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
2022-04-20 00:43:07 +00:00
parent 245e5ab128
commit 8d0e47d73e
156 changed files with 282 additions and 282 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -234,7 +234,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
size Triton Torch
0 4096.0 9.600000 9.600000
1 8192.0 19.200000 19.200000
2 16384.0 38.400001 38.400001
2 16384.0 31.999999 31.999999
3 32768.0 76.800002 76.800002
4 65536.0 127.999995 127.999995
5 131072.0 219.428568 219.428568
@@ -255,7 +255,7 @@ 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 48.582 seconds)
**Total running time of the script:** ( 1 minutes 46.974 seconds)
.. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

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

@@ -278,16 +278,16 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
softmax-performance:
N Triton Torch (native) Torch (jit)
0 256.0 546.133347 546.133347 188.321838
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 158.759699
4 768.0 722.823517 646.736871 162.754967
2 512.0 655.360017 606.814814 156.038096
3 640.0 682.666684 640.000002 160.000000
4 768.0 722.823517 646.736871 163.839992
.. ... ... ... ...
93 12160.0 814.058574 406.179533 198.834951
94 12288.0 814.111783 415.661740 199.096718
95 12416.0 814.163950 412.149375 198.755369
96 12544.0 814.214963 412.971190 198.913776
93 12160.0 814.058574 405.755985 198.936606
94 12288.0 814.111783 415.222812 199.197579
95 12416.0 814.163950 412.149375 198.954424
96 12544.0 814.214963 412.971190 199.111113
97 12672.0 814.265046 412.097543 199.167004
[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 28.316 seconds)
**Total running time of the script:** ( 3 minutes 28.936 seconds)
.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

48
master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt
View File

@@ -459,36 +459,36 @@ 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 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 16.384000 15.420235
1 384.0 7.372800 ... 7.899428 8.507077
2 512.0 14.563555 ... 16.384000 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 ... 41.321411 40.140799
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
7 1152.0 45.242181 ... 48.161033 47.396572
8 1280.0 51.200001 ... 58.514284 57.690139
9 1408.0 64.138541 ... 69.009825 69.009825
10 1536.0 80.430545 ... 80.430545 80.430545
11 1664.0 63.372618 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.142831 63.142831
13 1920.0 69.120002 ... 71.626943 70.892307
10 1536.0 79.526831 ... 80.430545 80.430545
11 1664.0 62.929456 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.142831 62.790080
13 1920.0 68.776119 ... 71.626943 71.257735
14 2048.0 73.584279 ... 78.398206 78.033565
15 2176.0 83.155572 ... 87.115360 86.739860
16 2304.0 68.251065 ... 77.810656 77.558029
16 2304.0 68.446623 ... 77.810656 77.558029
17 2432.0 71.125224 ... 75.726318 75.320281
18 2560.0 77.833728 ... 81.920002 81.512437
19 2688.0 83.369354 ... 91.404957 90.748936
20 2816.0 83.392363 ... 83.712490 83.873477
21 2944.0 81.967162 ... 83.477440 82.373605
22 3072.0 78.752578 ... 88.612060 87.246694
23 3200.0 79.601989 ... 96.096095 95.952022
24 3328.0 84.003845 ... 85.196803 85.703924
25 3456.0 81.683457 ... 92.350019 92.508971
26 3584.0 84.745889 ... 88.412386 94.250936
27 3712.0 85.675250 ... 87.706180 87.399253
28 3840.0 83.465663 ... 88.332269 91.777595
29 3968.0 88.040360 ... 91.678389 86.788006
30 4096.0 93.531519 ... 83.156833 86.593830
18 2560.0 77.833728 ... 82.125311 81.715711
19 2688.0 83.369354 ... 90.532356 90.748936
20 2816.0 80.916902 ... 83.552120 83.552120
21 2944.0 82.373605 ... 83.617504 83.617504
22 3072.0 81.707223 ... 87.651868 89.593522
23 3200.0 85.219705 ... 96.385543 96.385543
24 3328.0 82.275764 ... 86.011103 85.703924
25 3456.0 81.890873 ... 92.455926 92.138932
26 3584.0 86.623693 ... 89.290361 94.250936
27 3712.0 85.675250 ... 88.092894 84.874549
28 3840.0 84.679936 ... 92.468225 85.136259
29 3968.0 90.724116 ... 84.974886 90.522206
30 4096.0 90.996029 ... 87.438257 92.309303
[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 8.669 seconds)
**Total running time of the script:** ( 6 minutes 10.290 seconds)
.. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

