[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: eac485c17911d9cfbfb6f06e61db588a
+config: b6cd1dcd169459e28f870f9b1b9247aa
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -235,7 +235,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
     0        4096.0    9.600000    9.600000
     1        8192.0   19.200000   19.200000
     2       16384.0   38.400001   38.400001
-    3       32768.0   63.999998   63.999998
+    3       32768.0   63.999998   76.800002
     4       65536.0  127.999995  127.999995
     5      131072.0  219.428568  219.428568
     6      262144.0  341.333321  384.000001
@@ -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  43.089 seconds)
+   **Total running time of the script:** ( 1 minutes  33.654 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   190.511628
+    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
     ..      ...         ...             ...          ...
-    93  12160.0  814.058574      406.179533   198.631953
-    94  12288.0  814.111783      415.661740   198.895304
-    95  12416.0  814.163950      412.577363   198.457532
-    96  12544.0  814.214963      412.971190   198.716830
-    97  12672.0  814.265046      412.097543   198.776477
+    93  12160.0  814.058574      406.179533   199.038365
+    94  12288.0  814.111783      415.222812   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      411.679167   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  21.816 seconds)
+   **Total running time of the script:** ( 3 minutes  20.157 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  ...   2.978909              2.978909
     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  39.025776  ...  39.025776             39.025776
-    6   1024.0  51.150050  ...  52.428801             52.428801
+    5    896.0  39.025776  ...  40.140799             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             66.485074
-    10  1536.0  80.430545  ...  79.526831             78.643199
-    11  1664.0  62.929456  ...  62.492442             62.061463
-    12  1792.0  72.983276  ...  71.588687             72.047592
-    13  1920.0  69.120002  ...  70.172588             70.172588
-    14  2048.0  73.262953  ...  76.608294             76.608294
-    15  2176.0  83.155572  ...  85.998493             85.632545
+    10  1536.0  79.526831  ...  79.526831             78.643199
+    11  1664.0  62.929456  ...  62.061463             61.636381
+    12  1792.0  72.512412  ...  72.047592             72.047592
+    13  1920.0  68.776119  ...  70.530615             70.530615
+    14  2048.0  73.584279  ...  76.959706             76.608294
+    15  2176.0  83.500614  ...  85.998493             85.632545
     16  2304.0  68.446623  ...  76.319081             76.319081
-    17  2432.0  71.305746  ...  84.621881             84.115159
-    18  2560.0  78.019048  ...  81.108913             80.709358
-    19  2688.0  83.004501  ...  89.464755             89.464755
-    20  2816.0  82.916747  ...  82.759409             82.290955
-    21  2944.0  81.298583  ...  82.509987             82.646820
-    22  3072.0  81.825298  ...  84.135370             89.030036
-    23  3200.0  84.488448  ...  94.955488             94.604578
-    24  3328.0  82.939284  ...  81.346098             83.905938
-    25  3456.0  81.766291  ...  87.775250             90.790053
-    26  3584.0  87.296493  ...  97.947050             90.276496
-    27  3712.0  84.159518  ...  87.018592             85.748791
-    28  3840.0  84.874902  ...  92.313853             84.552479
-    29  3968.0  92.302520  ...  85.152783             91.028675
-    30  4096.0  86.703957  ...  85.434583             91.211502
+    17  2432.0  71.305746  ...  74.719317             85.134737
+    18  2560.0  78.019048  ...  80.709358             80.313727
+    19  2688.0  83.737433  ...  88.628636             89.254248
+    20  2816.0  79.879498  ...  83.233226             83.233226
+    21  2944.0  82.169877  ...  82.237674             82.102191
+    22  3072.0  81.121923  ...  88.612060             88.335577
+    23  3200.0  83.879425  ...  95.096582             95.380032
+    24  3328.0  82.843841  ...  84.200347             84.397770
+    25  3456.0  77.745004  ...  91.200871             84.686523
+    26  3584.0  86.540320  ...  97.840469             98.053863
+    27  3712.0  82.491612  ...  87.094458             86.867254
+    28  3840.0  81.859361  ...  90.058629             88.121115
+    29  3968.0  88.938731  ...  91.062642             86.880696
+    30  4096.0  93.012976  ...  91.242506             87.267706
 
     [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  1.969 seconds)
+   **Total running time of the script:** ( 5 minutes  57.748 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  0.479 seconds)
+   **Total running time of the script:** ( 0 minutes  0.522 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  311.088617   98.303995  307.200008
+    0    1024.0  307.200008   98.303995  307.200008
     1    1536.0  347.773587  134.050910  341.333333
     2    2048.0  420.102553  161.154101  334.367350
-    3    2560.0  458.507457  181.238943  330.322572
+    3    2560.0  455.111129  181.238943  330.322572
     4    3072.0  511.999982  191.999993  320.556515
     5    3584.0  551.384634  207.768111  310.527060
-    6    4096.0  564.965515  220.412561  297.890900
