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
2022-06-18 00:47:57 +00:00
parent 4412443b59
commit 5de1b15fff
158 changed files with 260 additions and 260 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: 5ab171cc8e40ebd53fce9d52a7350ca6
config: bab18fe850096d21a7ceed593584c803
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: 24 KiB

After

Width:  |  Height:  |  Size: 24 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: 37 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: 23 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: 59 KiB

After

Width:  |  Height:  |  Size: 59 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: 34 KiB

After

Width:  |  Height:  |  Size: 34 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: 35 KiB

After

Width:  |  Height:  |  Size: 35 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: 22 KiB

After

Width:  |  Height:  |  Size: 22 KiB

6
master/_sources/getting-started/tutorials/01-vector-add.rst.txt
View File

@@ -241,11 +241,11 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
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 722.823517
9 2097152.0 722.823517 702.171410
10 4194304.0 780.190482 780.190482
11 8388608.0 812.429770 812.429770
12 16777216.0 833.084721 833.084721
13 33554432.0 842.004273 843.811163
13 33554432.0 842.004273 842.004273
14 67108864.0 847.448255 848.362445
15 134217728.0 849.737435 850.656574
@@ -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 47.538 seconds)
**Total running time of the script:** ( 1 minutes 39.442 seconds)
.. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

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

@@ -278,17 +278,17 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
softmax-performance:
N Triton Torch (native) Torch (jit)
0 256.0 546.133347 512.000001 186.181817
1 384.0 614.400016 585.142862 153.600004
2 512.0 655.360017 585.142849 154.566038
0 256.0 512.000001 546.133347 190.511628
1 384.0 614.400016 558.545450 153.600004
2 512.0 655.360017 606.814814 154.566038
3 640.0 706.206879 640.000002 160.000000
4 768.0 722.823517 664.216187 162.754967
.. ... ... ... ...
93 12160.0 812.359066 406.179533 198.631953
94 12288.0 812.429770 415.661740 198.895304
95 12416.0 812.498981 412.149375 198.556711
96 12544.0 810.925276 412.971190 198.815254
97 12672.0 812.633240 412.097543 198.776477
93 12160.0 812.359066 405.755985 199.038365
94 12288.0 812.429770 415.661740 199.298541
95 12416.0 812.498981 411.722274 198.854847
96 12544.0 812.566838 412.971190 199.111113
97 12672.0 812.633240 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 22.808 seconds)
**Total running time of the script:** ( 3 minutes 22.625 seconds)
.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -459,37 +459,37 @@ 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 ... 3.276800 3.276800
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 15.420235 16.384000
0 256.0 2.730667 ... 3.276800 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 32.768000 ... 34.028308 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
4 768.0 32.768000 ... 35.389441 34.028308
5 896.0 39.025776 ... 40.140799 39.025776
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 45.242181 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 68.147202 66.485074
10 1536.0 79.526831 ... 81.355034 79.526831
11 1664.0 62.929456 ... 63.372618 62.492442
10 1536.0 80.430545 ... 81.355034 79.526831
11 1664.0 63.372618 ... 63.372618 62.492442
12 1792.0 72.983276 ... 73.460287 59.467852
13 1920.0 69.120002 ... 71.257735 70.892307
13 1920.0 69.467336 ... 71.257735 70.892307
14 2048.0 73.262953 ... 78.033565 76.959706
15 2176.0 83.155572 ... 87.876193 86.367588
15 2176.0 83.155572 ... 87.494120 85.632545
16 2304.0 68.446623 ... 78.064941 77.057651
17 2432.0 71.305746 ... 86.711310 75.118889
18 2560.0 77.833728 ... 82.956960 81.310171
19 2688.0 83.922689 ... 90.316801 89.254248
20 2816.0 83.712490 ... 84.360174 83.392363
21 2944.0 81.698415 ... 83.477440 82.509987
22 3072.0 82.420822 ... 90.020831 89.030036
23 3200.0 84.768213 ... 97.859331 95.380032
24 3328.0 83.034941 ... 86.011103 83.613586
25 3456.0 80.945348 ... 87.158452 81.105671
26 3584.0 87.211821 ... 99.354022 91.844118
27 3712.0 84.159518 ... 88.955779 88.483034
28 3840.0 84.292684 ... 93.484358 84.483849
29 3968.0 92.688139 ... 85.093402 91.472214
30 4096.0 86.620022 ... 88.621807 91.366730
17 2432.0 71.305746 ... 86.711310 85.393507
18 2560.0 77.833728 ... 82.331658 81.512437
19 2688.0 83.922689 ... 90.748936 88.836198
20 2816.0 79.879498 ... 84.197315 82.446516
21 2944.0 82.509987 ... 83.198715 81.967162
22 3072.0 82.062468 ... 88.750943 87.516392
23 3200.0 84.880639 ... 93.158662 93.841640
24 3328.0 81.530349 ... 85.857242 84.298943
25 3456.0 82.435141 ... 91.771848 90.892410
26 3584.0 85.552231 ... 88.496679 87.381330
27 3712.0 85.675250 ... 93.187820 87.706180
28 3840.0 81.798814 ... 90.723546 86.535214
29 3968.0 89.921841 ... 85.451873 88.040360
30 4096.0 92.691803 ... 93.271527 87.381330
[31 rows x 5 columns]
@@ -499,7 +499,7 @@ 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 12.160 seconds)
**Total running time of the script:** ( 6 minutes 9.590 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 0.472 seconds)
**Total running time of the script:** ( 0 minutes 0.468 seconds)
.. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