56
master/_sources/getting-started/tutorials/05-layer-norm.rst.txt
View File

@@ -40,34 +40,34 @@ Layer Normalization
N Triton Torch Apex
0 1024.0 361.411758 99.902435 315.076934
1 1536.0 409.599994 134.050910 344.523365
2 2048.0 491.520012 159.067963 334.367350
3 2560.0 458.507457 182.857144 330.322572
4 3072.0 522.893629 191.501303 321.956335
5 3584.0 554.941930 207.768111 309.410081
6 4096.0 564.965515 220.907859 299.707322
2 2048.0 496.484863 159.067963 323.368435
3 2560.0 461.954908 182.857144 325.079368
4 3072.0 519.211251 191.501303 320.556515
5 3584.0 554.941930 207.768111 310.527060
6 4096.0 564.965515 220.907859 301.546004
7 4608.0 502.690905 232.336141 287.251954
8 5120.0 529.655159 243.809526 287.102804
9 5632.0 542.843364 244.426754 291.939522
10 6144.0 552.269672 251.202731 288.000001
11 6656.0 532.479975 255.590406 286.793541
12 7168.0 512.000004 253.734520 277.919225
13 7680.0 487.619051 266.743841 284.444450
14 8192.0 468.114289 258.694729 278.481578
15 8704.0 414.476194 267.815384 285.377055
16 9216.0 429.483477 272.394084 290.267724
17 9728.0 438.033784 280.278512 288.950501
18 10240.0 444.412281 287.102804 290.153487
19 10752.0 426.525614 246.699797 289.941565
20 11264.0 427.071098 245.536784 286.372873
21 11776.0 418.702211 249.667843 288.981596
22 12288.0 415.369018 254.893699 294.323369
23 12800.0 410.695192 254.094291 289.538159
24 13312.0 409.599999 252.559690 289.391298
25 13824.0 404.112047 257.190689 292.056329
26 14336.0 396.387109 256.190622 288.886653
27 14848.0 385.662341 257.665934 288.777966
28 15360.0 378.869469 258.513318 287.775181
29 15872.0 372.000001 261.626369 290.341468
8 5120.0 529.655159 243.809526 286.433562
9 5632.0 542.843364 244.869560 291.310338
10 6144.0 550.208948 251.202731 287.438593
11 6656.0 534.260858 256.000009 286.793541
12 7168.0 510.480705 253.734520 277.919225
13 7680.0 487.619051 266.743841 285.325090
14 8192.0 468.114289 258.354805 278.087683
15 8704.0 415.300208 267.815384 285.377055
16 9216.0 430.319054 272.059034 290.267724
17 9728.0 438.033784 279.942444 288.950501
18 10240.0 445.217381 287.438599 290.840246
19 10752.0 427.231788 246.935876 289.941565
20 11264.0 427.746848 245.536784 286.372873
21 11776.0 419.323436 249.447482 288.981596
22 12288.0 415.954875 254.673582 294.323369
23 12800.0 410.695192 254.094291 289.811310
24 13312.0 410.125805 252.559690 289.391298
25 13824.0 404.604870 257.190689 291.799461
26 14336.0 396.844280 256.000002 289.129416
27 14848.0 386.080180 257.665934 289.012175
28 15360.0 378.869469 258.332158 287.550706
29 15872.0 372.363640 261.626369 290.562936
@@ -339,7 +339,7 @@ Layer Normalization
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 2 minutes 13.855 seconds)
**Total running time of the script:** ( 2 minutes 14.494 seconds)
.. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

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

@@ -5,16 +5,16 @@
Computation times
=================
**13:39.434** total execution time for **getting-started_tutorials** files:
**13:40.705** total execution time for **getting-started_tutorials** files:
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:08.669 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:10.290 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:28.316 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:28.936 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:13.855 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:14.494 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:48.582 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:46.974 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.012 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+