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
2022-04-14 00:44:57 +00:00
parent 9d65bf62fb
commit 2a53636c23
158 changed files with 346 additions and 346 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
master/_sources/getting-started/tutorials/01-vector-add.rst.txt
View File

@@ -238,19 +238,19 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
vector-add-performance:
size Triton Torch
0 4096.0 4.363636 9.600000
1 8192.0 9.600000 19.200000
2 16384.0 17.454545 38.400001
1 8192.0 8.727273 19.200000
2 16384.0 19.200000 38.400001
3 32768.0 38.400001 76.800002
4 65536.0 69.818181 127.999995
5 131072.0 127.999995 219.428568
4 65536.0 76.800002 127.999995
5 131072.0 139.636363 219.428568
6 262144.0 236.307695 341.333321
7 524288.0 341.333321 472.615390
8 1048576.0 472.615390 614.400016
9 2097152.0 614.400016 702.171410
10 4194304.0 712.347810 780.190482
11 8388608.0 774.047204 812.429770
12 16777216.0 812.429770 833.084721
13 33554432.0 829.569620 842.004273
11 8388608.0 768.000002 812.429770
12 16777216.0 809.086412 833.084721
13 33554432.0 831.323480 842.004273
14 67108864.0 840.205105 848.362445
15 134217728.0 845.625825 850.656574
@@ -260,7 +260,7 @@ 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 41.223 seconds)
**Total running time of the script:** ( 1 minutes 38.363 seconds)
.. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

22
master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt
View File

@@ -278,17 +278,17 @@ 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 188.321838
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
4 768.0 722.823517 646.736871 163.839992
0 256.0 512.000001 546.133347 186.181817
1 384.0 585.142862 585.142862 149.853661
2 512.0 655.360017 585.142849 154.566038
3 640.0 682.666684 640.000002 158.759699
4 768.0 722.823517 646.736871 162.754967
.. ... ... ... ...
93 12160.0 814.058574 405.755985 199.038365
94 12288.0 814.111783 415.222812 199.298541
95 12416.0 814.163950 412.149375 198.954424
96 12544.0 814.214963 412.971190 199.209928
97 12672.0 814.265046 412.097543 199.362843
93 12160.0 815.765209 406.179533 198.530610
94 12288.0 815.800825 416.101597 198.694297
95 12416.0 815.835709 412.577363 198.457532
96 12544.0 814.214963 412.971190 198.618504
97 12672.0 814.265046 412.097543 198.776477
[98 rows x 4 columns]
@@ -306,7 +306,7 @@ In the above plot, we can see that:
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 3 minutes 27.275 seconds)
**Total running time of the script:** ( 3 minutes 24.847 seconds)
.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

66
master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt
View File

@@ -457,38 +457,38 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
.. code-block:: none
matmul-performance:
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 256.0 2.730667 ... 3.276800 2.978909
1 384.0 7.372800 ... 7.899428 8.507077
2 512.0 14.563555 ... 15.420235 16.384000
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 35.389441 34.028308
5 896.0 37.971025 ... 40.140799 40.140799
6 1024.0 49.932191 ... 53.773130 53.773130
7 1152.0 44.566925 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 69.009825 67.305878
10 1536.0 79.526831 ... 79.526831 79.526831
11 1664.0 62.929456 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.142831 63.142831
13 1920.0 68.776119 ... 71.257735 70.892307
14 2048.0 73.262953 ... 78.398206 77.672296
15 2176.0 83.155572 ... 87.494120 86.367588
16 2304.0 68.251065 ... 77.810656 77.558029
17 2432.0 71.125224 ... 75.726318 75.320281
18 2560.0 77.833728 ... 82.331658 82.125311
19 2688.0 83.737433 ... 90.966561 89.888756
20 2816.0 80.767055 ... 83.712490 83.712490
21 2944.0 81.765436 ... 83.477440 83.899046
22 3072.0 81.943708 ... 89.030036 88.820552
23 3200.0 82.901554 ... 92.753621 88.213121
24 3328.0 80.798314 ... 82.369902 86.320498
25 3456.0 80.945348 ... 88.790274 91.200871
26 3584.0 87.127323 ... 100.017124 99.463928
27 3712.0 81.615477 ... 86.641231 88.248537
28 3840.0 82.778440 ... 87.148936 91.322872
29 3968.0 86.051653 ... 85.391135 84.270676
30 4096.0 91.366730 ... 84.149044 90.748973
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 256.0 2.730667 ... 2.978909 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 15.420235 15.420235
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 31.597714 ... 34.028308 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
6 1024.0 49.932191 ... 52.428801 52.428801
7 1152.0 43.911529 ... 46.656000 46.656000
8 1280.0 49.951220 ... 56.888887 56.109587
9 1408.0 62.664092 ... 67.305878 67.305878
10 1536.0 78.643199 ... 78.643199 78.643199
11 1664.0 62.061463 ... 62.492442 62.061463
12 1792.0 71.588687 ... 62.441243 62.096267
13 1920.0 68.098521 ... 70.172588 69.467336
14 2048.0 72.005219 ... 76.608294 76.260072
15 2176.0 81.472263 ... 85.269692 84.909907
16 2304.0 67.289781 ... 76.319081 76.076024
17 2432.0 69.713308 ... 73.932798 73.738752
18 2560.0 76.204654 ... 80.709358 80.313727
19 2688.0 82.284288 ... 89.044730 89.464755
20 2816.0 80.916902 ... 82.916747 82.602666
21 2944.0 80.902653 ... 82.373605 82.373605
22 3072.0 81.005868 ... 88.060814 88.197981
23 3200.0 83.660130 ... 95.522391 94.814812
24 3328.0 82.369902 ... 84.695641 84.795401
25 3456.0 80.783132 ... 91.046379 91.200871
26 3584.0 86.291162 ... 98.591437 98.591437
27 3712.0 84.874549 ... 88.876645 88.876645
28 3840.0 83.845335 ... 92.083268 92.083268
29 3968.0 92.442373 ... 91.678389 91.472214
30 4096.0 93.206754 ... 92.627833 92.980765
[31 rows x 5 columns]
@@ -498,7 +498,7 @@ 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:** ( 6 minutes 49.578 seconds)
**Total running time of the script:** ( 6 minutes 43.515 seconds)
.. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

