[GH-PAGES] Updated website

master/.buildinfo

@@ -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: b7b18d2918a6a7e59cc1dc27cf229d11
+config: 8eee1d5fd8e47ad721214965971ced11
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -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  37.620 seconds)
+   **Total running time of the script:** ( 1 minutes  41.632 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

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

@@ -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   192.752942
+    0     256.0  512.000001      546.133347   188.321838
     1     384.0  614.400016      585.142862   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
+    4     768.0  722.823517      664.216187   161.684218
     ..      ...         ...             ...          ...
-    93  12160.0  814.058574      406.179533   199.038365
+    93  12160.0  814.058574      406.179533   198.834951
-    94  12288.0  814.111783      415.661740   199.298541
+    94  12288.0  814.111783      415.222812   199.096718
-    95  12416.0  814.163950      412.149375   198.854847
+    95  12416.0  814.163950      412.149375   198.655991
-    96  12544.0  814.214963      412.971190   199.111113
+    96  12544.0  814.214963      412.971190   198.913776
-    97  12672.0  814.265046      411.679167   199.167004
+    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  18.443 seconds)
+   **Total running time of the script:** ( 3 minutes  20.741 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -458,37 +458,37 @@ 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   2.978909  ...   2.978909              2.978909
+    0    256.0   2.730667  ...   3.276800              2.978909
-    1    384.0   7.372800  ...   8.507077              8.507077
+    1    384.0   7.372800  ...   8.507077              7.899428
-    2    512.0  14.563555  ...  16.384000             16.384000
+    2    512.0  14.563555  ...  16.384000             15.420235
-    3    640.0  22.260869  ...  24.380953             24.380953
+    3    640.0  22.260869  ...  24.380953             23.272727
     4    768.0  32.768000  ...  34.028308             34.028308
-    5    896.0  39.025776  ...  40.140799             39.025776
+    5    896.0  37.971025  ...  39.025776             39.025776
     6   1024.0  49.932191  ...  52.428801             52.428801
     7   1152.0  45.242181  ...  46.656000             46.656000
     8   1280.0  51.200001  ...  56.888887             56.888887
-    9   1408.0  64.138541  ...  67.305878             65.684049
+    9   1408.0  64.138541  ...  67.305878             66.485074
-    10  1536.0  80.430545  ...  79.526831             78.643199
+    10  1536.0  79.526831  ...  79.526831             78.643199
-    11  1664.0  62.929456  ...  62.492442             62.061463
+    11  1664.0  62.929456  ...  62.929456             62.492442
-    12  1792.0  72.512412  ...  72.047592             72.047592
+    12  1792.0  72.983276  ...  72.512412             72.047592
-    13  1920.0  69.120002  ...  70.172588             70.172588
+    13  1920.0  69.467336  ...  70.172588             70.172588
     14  2048.0  73.262953  ...  76.608294             76.260072
-    15  2176.0  83.155572  ...  85.998493             85.269692
+    15  2176.0  83.155572  ...  85.998493             85.632545
-    16  2304.0  68.446623  ...  77.057651             76.809875
+    16  2304.0  68.251065  ...  76.809875             76.563695
-    17  2432.0  71.487187  ...  84.367759             85.134737
+    17  2432.0  71.487187  ...  84.877538             84.877538
-    18  2560.0  78.019048  ...  80.908642             80.511054
+    18  2560.0  77.833728  ...  80.908642             80.709358
-    19  2688.0  83.737433  ...  89.888756             89.254248
+    19  2688.0  83.552988  ...  89.888756             89.254248
-    20  2816.0  81.827785  ...  82.602666             82.135981
+    20  2816.0  83.074685  ...  82.602666             82.290955
-    21  2944.0  82.237674  ...  82.237674             82.102191
+    21  2944.0  82.102191  ...  82.102191             82.237674
-    22  3072.0  81.589488  ...  88.473602             88.197981
+    22  3072.0  82.301023  ...  88.542777             88.335577
-    23  3200.0  84.656085  ...  95.096582             94.955488
+    23  3200.0  83.989503  ...  95.380032             94.955488
-    24  3328.0  83.034941  ...  84.200347             83.808259
+    24  3328.0  83.226931  ...  84.695641             84.795401
-    25  3456.0  78.655188  ...  87.823058             87.632137
+    25  3456.0  80.220468  ...  84.156124             88.497878
-    26  3584.0  87.466332  ...  98.375705             93.467144
+    26  3584.0  82.189576  ...  89.646457             93.370085
-    27  3712.0  84.159518  ...  87.018592             88.092894
+    27  3712.0  85.748791  ...  86.264806             93.014284
-    28  3840.0  79.505392  ...  87.217666             91.473945
+    28  3840.0  81.859361  ...  87.355452             91.398346
-    29  3968.0  85.871877  ...  91.062642             84.038524
+    29  3968.0  85.991957  ...  91.369474             84.094627
-    30  4096.0  93.012976  ...  86.396995             89.958266
+    30  4096.0  93.466385  ...  87.381330             84.254693
 