+    6    4096.0  568.231237  220.412561  298.796351
     7    4608.0  504.986315  232.825259  286.507772
-    8    5120.0  529.655159  242.845844  285.104413
+    8    5120.0  527.381977  242.845844  284.444444
     9    5632.0  542.843364  243.545956  289.438969
     10   6144.0  546.133354  248.661056  286.879370
     11   6656.0  532.479975  256.000009  285.767438
     12   7168.0  507.469040  260.654538  286.242939
     13   7680.0  479.999983  262.190612  278.850215
-    14   8192.0  463.698115  267.130429  284.939124
+    14   8192.0  462.607053  267.130429  284.939124
     15   8704.0  417.791980  267.815384  284.987724
-    16   9216.0  431.157889  272.394084  288.751954
+    16   9216.0  430.319054  272.394084  288.751954
     17   9728.0  438.857162  280.278512  290.027323
-    18  10240.0  449.287041  286.767793  290.153487
+    18  10240.0  449.287041  286.433562  290.153487
     19  10752.0  426.525614  247.172406  290.594591
-    20  11264.0  427.071098  245.536784  286.676558
-    21  11776.0  423.089806  249.778170  288.981596
-    22  12288.0  419.504980  254.673582  294.176573
-    23  12800.0  414.016170  253.465340  289.538159
-    24  13312.0  411.181478  252.759501  289.916513
-    25  13824.0  404.112047  257.190689  292.056329
+    20  11264.0  426.397479  245.536784  286.676558
+    21  11776.0  422.457417  249.667843  288.686414
+    22  12288.0  419.504980  254.673582  294.029924
+    23  12800.0  413.458944  253.465340  289.538159
+    24  13312.0  411.181478  252.559690  289.916513
+    25  13824.0  404.112047  256.991469  292.313649
     26  14336.0  393.215988  254.485198  286.719986
-    27  14848.0  384.829370  257.665934  289.012175
-    28  15360.0  373.495460  257.970599  287.326580
-    29  15872.0  371.274849  261.806182  289.679087
+    27  14848.0  385.245405  257.665934  289.246765
+    28  15360.0  373.874218  257.970599  287.326580
+    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  12.779 seconds)
+   **Total running time of the script:** ( 2 minutes  11.405 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
 =================
-**13:20.131** total execution time for **getting-started_tutorials** files:
+**13:03.486** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:01.969 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:57.748 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:21.816 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:20.157 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:12.779 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:11.405 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:43.089 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:33.654 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.479 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.522 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -325,7 +325,7 @@ for different problem sizes.</p>
 0        4096.0    9.600000    9.600000
 1        8192.0   19.200000   19.200000
 2       16384.0   38.400001   38.400001
-3       32768.0   63.999998   63.999998
+3       32768.0   63.999998   76.800002
 4       65536.0  127.999995  127.999995
 5      131072.0  219.428568  219.428568
 6      262144.0  341.333321  384.000001
@@ -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  43.089 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  33.654 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   190.511628
+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
 ..      ...         ...             ...          ...
-93  12160.0  814.058574      406.179533   198.631953
-94  12288.0  814.111783      415.661740   198.895304
-95  12416.0  814.163950      412.577363   198.457532
-96  12544.0  814.214963      412.971190   198.716830
-97  12672.0  814.265046      412.097543   198.776477
+93  12160.0  814.058574      406.179533   199.038365
+94  12288.0  814.111783      415.222812   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      411.679167   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  21.816 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  20.157 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  ...   2.978909              2.978909
 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  39.025776  ...  39.025776             39.025776
-6   1024.0  51.150050  ...  52.428801             52.428801
+5    896.0  39.025776  ...  40.140799             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             66.485074
-10  1536.0  80.430545  ...  79.526831             78.643199
-11  1664.0  62.929456  ...  62.492442             62.061463
-12  1792.0  72.983276  ...  71.588687             72.047592
-13  1920.0  69.120002  ...  70.172588             70.172588
-14  2048.0  73.262953  ...  76.608294             76.608294
-15  2176.0  83.155572  ...  85.998493             85.632545
+10  1536.0  79.526831  ...  79.526831             78.643199
+11  1664.0  62.929456  ...  62.061463             61.636381
+12  1792.0  72.512412  ...  72.047592             72.047592
+13  1920.0  68.776119  ...  70.530615             70.530615
+14  2048.0  73.584279  ...  76.959706             76.608294
+15  2176.0  83.500614  ...  85.998493             85.632545
 16  2304.0  68.446623  ...  76.319081             76.319081
-17  2432.0  71.305746  ...  84.621881             84.115159
