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
2022-04-27 00:47:37 +00:00
parent b0a569b724
commit 9bf9b2f3d8
158 changed files with 302 additions and 302 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
master/.buildinfo
View File

@@ -1,4 +1,4 @@
# Sphinx build info version 1
# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
config: 5487c70acc23e996dced6a75eee6007c
config: 6a48eed9bde50fff8021e8a13e516902
tags: 645f666f9bcd5a90fca523b33c5a78b7

BIN
master/.doctrees/environment.pickle
View File

Binary file not shown.

BIN
master/.doctrees/getting-started/installation.doctree
View File

Binary file not shown.

BIN
master/.doctrees/getting-started/tutorials/01-vector-add.doctree
View File

Binary file not shown.

BIN
master/.doctrees/getting-started/tutorials/02-fused-softmax.doctree
View File

Binary file not shown.

BIN
master/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree
View File

Binary file not shown.

BIN
master/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree
View File

Binary file not shown.

BIN
master/.doctrees/getting-started/tutorials/05-layer-norm.doctree
View File

Binary file not shown.

BIN
master/.doctrees/getting-started/tutorials/index.doctree
View File

Binary file not shown.

BIN
master/.doctrees/getting-started/tutorials/sg_execution_times.doctree
View File

Binary file not shown.

BIN
master/.doctrees/index.doctree
View File

Binary file not shown.

BIN
master/.doctrees/programming-guide/chapter-1/introduction.doctree
View File

Binary file not shown.

BIN
master/.doctrees/programming-guide/chapter-2/related-work.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.Config.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.autotune.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.heuristics.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.jit.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.arange.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.atomic_add.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.atomic_cas.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.atomic_max.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.atomic_min.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.atomic_xchg.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.broadcast_to.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.cos.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.dot.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.exp.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.load.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.log.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.max.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.maximum.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.min.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.minimum.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.multiple_of.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.num_programs.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.program_id.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.rand.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.randint.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.randint4x.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.randn.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.ravel.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.reshape.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.sigmoid.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.sin.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.softmax.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.sqrt.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.store.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.sum.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.where.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.language.zeros.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.testing.Benchmark.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.testing.do_bench.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/generated/triton.testing.perf_report.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/triton.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/triton.language.doctree
View File

Binary file not shown.

BIN
master/.doctrees/python-api/triton.testing.doctree
View File

Binary file not shown.

BIN
master/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip
View File

Binary file not shown.

BIN
master/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip
View File

Binary file not shown.

BIN
master/_images/sphx_glr_01-vector-add_001.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 23 KiB

After

Width:  |  Height:  |  Size: 22 KiB

BIN
master/_images/sphx_glr_01-vector-add_thumb.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 15 KiB

After

Width:  |  Height:  |  Size: 15 KiB

BIN
master/_images/sphx_glr_02-fused-softmax_001.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 42 KiB

After

Width:  |  Height:  |  Size: 37 KiB

BIN
master/_images/sphx_glr_02-fused-softmax_thumb.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 25 KiB

After

Width:  |  Height:  |  Size: 23 KiB

BIN
master/_images/sphx_glr_03-matrix-multiplication_001.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 57 KiB

After

Width:  |  Height:  |  Size: 57 KiB

BIN
master/_images/sphx_glr_03-matrix-multiplication_thumb.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 33 KiB

After

Width:  |  Height:  |  Size: 33 KiB

BIN
master/_images/sphx_glr_05-layer-norm_001.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 34 KiB

After

Width:  |  Height:  |  Size: 33 KiB

BIN
master/_images/sphx_glr_05-layer-norm_thumb.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 21 KiB

