 481.253256 264.447629 279.272719
14 8192.0 459.364487 258.354805 273.827300
15 8704.0 415.300208 266.789264 284.599455
16 9216.0 428.651187 270.396088 286.879380
17 9728.0 438.033784 282.311967 290.388056
18 10240.0 447.650282 284.774046 287.775181
19 10752.0 431.518385 247.409390 291.250566
20 11264.0 427.746848 242.671458 283.966395
21 11776.0 423.089806 251.221344 291.064881
22 12288.0 418.314886 254.015505 294.029924
23 12800.0 416.824953 254.304635 288.450715
24 13312.0 411.711355 252.360194 289.653667
25 13824.0 405.594132 257.790206 292.056329
26 14336.0 396.844280 254.297107 286.481278
27 14848.0 387.760604 258.600868 290.188916
28 15360.0 375.397138 260.155264 289.583654
29 15872.0 368.758973 263.253636 292.796308
@@ -329,7 +329,7 @@ Layer Normalization
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 2 minutes 11.766 seconds)
**Total running time of the script:** ( 2 minutes 11.437 seconds)
.. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

10
v1.1.2/_sources/getting-started/tutorials/sg_execution_times.rst.txt
View File

@@ -5,16 +5,16 @@
Computation times
=================
**12:44.201** total execution time for **getting-started_tutorials** files:
**12:31.196** total execution time for **getting-started_tutorials** files:
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:23.977 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:18.978 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:22.745 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:21.436 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:11.766 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:11.437 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:45.701 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:39.333 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.011 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+