[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: 51db5db0f6c807e07764c81b4ee33b7f
+config: fd44bdf18c835f10b59347df4a0ac28b
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -238,14 +238,14 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
     3       32768.0   76.800002   76.800002
     4       65536.0  127.999995  127.999995
     5      131072.0  219.428568  219.428568
-    6      262144.0  384.000001  384.000001
+    6      262144.0  341.333321  384.000001
     7      524288.0  472.615390  472.615390
     8     1048576.0  614.400016  614.400016
     9     2097152.0  722.823517  722.823517
     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  842.004273
+    13   33554432.0  842.004273  843.811163
     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  45.396 seconds)
+   **Total running time of the script:** ( 1 minutes  41.086 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   188.321838
+    0     256.0  512.000001      546.133347   190.511628
     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
     ..      ...         ...             ...          ...
-    93  12160.0  814.058574      406.179533   199.038365
-    94  12288.0  814.111783      415.661740   199.298541
-    95  12416.0  814.163950      412.149375   198.854847
-    96  12544.0  814.214963      412.971190   199.111113
-    97  12672.0  814.265046      412.097543   199.167004
+    93  12160.0  815.765209      406.179533   198.834951
+    94  12288.0  814.111783      415.661740   199.096718
+    95  12416.0  814.163950      412.149375   198.655991
+    96  12544.0  814.214963      413.183734   198.913776
+    97  12672.0  814.265046      412.097543   198.873965
 
     [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  21.032 seconds)
+   **Total running time of the script:** ( 3 minutes  20.138 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -459,36 +459,36 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
     matmul-performance:
              M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
     0    256.0   2.730667  ...   2.978909              2.978909
-    1    384.0   7.372800  ...   8.507077              8.507077
-    2    512.0  14.563555  ...  16.384000             15.420235
+    1    384.0   7.372800  ...   8.507077              7.899428
+    2    512.0  14.563555  ...  16.384000             16.384000
     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
-    6   1024.0  49.932191  ...  52.428801             52.428801
+    5    896.0  39.025776  ...  40.140799             39.025776
+    6   1024.0  51.150050  ...  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
-    10  1536.0  80.430545  ...  79.526831             78.643199
+    9   1408.0  64.138541  ...  67.305878             66.485074
+    10  1536.0  80.430545  ...  79.526831             79.526831
     11  1664.0  62.929456  ...  62.492442             62.061463
-    12  1792.0  72.512412  ...  72.047592             72.047592
-    13  1920.0  68.776119  ...  70.172588             69.818184
-    14  2048.0  73.262953  ...  76.959706             76.608294
-    15  2176.0  83.500614  ...  86.367588             85.269692
-    16  2304.0  68.643310  ...  77.057651             76.809875
-    17  2432.0  71.487187  ...  84.367759             84.877538
-    18  2560.0  78.019048  ...  80.709358             80.511054
-    19  2688.0  83.004501  ...  89.888756             89.254248
-    20  2816.0  80.767055  ...  82.916747             81.521884
-    21  2944.0  81.698415  ...  82.237674             82.921853
-    22  3072.0  82.661468  ...  88.612060             87.516392
-    23  3200.0  82.051282  ...  94.814812             94.534716
-    24  3328.0  83.226931  ...  84.895397             84.496824
-    25  3456.0  81.108217  ...  91.200871             85.722029
-    26  3584.0  82.189576  ...  93.370085             95.047985
-    27  3712.0  82.491612  ...  88.092894             89.114488
-    28  3840.0  82.716526  ...  89.620748             86.670843
-    29  3968.0  85.934238  ...  91.062642             86.114283
-    30  4096.0  93.012976  ...  92.691803             88.243079
+    12  1792.0  72.983276  ...  71.588687             72.047592
+    13  1920.0  69.467336  ...  70.530615             70.530615
+    14  2048.0  73.584279  ...  76.959706             76.260072
+    15  2176.0  83.155572  ...  85.632545             85.632545
+    16  2304.0  68.446623  ...  76.319081             76.319081
+    17  2432.0  71.305746  ...  74.521127             84.877538
+    18  2560.0  78.019048  ...  81.310171             81.108913
+    19  2688.0  83.461070  ...  89.044730             89.464755
+    20  2816.0  81.521884  ...  82.446516             82.602666
+    21  2944.0  82.237674  ...  82.373605             82.921853
+    22  3072.0  82.181572  ...  88.750943             89.451983
+    23  3200.0  84.544253  ...  95.380032             95.096582
+    24  3328.0  83.130825  ...  83.905938             84.397770
+    25  3456.0  78.578525  ...  88.790274             90.382926
+    26  3584.0  87.211821  ...  98.483450             92.505546
+    27  3712.0  84.159518  ...  87.056508             85.751096
+    28  3840.0  85.005380  ...  92.390975             85.597527
+    29  3968.0  92.372393  ...  84.155345             88.809270
+    30  4096.0  86.370931  ...  92.627833             88.185107
 