After

Width:  |  Height:  |  Size: 21 KiB

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

@@ -235,7 +235,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
0 4096.0 9.600000 9.600000
1 8192.0 19.200000 19.200000
2 16384.0 38.400001 38.400001
3 32768.0 63.999998 76.800002
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 341.333321
@@ -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 41.030 seconds)
**Total running time of the script:** ( 1 minutes 49.234 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 512.000001 190.511628
1 384.0 438.857137 585.142862 151.703707
2 512.0 481.882344 606.814814 154.566038
3 640.0 465.454542 640.000002 158.759699
4 768.0 463.698115 664.216187 162.754967
0 256.0 546.133347 512.000001 188.321838
1 384.0 585.142862 585.142862 151.703707
2 512.0 655.360017 606.814814 154.566038
3 640.0 682.666684 640.000002 158.759699
4 768.0 722.823517 664.216187 162.754967
.. ... ... ... ...
93 12160.0 478.622374 405.333344 198.834951
94 12288.0 487.256521 415.661740 199.096718
95 12416.0 459.851851 411.722274 198.755369
96 12544.0 458.228323 412.971190 199.012395
97 12672.0 457.679461 412.097543 199.069228
93 12160.0 814.058574 405.755985 198.936606
94 12288.0 814.111783 415.442160 199.096718
95 12416.0 814.163950 411.296057 198.854847
96 12544.0 814.214963 412.971190 198.913776
97 12672.0 814.265046 412.097543 199.069228
[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 8.844 seconds)
**Total running time of the script:** ( 3 minutes 28.564 seconds)
.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -463,32 +463,32 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
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 39.025776
6 1024.0 49.932191 ... 53.773130 52.428801
5 896.0 37.971025 ... 40.140799 40.140799
6 1024.0 49.932191 ... 53.773130 53.773130
7 1152.0 45.242181 ... 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
9 1408.0 64.138541 ... 68.147202 67.305878
10 1536.0 79.526831 ... 80.430545 80.430545
11 1664.0 63.372618 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.499573 63.142831
13 1920.0 68.776119 ... 71.626943 71.257735
14 2048.0 73.584279 ... 78.398206 78.033565
15 2176.0 83.500614 ... 87.115360 86.739860
16 2304.0 68.251065 ... 77.810656 77.558029
17 2432.0 71.125224 ... 75.726318 75.522751
18 2560.0 77.833728 ... 82.331658 81.920002
19 2688.0 83.737433 ... 90.532356 90.316801
20 2816.0 82.290955 ... 83.712490 84.197315
21 2944.0 82.646820 ... 81.967162 83.477440
22 3072.0 82.062468 ... 85.662786 89.030036
23 3200.0 84.210524 ... 97.116842 95.952022
24 3328.0 83.905938 ... 86.946008 86.736504
25 3456.0 79.196043 ... 86.689860 91.407671
26 3584.0 87.211821 ... 94.947616 97.840469
27 3712.0 85.896254 ... 83.005689 88.404730
28 3840.0 81.738356 ... 88.297007 91.473945
29 3968.0 88.040360 ... 92.093539 84.797731
30 4096.0 93.336389 ... 91.491294 88.185107
13 1920.0 68.776119 ... 71.257735 71.257735
14 2048.0 73.908442 ... 78.033565 77.672296
15 2176.0 83.155572 ... 87.115360 86.739860
16 2304.0 68.446623 ... 77.810656 77.810656
17 2432.0 71.487187 ... 75.522751 75.522751
18 2560.0 77.833728 ... 82.539044 82.125311
19 2688.0 84.295681 ... 90.102270 91.185232
20 2816.0 84.197315 ... 84.197315 83.712490
21 2944.0 82.373605 ... 82.509987 84.111450
22 3072.0 82.062468 ... 89.451983 87.651868
23 3200.0 80.910237 ... 96.822991 96.822991
24 3328.0 83.516586 ... 84.052885 83.130825
25 3456.0 82.604067 ... 86.970406 89.679166
26 3584.0 84.072363 ... 91.563533 98.699661
27 3712.0 85.822459 ... 84.017953 88.326564
28 3840.0 80.960466 ... 86.130841 91.549669
29 3968.0 90.825409 ... 91.643962 84.856701
30 4096.0 93.433852 ... 91.304576 90.443212
[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 27.164 seconds)