     [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:** ( 5 minutes  56.421 seconds)
+   **Total running time of the script:** ( 5 minutes  54.058 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

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

@@ -240,7 +240,7 @@ References
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  0.486 seconds)
+   **Total running time of the script:** ( 0 minutes  0.497 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

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

@@ -38,35 +38,35 @@ Layer Normalization
 
     layer-norm-backward:
               N      Triton       Torch        Apex
-    0    1024.0  311.088617   98.303995  307.200008
+    0    1024.0  307.200008   98.303995  303.407414
-    1    1536.0  347.773587  134.540150  344.523365
+    1    1536.0  347.773587  134.540150  341.333333
     2    2048.0  420.102553  161.684218  334.367350
-    3    2560.0  458.507457  181.775141  330.322572
+    3    2560.0  455.111129  181.775141  330.322572
     4    3072.0  511.999982  192.501302  320.556515
-    5    3584.0  547.872604  208.271186  311.652167
+    5    3584.0  547.872604  207.768111  311.652167
-    6    4096.0  568.231237  220.412561  297.890900
+    6    4096.0  564.965515  220.412561  297.890900
-    7    4608.0  507.302750  232.825259  287.251954
+    7    4608.0  507.302750  232.825259  286.507772
-    8    5120.0  529.655159  242.845844  285.104413
+    8    5120.0  527.381977  242.845844  285.104413
-    9    5632.0  545.032265  243.545956  290.060087
+    9    5632.0  542.843364  243.545956  290.060087
     10   6144.0  546.133354  248.661056  286.879370
     11   6656.0  534.260858  256.000009  285.767438
     12   7168.0  505.976473  260.654538  286.242939
-    13   7680.0  482.513091  262.564106  278.429013
+    13   7680.0  482.513091  262.564106  278.850215
-    14   8192.0  463.698115  267.493874  284.939124
+    14   8192.0  462.607053  267.130429  284.939124
-    15   8704.0  418.629245  267.815384  284.987724
+    15   8704.0  418.629245  267.815384  285.377055
     16   9216.0  432.845409  272.394084  288.751954
     17   9728.0  439.683593  280.615388  289.667485
-    18  10240.0  448.467168  286.433562  290.153487
+    18  10240.0  449.287041  286.433562  290.153487
-    19  10752.0  426.525614  247.172406  290.922209
+    19  10752.0  425.821771  246.935876  290.922209
     20  11264.0  427.071098  245.536784  286.676558
-    21  11776.0  423.724129  249.667843  288.981596
+    21  11776.0  423.089806  249.667843  288.981596
-    22  12288.0  419.504980  254.673582  294.323369
+    22  12288.0  420.102570  254.453844  294.323369
-    23  12800.0  413.458944  253.465340  289.811310
+    23  12800.0  414.016170  253.465340  288.180121
-    24  13312.0  412.242569  252.959629  290.048115
+    24  13312.0  412.242569  252.759501  289.916513
-    25  13824.0  405.594132  257.190689  292.056329
+    25  13824.0  405.594132  257.390218  292.056329
-    26  14336.0  395.021816  254.485198  286.719986
+    26  14336.0  394.568805  254.485198  286.719986
-    27  14848.0  386.498925  257.665934  289.246765
+    27  14848.0  386.080180  257.479779  289.246765
-    28  15360.0  373.495460  257.970599  288.000007
+    28  15360.0  373.495460  257.790220  287.550706
     29  15872.0  371.274849  261.806182  289.899545
 