     [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  7.784 seconds)
+   **Total running time of the script:** ( 6 minutes  2.945 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  0.489 seconds)
+   **Total running time of the script:** ( 0 minutes  0.484 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

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

@@ -38,36 +38,36 @@ Layer Normalization
 
     layer-norm-backward:
               N      Triton       Torch        Apex
-    0    1024.0  307.200008   98.303995  307.200008
+    0    1024.0  311.088617   98.303995  307.200008
     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
-    4    3072.0  511.999982  192.501302  320.556515
+    2    2048.0  420.102553  161.684218  325.509933
+    3    2560.0  458.507457  181.775141  326.808501
+    4    3072.0  511.999982  192.501302  317.793096
     5    3584.0  551.384634  208.271186  311.652167
-    6    4096.0  564.965515  220.412561  297.890900
-    7    4608.0  507.302750  232.825259  286.507772
-    8    5120.0  531.948056  242.845844  285.104413
-    9    5632.0  545.032265  243.545956  289.438969
-    10   6144.0  548.163546  248.661056  285.767458
+    6    4096.0  564.965515  220.412561  295.207204
+    7    4608.0  507.302750  232.825259  291.799469
+    8    5120.0  529.655159  242.845844  289.811322
+    9    5632.0  542.843364  243.545956  288.820505
+    10   6144.0  548.163546  248.661056  286.322318
     11   6656.0  534.260858  256.000009  285.767438
     12   7168.0  507.469040  260.654538  286.242939
-    13   7680.0  479.999983  262.190612  275.104486
-    14   8192.0  462.607053  267.130429  284.939124
-    15   8704.0  418.629245  267.472468  284.599455
-    16   9216.0  432.000001  272.394084  288.751954
-    17   9728.0  440.513191  280.615388  290.027323
-    18  10240.0  450.109870  286.433562  287.775181
-    19  10752.0  427.231788  247.172406  290.922209
-    20  11264.0  427.071098  245.536784  286.676558
-    21  11776.0  423.089806  249.667843  288.686414
-    22  12288.0  419.504980  254.453844  294.323369
-    23  12800.0  414.016170  253.465340  289.538159
-    24  13312.0  411.181478  252.759501  289.916513
+    13   7680.0  479.999983  262.564106  275.104486
+    14   8192.0  463.698115  267.130429  284.939124
+    15   8704.0  417.791980  267.815384  284.987724
+    16   9216.0  431.157889  272.394084  289.129410
+    17   9728.0  439.683593  280.278512  290.027323
+    18  10240.0  450.109870  286.433562  290.153487
+    19  10752.0  426.525614  247.172406  290.922209
+    20  11264.0  427.071098  245.760001  286.676558
+    21  11776.0  423.089806  249.888595  288.981596
+    22  12288.0  420.102570  254.673582  294.323369
+    23  12800.0  414.016170  253.674644  288.180121
+    24  13312.0  411.181478  252.959629  289.916513
     25  13824.0  404.604870  257.190689  292.056329
     26  14336.0  393.665895  254.485198  286.719986
-    27  14848.0  385.662341  257.665934  289.246765
-    28  15360.0  373.874218  257.970599  287.102804
-    29  15872.0  371.274849  261.986243  289.899545
+    27  14848.0  385.245405  257.665934  289.246765
+    28  15360.0  373.495460  257.970599  286.211174
+    29  15872.0  371.637071  261.626369  289.899545
 
 
 