**Total running time of the script:** ( 6 minutes 55.735 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 0.325 seconds)
**Total running time of the script:** ( 0 minutes 0.326 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 1024.0 114.306981 99.497980 315.076934
1 1536.0 117.776359 132.604320 341.333333
2 2048.0 124.751268 158.554837 321.254900
3 2560.0 119.766080 182.857144 325.079368
4 3072.0 123.912607 191.501303 319.168834
5 3584.0 126.308369 208.271186 309.410081
6 4096.0 130.549806 220.412561 298.796351
7 4608.0 105.325718 231.849059 285.767436
8 5120.0 108.647215 244.294240 286.433562
9 5632.0 109.803417 244.426754 291.310338
10 6144.0 111.878602 251.202731 286.879370
11 6656.0 112.733948 256.000009 286.793541
12 7168.0 114.917836 253.360829 277.470965
13 7680.0 115.128047 266.743841 284.444450
14 8192.0 115.583772 258.694729 277.303250
15 8704.0 93.928060 267.130429 286.158893
16 9216.0 96.650214 272.729961 289.129410
17 9728.0 97.564561 279.942444 288.950501
18 10240.0 100.024417 287.102804 290.153487
19 10752.0 100.997264 246.699797 289.941565
20 11264.0 102.985144 246.432094 287.897767
21 11776.0 103.373808 249.667843 289.573776
22 12288.0 106.007189 254.453844 294.029924
23 12800.0 105.967577 254.094291 290.084977
24 13312.0 107.138837 252.959629 289.391298
25 13824.0 107.370873 256.991469 292.056329
26 14336.0 109.157360 255.429842 288.160801
27 14848.0 109.461527 257.108233 288.544136
28 15360.0 110.669469 258.513318 288.225185
29 15872.0 110.960674 262.527914 290.562936
0 1024.0 361.411758 99.497980 315.076934
1 1536.0 405.098894 133.083026 344.523365
2 2048.0 496.484863 158.045011 332.108094
3 2560.0 458.507457 182.857144 328.556154
4 3072.0 519.211251 191.501303 316.429186
5 3584.0 554.941930 207.768111 310.527060
6 4096.0 558.545450 219.919464 297.890900
7 4608.0 500.416301 231.849059 289.507855
8 5120.0 527.381977 244.294240 289.811322
9 5632.0 542.843364 244.426754 291.310338
10 6144.0 550.208948 251.202731 288.000001
11 6656.0 536.053693 256.000009 286.793541
12 7168.0 513.528374 253.734520 277.470965
13 7680.0 486.332448 266.358392 284.884090
14 8192.0 467.002371 258.694729 277.694924
15 8704.0 414.476194 267.130429 286.158893
16 9216.0 427.822068 273.066667 289.507855
17 9728.0 439.683593 279.942444 288.950501
18 10240.0 445.217381 287.102804 289.811322
19 10752.0 431.518385 246.699797 289.941565
20 11264.0 427.071098 246.432094 288.204696
21 11776.0 421.198220 249.667843 289.573776
22 12288.0 414.784810 254.673582 294.617366
23 12800.0 411.796260 254.094291 288.450715
24 13312.0 410.125805 253.360814 289.391298
25 13824.0 403.620451 256.991469 292.056329
26 14336.0 397.761846 255.429842 288.402346
27 14848.0 383.586664 256.922861 288.310684
28 15360.0 379.649845 258.332158 288.902809
29 15872.0 372.363640 261.806182 289.899545
@@ -339,7 +339,7 @@ Layer Normalization
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 2 minutes 2.154 seconds)
**Total running time of the script:** ( 2 minutes 12.794 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
=================
**13:19.517** total execution time for **getting-started_tutorials** files:
**14:26.653** total execution time for **getting-started_tutorials** files:
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:27.164 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:55.735 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:08.844 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:28.564 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:02.154 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:12.794 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:41.030 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:49.234 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.325 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.326 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+