54
master/_sources/getting-started/tutorials/05-layer-norm.rst.txt
View File

@@ -38,36 +38,36 @@ Layer Normalization
layer-norm:
N Triton Torch Apex
0 1024.0 585.142849 277.694907 468.114273
0 1024.0 585.142849 277.694907 481.882344
1 1536.0 630.153868 323.368435 511.999982
2 2048.0 682.666643 334.367358 520.126988
3 2560.0 694.237267 362.477870 518.481028
2 2048.0 682.666643 337.814445 520.126988
3 2560.0 694.237267 362.477870 512.000013
4 3072.0 712.347810 378.092307 501.551037
5 3584.0 725.873439 384.859062 458.751978
6 4096.0 728.177767 381.023256 458.293714
7 4608.0 670.254540 396.387087 426.173427
8 5120.0 694.237267 397.669909 426.666652
9 5632.0 704.000002 395.228063 413.357796
5 3584.0 725.873439 384.859062 451.527536
6 4096.0 728.177767 381.023256 451.972420
7 4608.0 676.403666 396.387087 428.651163
8 5120.0 688.403381 395.748783 420.102563
9 5632.0 709.543270 395.228063 415.262685
10 6144.0 702.171410 402.885254 411.313806
11 6656.0 700.631610 400.360920 398.861429
12 7168.0 695.078767 396.844306 388.772874
13 7680.0 682.666656 392.587863 387.634072
14 8192.0 642.509816 393.609605 372.363633
15 8704.0 630.153861 389.005597 380.502740
16 9216.0 609.322328 407.337026 383.999986
17 9728.0 589.575753 409.599987 383.369452
18 10240.0 566.920437 408.578556 382.803739
11 6656.0 700.631610 400.360920 400.360920
12 7168.0 690.891575 388.772874 384.859062
13 7680.0 682.666656 392.587863 386.415087
14 8192.0 639.375598 390.095241 370.259899
15 8704.0 624.502255 389.005597 379.465939
16 9216.0 606.814809 406.214877 382.010363
17 9728.0 587.350922 408.524944 382.427505
18 10240.0 566.920437 409.600010 382.803739
19 10752.0 549.623009 411.559798 381.445676
20 11264.0 536.380957 406.826188 373.134567
21 11776.0 523.377770 409.599991 377.587162
22 12288.0 516.031509 413.911572 383.251457
23 12800.0 505.679014 410.420828 376.470582
24 13312.0 494.180982 405.699062 376.310952
25 13824.0 482.934503 411.888257 379.389355
26 14336.0 471.967074 406.695045 374.185964
27 14848.0 461.297068 408.192434 375.304904
28 15360.0 454.269882 406.214870 378.092307
29 15872.0 447.098578 406.974373 376.225175
20 11264.0 534.789310 403.185684 371.595879
21 11776.0 523.377770 410.492372 376.831982
22 12288.0 518.754611 413.911572 383.251457
23 12800.0 505.679014 409.599981 377.163903
24 13312.0 495.330249 405.699062 376.976995
25 13824.0 482.934503 412.656711 379.389355
26 14336.0 471.967074 403.830973 371.158581
27 14848.0 461.297068 406.794504 374.712936
28 15360.0 454.269882 406.887417 378.092307
29 15872.0 447.098578 406.974373 375.668625
@@ -389,7 +389,7 @@ Layer Normalization
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 5 minutes 26.669 seconds)
**Total running time of the script:** ( 5 minutes 24.904 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
=================
**16:49.647** total execution time for **getting-started_tutorials** files:
**16:37.029** total execution time for **getting-started_tutorials** files:
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:12.160 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:09.590 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:26.669 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:24.904 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:22.808 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:22.625 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:47.538 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:39.442 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.472 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.468 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+