2
master/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt
View File

@@ -240,7 +240,7 @@ References
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 0 minutes 0.328 seconds)
**Total running time of the script:** ( 0 minutes 0.327 seconds)
.. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

62
master/_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 1024.0 356.173905 99.497980 315.076934
1 1536.0 405.098894 134.050910 344.523365
2 2048.0 491.520012 159.584422 321.254900
3 2560.0 458.507457 182.857144 326.808501
4 3072.0 519.211251 191.501303 319.168834
5 3584.0 551.384634 207.768111 307.199992
6 4096.0 564.965515 220.907859 293.444785
7 4608.0 502.690905 232.336141 290.267724
8 5120.0 527.381977 243.809526 287.102804
9 5632.0 540.671974 244.426754 291.310338
10 6144.0 548.163546 251.202731 288.000001
11 6656.0 532.479975 255.590406 286.279570
12 7168.0 510.480705 253.734520 277.919225
13 7680.0 487.619051 266.743841 284.884090
14 8192.0 468.114289 258.694729 278.481578
15 8704.0 415.300208 267.472468 284.987724
16 9216.0 429.483477 272.394084 290.267724
17 9728.0 438.033784 279.942444 288.950501
18 10240.0 444.412281 287.102804 289.811322
19 10752.0 426.525614 246.699797 290.267711
20 11264.0 426.397479 245.536784 286.372873
21 11776.0 419.323436 249.447482 288.981596
22 12288.0 414.784810 254.673582 294.323369
23 12800.0 410.146863 254.094291 288.180121
24 13312.0 410.125805 252.161013 289.391298
25 13824.0 404.112047 257.190689 291.799461
26 14336.0 395.475867 256.000002 288.644296
27 14848.0 386.080180 257.665934 288.544136
28 15360.0 380.433442 258.513318 286.433562
29 15872.0 372.363640 261.806182 290.562936
0 1024.0 351.085705 98.698793 311.088617
1 1536.0 396.387087 132.604320 341.333333
2 2048.0 481.882362 158.045011 321.254900
3 2560.0 451.764698 181.238943 325.079368
4 3072.0 508.468972 190.511624 317.793096
5 3584.0 547.872604 206.769233 308.301075
6 4096.0 564.965515 219.919464 300.623865
7 4608.0 493.714279 231.364016 285.767436
8 5120.0 518.481012 242.366855 285.767451
9 5632.0 532.157453 243.545956 291.310338
10 6144.0 544.118087 249.925419 286.322318
11 6656.0 530.710976 254.775119 286.279570
12 7168.0 510.480705 252.616738 277.024148
13 7680.0 486.332448 265.590783 284.006166
14 8192.0 467.002371 257.677592 277.303250
15 8704.0 405.623284 266.789264 284.212242
16 9216.0 420.501910 271.391419 289.129410
17 9728.0 428.388977 279.272720 287.881626
18 10240.0 434.973455 286.100109 289.129408
19 10752.0 421.647056 245.760009 289.291486
20 11264.0 423.724120 244.647957 285.465683
21 11776.0 416.849568 248.788725 288.097854
22 12288.0 413.042003 253.578674 293.444785
23 12800.0 408.510626 253.256381 287.371378
24 13312.0 408.552421 251.565353 288.607034
25 13824.0 403.130022 256.197690 291.031592
26 14336.0 395.930964 255.051144 287.919661
27 14848.0 385.245405 256.737757 287.844912
28 15360.0 380.041240 257.610071 285.546077
29 15872.0 372.545726 260.731015 289.679087
@@ -339,7 +339,7 @@ Layer Normalization
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 2 minutes 14.213 seconds)
**Total running time of the script:** ( 2 minutes 15.333 seconds)
.. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

12
master/_sources/getting-started/tutorials/sg_execution_times.rst.txt
View File

@@ -5,16 +5,16 @@
Computation times
=================
**14:12.617** total execution time for **getting-started_tutorials** files:
**14:02.386** total execution time for **getting-started_tutorials** files:
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:49.578 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:43.515 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:27.275 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:24.847 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:14.213 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:15.333 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:41.223 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:38.363 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.328 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.327 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+