4
master/getting-started/tutorials/01-vector-add.html
View File

@@ -325,7 +325,7 @@ for different problem sizes.</p>
0 4096.0 9.600000 9.600000
1 8192.0 19.200000 19.200000
2 16384.0 38.400001 38.400001
3 32768.0 63.999998 76.800002
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 341.333321
@@ -340,7 +340,7 @@ for different problem sizes.</p>
15 134217728.0 849.737435 850.656574
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 41.030 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 49.234 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-01-vector-add-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/62d97d49a32414049819dd8bb8378080/01-vector-add.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">01-vector-add.py</span></code></a></p>

22
master/getting-started/tutorials/02-fused-softmax.html
View File

@@ -369,17 +369,17 @@ We will then compare its performance against (1) <code class="code docutils lite
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>softmax-performance:
N Triton Torch (native) Torch (jit)
0 256.0 512.000001 512.000001 190.511628
1 384.0 438.857137 585.142862 151.703707
2 512.0 481.882344 606.814814 154.566038
3 640.0 465.454542 640.000002 158.759699
4 768.0 463.698115 664.216187 162.754967
0 256.0 546.133347 512.000001 188.321838
1 384.0 585.142862 585.142862 151.703707
2 512.0 655.360017 606.814814 154.566038
3 640.0 682.666684 640.000002 158.759699
4 768.0 722.823517 664.216187 162.754967
.. ... ... ... ...
93 12160.0 478.622374 405.333344 198.834951
94 12288.0 487.256521 415.661740 199.096718
95 12416.0 459.851851 411.722274 198.755369
96 12544.0 458.228323 412.971190 199.012395
97 12672.0 457.679461 412.097543 199.069228
93 12160.0 814.058574 405.755985 198.936606
94 12288.0 814.111783 415.442160 199.096718
95 12416.0 814.163950 411.296057 198.854847
96 12544.0 814.214963 412.971190 198.913776
97 12672.0 814.265046 412.097543 199.069228
[98 rows x 4 columns]
</pre></div>
@@ -392,7 +392,7 @@ We will then compare its performance against (1) <code class="code docutils lite
Note however that the PyTorch <cite>softmax</cite> operation is more general and will works on tensors of any shape.</p></li>
</ul>
</div></blockquote>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 8.844 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 28.564 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-02-fused-softmax-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/d91442ac2982c4e0cc3ab0f43534afbc/02-fused-softmax.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">02-fused-softmax.py</span></code></a></p>

48
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -569,37 +569,37 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
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 39.025776
6 1024.0 49.932191 ... 53.773130 52.428801
5 896.0 37.971025 ... 40.140799 40.140799
6 1024.0 49.932191 ... 53.773130 53.773130
7 1152.0 45.242181 ... 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
9 1408.0 64.138541 ... 68.147202 67.305878
10 1536.0 79.526831 ... 80.430545 80.430545
11 1664.0 63.372618 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.499573 63.142831
13 1920.0 68.776119 ... 71.626943 71.257735
14 2048.0 73.584279 ... 78.398206 78.033565
15 2176.0 83.500614 ... 87.115360 86.739860
16 2304.0 68.251065 ... 77.810656 77.558029
17 2432.0 71.125224 ... 75.726318 75.522751
18 2560.0 77.833728 ... 82.331658 81.920002
19 2688.0 83.737433 ... 90.532356 90.316801
20 2816.0 82.290955 ... 83.712490 84.197315
21 2944.0 82.646820 ... 81.967162 83.477440
22 3072.0 82.062468 ... 85.662786 89.030036
23 3200.0 84.210524 ... 97.116842 95.952022
24 3328.0 83.905938 ... 86.946008 86.736504
25 3456.0 79.196043 ... 86.689860 91.407671
26 3584.0 87.211821 ... 94.947616 97.840469
27 3712.0 85.896254 ... 83.005689 88.404730
28 3840.0 81.738356 ... 88.297007 91.473945
29 3968.0 88.040360 ... 92.093539 84.797731
30 4096.0 93.336389 ... 91.491294 88.185107
13 1920.0 68.776119 ... 71.257735 71.257735
14 2048.0 73.908442 ... 78.033565 77.672296
15 2176.0 83.155572 ... 87.115360 86.739860
16 2304.0 68.446623 ... 77.810656 77.810656
17 2432.0 71.487187 ... 75.522751 75.522751
18 2560.0 77.833728 ... 82.539044 82.125311
19 2688.0 84.295681 ... 90.102270 91.185232
20 2816.0 84.197315 ... 84.197315 83.712490
21 2944.0 82.373605 ... 82.509987 84.111450
22 3072.0 82.062468 ... 89.451983 87.651868
23 3200.0 80.910237 ... 96.822991 96.822991
24 3328.0 83.516586 ... 84.052885 83.130825
25 3456.0 82.604067 ... 86.970406 89.679166
26 3584.0 84.072363 ... 91.563533 98.699661
27 3712.0 85.822459 ... 84.017953 88.326564
28 3840.0 80.960466 ... 86.130841 91.549669
29 3968.0 90.825409 ... 91.643962 84.856701
30 4096.0 93.433852 ... 91.304576 90.443212
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 27.164 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 55.735 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-03-matrix-multiplication-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/d5fee5b55a64e47f1b5724ec39adf171/03-matrix-multiplication.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">03-matrix-multiplication.py</span></code></a></p>