@@ -339,7 +339,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  12.249 seconds)
+   **Total running time of the script:** ( 2 minutes  11.317 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
 =================
-**13:26.950** total execution time for **getting-started_tutorials** files:
+**13:15.970** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:07.784 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:02.945 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:21.032 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:20.138 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:12.249 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:11.317 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:45.396 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:41.086 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.489 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.484 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -328,19 +328,19 @@ for different problem sizes.</p>
 3       32768.0   76.800002   76.800002
 4       65536.0  127.999995  127.999995
 5      131072.0  219.428568  219.428568
-6      262144.0  384.000001  384.000001
+6      262144.0  341.333321  384.000001
 7      524288.0  472.615390  472.615390
 8     1048576.0  614.400016  614.400016
 9     2097152.0  722.823517  722.823517
 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  842.004273
+13   33554432.0  842.004273  843.811163
 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  45.396 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  41.086 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   188.321838
+0     256.0  512.000001      546.133347   190.511628
 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
 ..      ...         ...             ...          ...
-93  12160.0  814.058574      406.179533   199.038365
-94  12288.0  814.111783      415.661740   199.298541
-95  12416.0  814.163950      412.149375   198.854847
-96  12544.0  814.214963      412.971190   199.111113
-97  12672.0  814.265046      412.097543   199.167004
+93  12160.0  815.765209      406.179533   198.834951
+94  12288.0  814.111783      415.661740   199.096718
+95  12416.0  814.163950      412.149375   198.655991
+96  12544.0  814.214963      413.183734   198.913776
+97  12672.0  814.265046      412.097543   198.873965
 
 [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  21.032 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  20.138 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

@@ -565,41 +565,41 @@ torch_output=tensor([[  1.1045, -36.9688,  31.4688,  ..., -11.3906,  24.4531, -3
 <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  ...   2.978909              2.978909
-1    384.0   7.372800  ...   8.507077              8.507077
-2    512.0  14.563555  ...  16.384000             15.420235
+1    384.0   7.372800  ...   8.507077              7.899428
+2    512.0  14.563555  ...  16.384000             16.384000
 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
-6   1024.0  49.932191  ...  52.428801             52.428801
+5    896.0  39.025776  ...  40.140799             39.025776
+6   1024.0  51.150050  ...  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
-10  1536.0  80.430545  ...  79.526831             78.643199
+9   1408.0  64.138541  ...  67.305878             66.485074
+10  1536.0  80.430545  ...  79.526831             79.526831
 11  1664.0  62.929456  ...  62.492442             62.061463
-12  1792.0  72.512412  ...  72.047592             72.047592
-13  1920.0  68.776119  ...  70.172588             69.818184
-14  2048.0  73.262953  ...  76.959706             76.608294
-15  2176.0  83.500614  ...  86.367588             85.269692
-16  2304.0  68.643310  ...  77.057651             76.809875
-17  2432.0  71.487187  ...  84.367759             84.877538
-18  2560.0  78.019048  ...  80.709358             80.511054
-19  2688.0  83.004501  ...  89.888756             89.254248
-20  2816.0  80.767055  ...  82.916747             81.521884
-21  2944.0  81.698415  ...  82.237674             82.921853
-22  3072.0  82.661468  ...  88.612060             87.516392
-23  3200.0  82.051282  ...  94.814812             94.534716
-24  3328.0  83.226931  ...  84.895397             84.496824
-25  3456.0  81.108217  ...  91.200871             85.722029
-26  3584.0  82.189576  ...  93.370085             95.047985
-27  3712.0  82.491612  ...  88.092894             89.114488
-28  3840.0  82.716526  ...  89.620748             86.670843
-29  3968.0  85.934238  ...  91.062642             86.114283
-30  4096.0  93.012976  ...  92.691803             88.243079
+12  1792.0  72.983276  ...  71.588687             72.047592
+13  1920.0  69.467336  ...  70.530615             70.530615
+14  2048.0  73.584279  ...  76.959706             76.260072
+15  2176.0  83.155572  ...  85.632545             85.632545
+16  2304.0  68.446623  ...  76.319081             76.319081
+17  2432.0  71.305746  ...  74.521127             84.877538
+18  2560.0  78.019048  ...  81.310171             81.108913
+19  2688.0  83.461070  ...  89.044730             89.464755
+20  2816.0  81.521884  ...  82.446516             82.602666
+21  2944.0  82.237674  ...  82.373605             82.921853
+22  3072.0  82.181572  ...  88.750943             89.451983
+23  3200.0  84.544253  ...  95.380032             95.096582
+24  3328.0  83.130825  ...  83.905938             84.397770
+25  3456.0  78.578525  ...  88.790274             90.382926
+26  3584.0  87.211821  ...  98.483450             92.505546
+27  3712.0  84.159518  ...  87.056508             85.751096
+28  3840.0  85.005380  ...  92.390975             85.597527
+29  3968.0  92.372393  ...  84.155345             88.809270
+30  4096.0  86.370931  ...  92.627833             88.185107
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  7.784 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  2.945 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  0.489 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.484 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