 
@@ -339,7 +339,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  11.775 seconds)
+   **Total running time of the script:** ( 2 minutes  12.350 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

master/_sources/getting-started/tutorials/sg_execution_times.rst.txt

@@ -5,16 +5,16 @@
 
 Computation times
 =================
-**13:04.745** total execution time for **getting-started_tutorials** files:
+**13:09.277** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:56.421 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:54.058 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:18.443 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:20.741 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:11.775 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:12.350 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:37.620 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:41.632 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.486 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.497 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

master/getting-started/tutorials/01-vector-add.html

@@ -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  37.620 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  41.632 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>

master/getting-started/tutorials/02-fused-softmax.html

@@ -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      546.133347   192.752942
+0     256.0  512.000001      546.133347   188.321838
 1     384.0  614.400016      585.142862   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
+4     768.0  722.823517      664.216187   161.684218
 ..      ...         ...             ...          ...
-93  12160.0  814.058574      406.179533   199.038365
+93  12160.0  814.058574      406.179533   198.834951
-94  12288.0  814.111783      415.661740   199.298541
+94  12288.0  814.111783      415.222812   199.096718
-95  12416.0  814.163950      412.149375   198.854847
+95  12416.0  814.163950      412.149375   198.655991
-96  12544.0  814.214963      412.971190   199.111113
+96  12544.0  814.214963      412.971190   198.913776
-97  12672.0  814.265046      411.679167   199.167004
+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  18.443 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  20.741 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>

master/getting-started/tutorials/03-matrix-multiplication.html

@@ -564,42 +564,42 @@ 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   2.978909  ...   2.978909              2.978909
+0    256.0   2.730667  ...   3.276800              2.978909
-1    384.0   7.372800  ...   8.507077              8.507077
+1    384.0   7.372800  ...   8.507077              7.899428
-2    512.0  14.563555  ...  16.384000             16.384000
+2    512.0  14.563555  ...  16.384000             15.420235
-3    640.0  22.260869  ...  24.380953             24.380953
+3    640.0  22.260869  ...  24.380953             23.272727
 4    768.0  32.768000  ...  34.028308             34.028308
-5    896.0  39.025776  ...  40.140799             39.025776
+5    896.0  37.971025  ...  39.025776             39.025776
 6   1024.0  49.932191  ...  52.428801             52.428801
 7   1152.0  45.242181  ...  46.656000             46.656000
 8   1280.0  51.200001  ...  56.888887             56.888887
-9   1408.0  64.138541  ...  67.305878             65.684049
+9   1408.0  64.138541  ...  67.305878             66.485074
-10  1536.0  80.430545  ...  79.526831             78.643199
+10  1536.0  79.526831  ...  79.526831             78.643199
-11  1664.0  62.929456  ...  62.492442             62.061463
+11  1664.0  62.929456  ...  62.929456             62.492442
-12  1792.0  72.512412  ...  72.047592             72.047592
+12  1792.0  72.983276  ...  72.512412             72.047592
-13  1920.0  69.120002  ...  70.172588             70.172588
+13  1920.0  69.467336  ...  70.172588             70.172588
 14  2048.0  73.262953  ...  76.608294             76.260072
-15  2176.0  83.155572  ...  85.998493             85.269692
+15  2176.0  83.155572  ...  85.998493             85.632545
-16  2304.0  68.446623  ...  77.057651             76.809875
+16  2304.0  68.251065  ...  76.809875             76.563695
-17  2432.0  71.487187  ...  84.367759             85.134737
+17  2432.0  71.487187  ...  84.877538             84.877538
-18  2560.0  78.019048  ...  80.908642             80.511054
+18  2560.0  77.833728  ...  80.908642             80.709358
-19  2688.0  83.737433  ...  89.888756             89.254248
+19  2688.0  83.552988  ...  89.888756             89.254248
-20  2816.0  81.827785  ...  82.602666             82.135981
+20  2816.0  83.074685  ...  82.602666             82.290955
-21  2944.0  82.237674  ...  82.237674             82.102191
+21  2944.0  82.102191  ...  82.102191             82.237674
-22  3072.0  81.589488  ...  88.473602             88.197981
+22  3072.0  82.301023  ...  88.542777             88.335577
-23  3200.0  84.656085  ...  95.096582             94.955488
+23  3200.0  83.989503  ...  95.380032             94.955488
-24  3328.0  83.034941  ...  84.200347             83.808259
+24  3328.0  83.226931  ...  84.695641             84.795401
-25  3456.0  78.655188  ...  87.823058             87.632137
+25  3456.0  80.220468  ...  84.156124             88.497878
-26  3584.0  87.466332  ...  98.375705             93.467144
+26  3584.0  82.189576  ...  89.646457             93.370085
-27  3712.0  84.159518  ...  87.018592             88.092894
+27  3712.0  85.748791  ...  86.264806             93.014284
-28  3840.0  79.505392  ...  87.217666             91.473945
+28  3840.0  81.859361  ...  87.355452             91.398346
-29  3968.0  85.871877  ...  91.062642             84.038524
+29  3968.0  85.991957  ...  91.369474             84.094627
-30  4096.0  93.012976  ...  86.396995             89.958266
+30  4096.0  93.466385  ...  87.381330             84.254693
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  56.421 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  54.058 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>