2
master/getting-started/tutorials/04-low-memory-dropout.html
View File

@@ -372,7 +372,7 @@ to explore the <cite>triton/language/random</cite> folder!</p>
<dd><p>Nitish Srivastava and Geoffrey Hinton and Alex Krizhevsky and Ilya Sutskever and Ruslan Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting”, JMLR 2014</p>
</dd>
</dl>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes 0.325 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes 0.326 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-04-low-memory-dropout-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/c9aed78977a4c05741d675a38dde3d7d/04-low-memory-dropout.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">04-low-memory-dropout.py</span></code></a></p>

62
master/getting-started/tutorials/05-layer-norm.html
View File

@@ -194,36 +194,36 @@ to download the full example code</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>layer-norm-backward:
N Triton Torch Apex
0 1024.0 114.306981 99.497980 315.076934
1 1536.0 117.776359 132.604320 341.333333
2 2048.0 124.751268 158.554837 321.254900
3 2560.0 119.766080 182.857144 325.079368
4 3072.0 123.912607 191.501303 319.168834
5 3584.0 126.308369 208.271186 309.410081
6 4096.0 130.549806 220.412561 298.796351
7 4608.0 105.325718 231.849059 285.767436
8 5120.0 108.647215 244.294240 286.433562
9 5632.0 109.803417 244.426754 291.310338
10 6144.0 111.878602 251.202731 286.879370
11 6656.0 112.733948 256.000009 286.793541
12 7168.0 114.917836 253.360829 277.470965
13 7680.0 115.128047 266.743841 284.444450
14 8192.0 115.583772 258.694729 277.303250
15 8704.0 93.928060 267.130429 286.158893
16 9216.0 96.650214 272.729961 289.129410
17 9728.0 97.564561 279.942444 288.950501
18 10240.0 100.024417 287.102804 290.153487
19 10752.0 100.997264 246.699797 289.941565
20 11264.0 102.985144 246.432094 287.897767
21 11776.0 103.373808 249.667843 289.573776
22 12288.0 106.007189 254.453844 294.029924
23 12800.0 105.967577 254.094291 290.084977
24 13312.0 107.138837 252.959629 289.391298
25 13824.0 107.370873 256.991469 292.056329
26 14336.0 109.157360 255.429842 288.160801
27 14848.0 109.461527 257.108233 288.544136
28 15360.0 110.669469 258.513318 288.225185
29 15872.0 110.960674 262.527914 290.562936
0 1024.0 361.411758 99.497980 315.076934
1 1536.0 405.098894 133.083026 344.523365
2 2048.0 496.484863 158.045011 332.108094
3 2560.0 458.507457 182.857144 328.556154
4 3072.0 519.211251 191.501303 316.429186
5 3584.0 554.941930 207.768111 310.527060
6 4096.0 558.545450 219.919464 297.890900
7 4608.0 500.416301 231.849059 289.507855
8 5120.0 527.381977 244.294240 289.811322
9 5632.0 542.843364 244.426754 291.310338
10 6144.0 550.208948 251.202731 288.000001
11 6656.0 536.053693 256.000009 286.793541
12 7168.0 513.528374 253.734520 277.470965
13 7680.0 486.332448 266.358392 284.884090
14 8192.0 467.002371 258.694729 277.694924
15 8704.0 414.476194 267.130429 286.158893
16 9216.0 427.822068 273.066667 289.507855
17 9728.0 439.683593 279.942444 288.950501
18 10240.0 445.217381 287.102804 289.811322
19 10752.0 431.518385 246.699797 289.941565
20 11264.0 427.071098 246.432094 288.204696
21 11776.0 421.198220 249.667843 289.573776
22 12288.0 414.784810 254.673582 294.617366
23 12800.0 411.796260 254.094291 288.450715
24 13312.0 410.125805 253.360814 289.391298
25 13824.0 403.620451 256.991469 292.056329
26 14336.0 397.761846 255.429842 288.402346
27 14848.0 383.586664 256.922861 288.310684
28 15360.0 379.649845 258.332158 288.902809
29 15872.0 372.363640 261.806182 289.899545
</pre></div>
</div>
<div class="line-block">
@@ -487,7 +487,7 @@ to download the full example code</p>
<span class="n">bench_layer_norm</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">save_path</span><span class="o">=</span><span class="s1">&#39;.&#39;</span><span class="p">,</span> <span class="n">print_data</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 2.154 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 12.794 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-05-layer-norm-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/935c0dd0fbeb4b2e69588471cbb2d4b2/05-layer-norm.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">05-layer-norm.py</span></code></a></p>