6
master/getting-started/tutorials/01-vector-add.html
View File

@@ -331,16 +331,16 @@ for different problem sizes.</p>
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 722.823517
9 2097152.0 722.823517 702.171410
10 4194304.0 780.190482 780.190482
11 8388608.0 812.429770 812.429770
12 16777216.0 833.084721 833.084721
13 33554432.0 842.004273 843.811163
13 33554432.0 842.004273 842.004273
14 67108864.0 847.448255 848.362445
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 47.538 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 39.442 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>

18
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)
0 256.0 546.133347 512.000001 186.181817
1 384.0 614.400016 585.142862 153.600004
2 512.0 655.360017 585.142849 154.566038
0 256.0 512.000001 546.133347 190.511628
1 384.0 614.400016 558.545450 153.600004
2 512.0 655.360017 606.814814 154.566038
3 640.0 706.206879 640.000002 160.000000
4 768.0 722.823517 664.216187 162.754967
.. ... ... ... ...
93 12160.0 812.359066 406.179533 198.631953
94 12288.0 812.429770 415.661740 198.895304
95 12416.0 812.498981 412.149375 198.556711
96 12544.0 810.925276 412.971190 198.815254
97 12672.0 812.633240 412.097543 198.776477
93 12160.0 812.359066 405.755985 199.038365
94 12288.0 812.429770 415.661740 199.298541
95 12416.0 812.498981 411.722274 198.854847
96 12544.0 812.566838 412.971190 199.111113
97 12672.0 812.633240 412.097543 199.167004
[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 22.808 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 22.625 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

@@ -565,42 +565,42 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>matmul-performance:
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 256.0 2.730667 ... 3.276800 3.276800
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 15.420235 16.384000
0 256.0 2.730667 ... 3.276800 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 32.768000 ... 34.028308 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
4 768.0 32.768000 ... 35.389441 34.028308
5 896.0 39.025776 ... 40.140799 39.025776
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 45.242181 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 68.147202 66.485074
10 1536.0 79.526831 ... 81.355034 79.526831
11 1664.0 62.929456 ... 63.372618 62.492442
10 1536.0 80.430545 ... 81.355034 79.526831
11 1664.0 63.372618 ... 63.372618 62.492442
12 1792.0 72.983276 ... 73.460287 59.467852
13 1920.0 69.120002 ... 71.257735 70.892307
13 1920.0 69.467336 ... 71.257735 70.892307
14 2048.0 73.262953 ... 78.033565 76.959706
15 2176.0 83.155572 ... 87.876193 86.367588
15 2176.0 83.155572 ... 87.494120 85.632545
16 2304.0 68.446623 ... 78.064941 77.057651
17 2432.0 71.305746 ... 86.711310 75.118889
18 2560.0 77.833728 ... 82.956960 81.310171
19 2688.0 83.922689 ... 90.316801 89.254248
20 2816.0 83.712490 ... 84.360174 83.392363
21 2944.0 81.698415 ... 83.477440 82.509987
22 3072.0 82.420822 ... 90.020831 89.030036
23 3200.0 84.768213 ... 97.859331 95.380032
24 3328.0 83.034941 ... 86.011103 83.613586
25 3456.0 80.945348 ... 87.158452 81.105671
26 3584.0 87.211821 ... 99.354022 91.844118
27 3712.0 84.159518 ... 88.955779 88.483034
28 3840.0 84.292684 ... 93.484358 84.483849
29 3968.0 92.688139 ... 85.093402 91.472214
30 4096.0 86.620022 ... 88.621807 91.366730
17 2432.0 71.305746 ... 86.711310 85.393507
18 2560.0 77.833728 ... 82.331658 81.512437
19 2688.0 83.922689 ... 90.748936 88.836198
20 2816.0 79.879498 ... 84.197315 82.446516
21 2944.0 82.509987 ... 83.198715 81.967162
22 3072.0 82.062468 ... 88.750943 87.516392
23 3200.0 84.880639 ... 93.158662 93.841640
24 3328.0 81.530349 ... 85.857242 84.298943
25 3456.0 82.435141 ... 91.771848 90.892410
26 3584.0 85.552231 ... 88.496679 87.381330
27 3712.0 85.675250 ... 93.187820 87.706180
28 3840.0 81.798814 ... 90.723546 86.535214
29 3968.0 89.921841 ... 85.451873 88.040360
30 4096.0 92.691803 ... 93.271527 87.381330
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 12.160 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 9.590 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 0.472 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes 0.468 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>