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

@@ -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  0.486 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.497 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>

master/getting-started/tutorials/05-layer-norm.html

@@ -194,35 +194,35 @@ 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  311.088617   98.303995  307.200008
+0    1024.0  307.200008   98.303995  303.407414
-1    1536.0  347.773587  134.540150  344.523365
+1    1536.0  347.773587  134.540150  341.333333
 2    2048.0  420.102553  161.684218  334.367350
-3    2560.0  458.507457  181.775141  330.322572
+3    2560.0  455.111129  181.775141  330.322572
 4    3072.0  511.999982  192.501302  320.556515
-5    3584.0  547.872604  208.271186  311.652167
+5    3584.0  547.872604  207.768111  311.652167
-6    4096.0  568.231237  220.412561  297.890900
+6    4096.0  564.965515  220.412561  297.890900
-7    4608.0  507.302750  232.825259  287.251954
+7    4608.0  507.302750  232.825259  286.507772
-8    5120.0  529.655159  242.845844  285.104413
+8    5120.0  527.381977  242.845844  285.104413
-9    5632.0  545.032265  243.545956  290.060087
+9    5632.0  542.843364  243.545956  290.060087
 10   6144.0  546.133354  248.661056  286.879370
 11   6656.0  534.260858  256.000009  285.767438
 12   7168.0  505.976473  260.654538  286.242939
-13   7680.0  482.513091  262.564106  278.429013
+13   7680.0  482.513091  262.564106  278.850215
-14   8192.0  463.698115  267.493874  284.939124
+14   8192.0  462.607053  267.130429  284.939124
-15   8704.0  418.629245  267.815384  284.987724
+15   8704.0  418.629245  267.815384  285.377055
 16   9216.0  432.845409  272.394084  288.751954
 17   9728.0  439.683593  280.615388  289.667485
-18  10240.0  448.467168  286.433562  290.153487
+18  10240.0  449.287041  286.433562  290.153487
-19  10752.0  426.525614  247.172406  290.922209
+19  10752.0  425.821771  246.935876  290.922209
 20  11264.0  427.071098  245.536784  286.676558
-21  11776.0  423.724129  249.667843  288.981596
+21  11776.0  423.089806  249.667843  288.981596
-22  12288.0  419.504980  254.673582  294.323369
+22  12288.0  420.102570  254.453844  294.323369
-23  12800.0  413.458944  253.465340  289.811310
+23  12800.0  414.016170  253.465340  288.180121
-24  13312.0  412.242569  252.959629  290.048115
+24  13312.0  412.242569  252.759501  289.916513
-25  13824.0  405.594132  257.190689  292.056329
+25  13824.0  405.594132  257.390218  292.056329
-26  14336.0  395.021816  254.485198  286.719986
+26  14336.0  394.568805  254.485198  286.719986
-27  14848.0  386.498925  257.665934  289.246765
+27  14848.0  386.080180  257.479779  289.246765
-28  15360.0  373.495460  257.970599  288.000007
+28  15360.0  373.495460  257.790220  287.550706
 29  15872.0  371.274849  261.806182  289.899545
 </pre></div>
 </div>
@@ -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  11.775 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  12.350 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>

master/getting-started/tutorials/sg_execution_times.html

@@ -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>13:04.745</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:09.277</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>05:56.421</p></td>
+<td><p>05:54.058</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>03:18.443</p></td>
+<td><p>03:20.741</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>02:11.775</p></td>
+<td><p>02:12.350</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>01:37.620</p></td>
+<td><p>01:41.632</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>00:00.486</p></td>
+<td><p>00:00.497</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>

v1.1.2/.buildinfo

@@ -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: 32a39855c7c0f65c3af0c5cffdc6a527
+config: adc213de09baaaffc5c64ac7ed50136c
 tags: 645f666f9bcd5a90fca523b33c5a78b7