12
master/getting-started/tutorials/sg_execution_times.html
View File

@@ -174,7 +174,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-getting-started-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline"></a></h1>
<p><strong>13:19.517</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
<p><strong>14:26.653</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -183,23 +183,23 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="03-matrix-multiplication.html#sphx-glr-getting-started-tutorials-03-matrix-multiplication-py"><span class="std std-ref">Matrix Multiplication</span></a> (<code class="docutils literal notranslate"><span class="pre">03-matrix-multiplication.py</span></code>)</p></td>
<td><p>06:27.164</p></td>
<td><p>06:55.735</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="02-fused-softmax.html#sphx-glr-getting-started-tutorials-02-fused-softmax-py"><span class="std std-ref">Fused Softmax</span></a> (<code class="docutils literal notranslate"><span class="pre">02-fused-softmax.py</span></code>)</p></td>
<td><p>03:08.844</p></td>
<td><p>03:28.564</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="05-layer-norm.html#sphx-glr-getting-started-tutorials-05-layer-norm-py"><span class="std std-ref">Layer Normalization</span></a> (<code class="docutils literal notranslate"><span class="pre">05-layer-norm.py</span></code>)</p></td>
<td><p>02:02.154</p></td>
<td><p>02:12.794</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="01-vector-add.html#sphx-glr-getting-started-tutorials-01-vector-add-py"><span class="std std-ref">Vector Addition</span></a> (<code class="docutils literal notranslate"><span class="pre">01-vector-add.py</span></code>)</p></td>
<td><p>01:41.030</p></td>
<td><p>01:49.234</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="04-low-memory-dropout.html#sphx-glr-getting-started-tutorials-04-low-memory-dropout-py"><span class="std std-ref">Low-Memory Dropout</span></a> (<code class="docutils literal notranslate"><span class="pre">04-low-memory-dropout.py</span></code>)</p></td>
<td><p>00:00.325</p></td>
<td><p>00:00.326</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>

2
master/searchindex.js
View File

File diff suppressed because one or more lines are too long

2
v1.1.2/.buildinfo
View File

@@ -1,4 +1,4 @@
# Sphinx build info version 1
# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
config: 3a8acee5fe178d3f643ad23f3c4c0e16
config: 1dcc604255008901a72982cd5af57aa7
tags: 645f666f9bcd5a90fca523b33c5a78b7

BIN
v1.1.2/.doctrees/environment.pickle
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/getting-started/installation.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/getting-started/tutorials/01-vector-add.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/getting-started/tutorials/02-fused-softmax.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/getting-started/tutorials/05-layer-norm.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/getting-started/tutorials/index.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/getting-started/tutorials/sg_execution_times.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/index.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/programming-guide/chapter-1/introduction.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/programming-guide/chapter-2/related-work.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/python-api/generated/triton.Config.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/python-api/generated/triton.autotune.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/python-api/generated/triton.heuristics.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/python-api/generated/triton.jit.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/python-api/generated/triton.language.arange.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/python-api/generated/triton.language.atomic_add.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/python-api/generated/triton.language.atomic_cas.doctree
View File

Binary file not shown.

BIN
v1.1.2/.doctrees/python-api/generated/triton.language.atomic_max.doctree
View File

Binary file not shown.

Some files were not shown because too many files have changed in this diff Show More