-18  2560.0  78.019048  ...  81.108913             80.709358
-19  2688.0  83.004501  ...  89.464755             89.464755
-20  2816.0  82.916747  ...  82.759409             82.290955
-21  2944.0  81.298583  ...  82.509987             82.646820
-22  3072.0  81.825298  ...  84.135370             89.030036
-23  3200.0  84.488448  ...  94.955488             94.604578
-24  3328.0  82.939284  ...  81.346098             83.905938
-25  3456.0  81.766291  ...  87.775250             90.790053
-26  3584.0  87.296493  ...  97.947050             90.276496
-27  3712.0  84.159518  ...  87.018592             85.748791
-28  3840.0  84.874902  ...  92.313853             84.552479
-29  3968.0  92.302520  ...  85.152783             91.028675
-30  4096.0  86.703957  ...  85.434583             91.211502
+17  2432.0  71.305746  ...  74.719317             85.134737
+18  2560.0  78.019048  ...  80.709358             80.313727
+19  2688.0  83.737433  ...  88.628636             89.254248
+20  2816.0  79.879498  ...  83.233226             83.233226
+21  2944.0  82.169877  ...  82.237674             82.102191
+22  3072.0  81.121923  ...  88.612060             88.335577
+23  3200.0  83.879425  ...  95.096582             95.380032
+24  3328.0  82.843841  ...  84.200347             84.397770
+25  3456.0  77.745004  ...  91.200871             84.686523
+26  3584.0  86.540320  ...  97.840469             98.053863
+27  3712.0  82.491612  ...  87.094458             86.867254
+28  3840.0  81.859361  ...  90.058629             88.121115
+29  3968.0  88.938731  ...  91.062642             86.880696
+30  4096.0  93.012976  ...  91.242506             87.267706
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  1.969 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  57.748 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  0.479 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.522 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  311.088617   98.303995  307.200008
+0    1024.0  307.200008   98.303995  307.200008
 1    1536.0  347.773587  134.050910  341.333333
 2    2048.0  420.102553  161.154101  334.367350
-3    2560.0  458.507457  181.238943  330.322572
+3    2560.0  455.111129  181.238943  330.322572
 4    3072.0  511.999982  191.999993  320.556515
 5    3584.0  551.384634  207.768111  310.527060
-6    4096.0  564.965515  220.412561  297.890900
+6    4096.0  568.231237  220.412561  298.796351
 7    4608.0  504.986315  232.825259  286.507772
-8    5120.0  529.655159  242.845844  285.104413
+8    5120.0  527.381977  242.845844  284.444444
 9    5632.0  542.843364  243.545956  289.438969
 10   6144.0  546.133354  248.661056  286.879370
 11   6656.0  532.479975  256.000009  285.767438
 12   7168.0  507.469040  260.654538  286.242939
 13   7680.0  479.999983  262.190612  278.850215
-14   8192.0  463.698115  267.130429  284.939124
+14   8192.0  462.607053  267.130429  284.939124
 15   8704.0  417.791980  267.815384  284.987724
-16   9216.0  431.157889  272.394084  288.751954
+16   9216.0  430.319054  272.394084  288.751954
 17   9728.0  438.857162  280.278512  290.027323
-18  10240.0  449.287041  286.767793  290.153487
+18  10240.0  449.287041  286.433562  290.153487
 19  10752.0  426.525614  247.172406  290.594591
-20  11264.0  427.071098  245.536784  286.676558
-21  11776.0  423.089806  249.778170  288.981596
-22  12288.0  419.504980  254.673582  294.176573
-23  12800.0  414.016170  253.465340  289.538159
-24  13312.0  411.181478  252.759501  289.916513
-25  13824.0  404.112047  257.190689  292.056329
+20  11264.0  426.397479  245.536784  286.676558
+21  11776.0  422.457417  249.667843  288.686414
+22  12288.0  419.504980  254.673582  294.029924
+23  12800.0  413.458944  253.465340  289.538159
+24  13312.0  411.181478  252.559690  289.916513
+25  13824.0  404.112047  256.991469  292.313649
 26  14336.0  393.215988  254.485198  286.719986
-27  14848.0  384.829370  257.665934  289.012175
-28  15360.0  373.495460  257.970599  287.326580
-29  15872.0  371.274849  261.806182  289.679087
+27  14848.0  385.245405  257.665934  289.246765
+28  15360.0  373.874218  257.970599  287.326580
+29  15872.0  371.274849  261.806182  289.899545
 </pre></div>
 </div>
 <div class="line-block">
@@ -487,7 +487,7 @@ to download the full example code</p>
 <span class="n">bench_layer_norm</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">save_path</span><span class="o">=</span><span class="s1">&#39;.&#39;</span><span class="p">,</span> <span class="n">print_data</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  12.779 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  11.405 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>13:20.131</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:03.486</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>06:01.969</p></td>
+<td><p>05:57.748</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>03:21.816</p></td>
+<td><p>03:20.157</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>02:12.779</p></td>
+<td><p>02:11.405</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>01:43.089</p></td>
+<td><p>01:33.654</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>00:00.479</p></td>
+<td><p>00:00.522</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: 89680b1d82d12ad5a0d2af7995026445
+config: 340ecbef6c08458269cb8727b14813c1
 tags: 645f666f9bcd5a90fca523b33c5a78b7