54
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:
N Triton Torch Apex
0 1024.0 585.142849 277.694907 468.114273
0 1024.0 585.142849 277.694907 481.882344
1 1536.0 630.153868 323.368435 511.999982
2 2048.0 682.666643 334.367358 520.126988
3 2560.0 694.237267 362.477870 518.481028
2 2048.0 682.666643 337.814445 520.126988
3 2560.0 694.237267 362.477870 512.000013
4 3072.0 712.347810 378.092307 501.551037
5 3584.0 725.873439 384.859062 458.751978
6 4096.0 728.177767 381.023256 458.293714
7 4608.0 670.254540 396.387087 426.173427
8 5120.0 694.237267 397.669909 426.666652
9 5632.0 704.000002 395.228063 413.357796
5 3584.0 725.873439 384.859062 451.527536
6 4096.0 728.177767 381.023256 451.972420
7 4608.0 676.403666 396.387087 428.651163
8 5120.0 688.403381 395.748783 420.102563
9 5632.0 709.543270 395.228063 415.262685
10 6144.0 702.171410 402.885254 411.313806
11 6656.0 700.631610 400.360920 398.861429
12 7168.0 695.078767 396.844306 388.772874
13 7680.0 682.666656 392.587863 387.634072
14 8192.0 642.509816 393.609605 372.363633
15 8704.0 630.153861 389.005597 380.502740
16 9216.0 609.322328 407.337026 383.999986
17 9728.0 589.575753 409.599987 383.369452
18 10240.0 566.920437 408.578556 382.803739
11 6656.0 700.631610 400.360920 400.360920
12 7168.0 690.891575 388.772874 384.859062
13 7680.0 682.666656 392.587863 386.415087
14 8192.0 639.375598 390.095241 370.259899
15 8704.0 624.502255 389.005597 379.465939
16 9216.0 606.814809 406.214877 382.010363
17 9728.0 587.350922 408.524944 382.427505
18 10240.0 566.920437 409.600010 382.803739
19 10752.0 549.623009 411.559798 381.445676
20 11264.0 536.380957 406.826188 373.134567
21 11776.0 523.377770 409.599991 377.587162
22 12288.0 516.031509 413.911572 383.251457
23 12800.0 505.679014 410.420828 376.470582
24 13312.0 494.180982 405.699062 376.310952
25 13824.0 482.934503 411.888257 379.389355
26 14336.0 471.967074 406.695045 374.185964
27 14848.0 461.297068 408.192434 375.304904
28 15360.0 454.269882 406.214870 378.092307
29 15872.0 447.098578 406.974373 376.225175
20 11264.0 534.789310 403.185684 371.595879
21 11776.0 523.377770 410.492372 376.831982
22 12288.0 518.754611 413.911572 383.251457
23 12800.0 505.679014 409.599981 377.163903
24 13312.0 495.330249 405.699062 376.976995
25 13824.0 482.934503 412.656711 379.389355
26 14336.0 471.967074 403.830973 371.158581
27 14848.0 461.297068 406.794504 374.712936
28 15360.0 454.269882 406.887417 378.092307
29 15872.0 447.098578 406.974373 375.668625
</pre></div>
</div>
<div class="line-block">
@@ -537,7 +537,7 @@ 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> ( 5 minutes 26.669 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.904 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>16:49.647</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
<p><strong>16:37.029</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>06:12.160</p></td>
<td><p>06:09.590</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><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>05:26.669</p></td>
<td><p>05:24.904</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><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>03:22.808</p></td>
<td><p>03:22.625</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>01:47.538</p></td>
<td><p>01:39.442</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>00:00.472</p></td>
<td><p>00:00.468</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: f3703c89bb069d71c8a6d1414c97f31b
config: bae9558105859570a135817d997f9621
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