@@ -194,36 +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  307.200008   98.303995  307.200008
+0    1024.0  311.088617   98.303995  307.200008
 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
-4    3072.0  511.999982  192.501302  320.556515
+2    2048.0  420.102553  161.684218  325.509933
+3    2560.0  458.507457  181.775141  326.808501
+4    3072.0  511.999982  192.501302  317.793096
 5    3584.0  551.384634  208.271186  311.652167
-6    4096.0  564.965515  220.412561  297.890900
-7    4608.0  507.302750  232.825259  286.507772
-8    5120.0  531.948056  242.845844  285.104413
-9    5632.0  545.032265  243.545956  289.438969
-10   6144.0  548.163546  248.661056  285.767458
+6    4096.0  564.965515  220.412561  295.207204
+7    4608.0  507.302750  232.825259  291.799469
+8    5120.0  529.655159  242.845844  289.811322
+9    5632.0  542.843364  243.545956  288.820505
+10   6144.0  548.163546  248.661056  286.322318
 11   6656.0  534.260858  256.000009  285.767438
 12   7168.0  507.469040  260.654538  286.242939
-13   7680.0  479.999983  262.190612  275.104486
-14   8192.0  462.607053  267.130429  284.939124
-15   8704.0  418.629245  267.472468  284.599455
-16   9216.0  432.000001  272.394084  288.751954
-17   9728.0  440.513191  280.615388  290.027323
-18  10240.0  450.109870  286.433562  287.775181
-19  10752.0  427.231788  247.172406  290.922209
-20  11264.0  427.071098  245.536784  286.676558
-21  11776.0  423.089806  249.667843  288.686414
-22  12288.0  419.504980  254.453844  294.323369
-23  12800.0  414.016170  253.465340  289.538159
-24  13312.0  411.181478  252.759501  289.916513
+13   7680.0  479.999983  262.564106  275.104486
+14   8192.0  463.698115  267.130429  284.939124
+15   8704.0  417.791980  267.815384  284.987724
+16   9216.0  431.157889  272.394084  289.129410
+17   9728.0  439.683593  280.278512  290.027323
+18  10240.0  450.109870  286.433562  290.153487
+19  10752.0  426.525614  247.172406  290.922209
+20  11264.0  427.071098  245.760001  286.676558
+21  11776.0  423.089806  249.888595  288.981596
+22  12288.0  420.102570  254.673582  294.323369
+23  12800.0  414.016170  253.674644  288.180121
+24  13312.0  411.181478  252.959629  289.916513
 25  13824.0  404.604870  257.190689  292.056329
 26  14336.0  393.665895  254.485198  286.719986
-27  14848.0  385.662341  257.665934  289.246765
-28  15360.0  373.874218  257.970599  287.102804
-29  15872.0  371.274849  261.986243  289.899545
+27  14848.0  385.245405  257.665934  289.246765
+28  15360.0  373.495460  257.970599  286.211174
+29  15872.0  371.637071  261.626369  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  12.249 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  11.317 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>13:26.950</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:15.970</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>06:07.784</p></td>
+<td><p>06:02.945</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>03:21.032</p></td>
+<td><p>03:20.138</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>02:12.249</p></td>
+<td><p>02:11.317</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>01:45.396</p></td>
+<td><p>01:41.086</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>00:00.489</p></td>
+<td><p>00:00.484</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: 1d70fc594d33ccbd6e84ded2e0a1794e
+config: 03409dc47225f6d13304842a651eaf7f
 tags: 645f666f9bcd5a90fca523b33c5a78b7