[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: cdc1d640ba7f10ca3869ccb270ba18e8
+config: 456fb2bf2c82c803cfdaa7bcb3e778a9
 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  341.333321  384.000001
+    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
     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  44.385 seconds)
+   **Total running time of the script:** ( 1 minutes  42.600 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   186.181817
     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   163.839992
+    3     640.0  706.206879      640.000002   158.759699
+    4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
-    93  12160.0  814.058574      405.755985   198.936606
+    93  12160.0  814.058574      406.179533   198.834951
     94  12288.0  814.111783      415.661740   199.096718
-    95  12416.0  814.163950      411.296057   198.755369
+    95  12416.0  814.163950      412.149375   198.655991
     96  12544.0  814.214963      412.971190   198.913776
-    97  12672.0  814.265046      412.097543   199.069228
+    97  12672.0  814.265046      411.679167   198.971549
 
     [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  23.498 seconds)
+   **Total running time of the script:** ( 3 minutes  19.345 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  ...   3.276800              2.978909
-    1    384.0   7.372800  ...   7.899428              7.899428
-    2    512.0  14.563555  ...  15.420235             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  39.025776  ...  40.140799             39.025776
-    6   1024.0  49.932191  ...  52.428801             51.150050
+    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  ...  62.929456             62.492442
-    12  1792.0  72.983276  ...  72.047592             72.047592
-    13  1920.0  68.776119  ...  70.172588             69.818184
+    11  1664.0  62.929456  ...  62.492442             61.636381
+    12  1792.0  72.512412  ...  72.512412             72.047592
+    13  1920.0  69.467336  ...  70.172588             69.818184
     14  2048.0  73.262953  ...  76.608294             76.608294
-    15  2176.0  83.155572  ...  85.998493             85.632545
-    16  2304.0  68.251065  ...  76.809875             76.809875
-    17  2432.0  71.305746  ...  85.393507             85.393507
-    18  2560.0  77.283019  ...  80.908642             81.108913
-    19  2688.0  83.369354  ...  90.532356             89.464755
-    20  2816.0  83.873477  ...  83.233226             83.392363
-    21  2944.0  82.034625  ...  82.373605             82.373605
-    22  3072.0  82.062468  ...  88.890270             86.712254
-    23  3200.0  81.632656  ...  94.955488             95.380032
-    24  3328.0  83.034941  ...  84.200347             84.695641
-    25  3456.0  81.766291  ...  90.586029             91.097818
-    26  3584.0  85.879071  ...  92.600816             95.451583
-    27  3712.0  85.601834  ...  89.835744             91.606915
-    28  3840.0  84.679936  ...  85.996889             83.718392
-    29  3968.0  92.864488  ...  85.034103             90.859224
-    30  4096.0  85.818678  ...  84.947927             91.056800
+    15  2176.0  83.500614  ...  85.998493             85.632545
+    16  2304.0  68.643310  ...  77.057651             76.319081
+    17  2432.0  71.305746  ...  85.393507             85.134737
+    18  2560.0  78.019048  ...  80.709358             81.108913
+    19  2688.0  83.004501  ...  89.464755             89.254248
+    20  2816.0  80.767055  ...  83.552120             82.602666
+    21  2944.0  81.298583  ...  82.237674             81.967162
+    22  3072.0  81.707223  ...  88.473602             87.516392
+    23  3200.0  84.377059  ...  94.955488             94.674553
+    24  3328.0  83.034941  ...  84.695641             83.905938
+    25  3456.0  81.108217  ...  85.133652             81.029251
+    26  3584.0  86.623693  ...  98.483450             98.160909
+    27  3712.0  81.682211  ...  88.404730             84.017953
+    28  3840.0  82.592983  ...  92.006659             85.169042
+    29  3968.0  90.791620  ...  86.236000             90.522206
+    30  4096.0  86.369197  ...  85.001726             91.304576
 
     [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  8.116 seconds)
+   **Total running time of the script:** ( 6 minutes  0.645 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  0.483 seconds)
+   **Total running time of the script:** ( 0 minutes  0.482 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   99.497980  307.200008
-    1    1536.0  347.773587  133.083026  338.201833
-    2    2048.0  423.724127  159.067963  321.254900
-    3    2560.0  451.764698  183.402991  330.322572
-    4    3072.0  508.468972  193.005236  315.076914
-    5    3584.0  547.872604  208.271186  308.301075
-    6    4096.0  564.965515  220.412561  301.546004
+    0    1024.0  311.088617   98.303995  303.407414
+    1    1536.0  347.773587  134.050910  341.333333
+    2    2048.0  420.102553  161.684218  325.509933
+    3    2560.0  455.111129  181.238943  326.808501
+    4    3072.0  511.999982  191.999993  317.793096
+    5    3584.0  547.872604  207.768111  310.527060
+    6    4096.0  564.965515  219.919464  295.207204
     7    4608.0  504.986315  232.825259  291.799469
-    8    5120.0  529.655159  240.941184  285.767451
-    9    5632.0  547.238891  241.371422  288.820505
-    10   6144.0  552.269672  249.502530  286.879370
-    11   6656.0  536.053693  254.369423  284.242007
-    12   7168.0  515.065851  252.616738  276.134819
-    13   7680.0  486.332448  263.314295  280.547947
-    14   8192.0  463.698115  263.196793  280.467910
-    15   8704.0  416.958106  265.096445  283.440968
-    16   9216.0  431.157889  271.724806  287.625496
-    17   9728.0  441.345926  280.615388  288.593329
-    18  10240.0  446.836366  285.767451  289.469963
-    19  10752.0  429.364408  246.464170  289.941565
-    20  11264.0  423.724120  244.869560  284.864065
-    21  11776.0  421.826879  250.109737  289.573776
-    22  12288.0  419.504980  253.796902  294.323369
-    23  12800.0  415.696898  253.256381  287.640454
-    24  13312.0  409.599999  253.160074  290.707920
-    25  13824.0  405.098897  256.593977  291.799461
-    26  14336.0  397.761846  254.673567  287.438588
-    27  14848.0  381.942121  256.922861  287.612590
-    28  15360.0  376.932517  259.971797  288.676598
-    29  15872.0  367.691129  264.717162  292.796308
+    8    5120.0  527.381977  242.845844  288.450695
+    9    5632.0  542.843364  243.107920  288.820505
+    10   6144.0  546.133354  248.661056  286.879370
+    11   6656.0  532.479975  256.000009  285.767438
+    12   7168.0  505.976473  260.654538  286.242939
+    13   7680.0  481.253256  262.190612  278.429013
+    14   8192.0  463.698115  267.130429  284.939124
+    15   8704.0  417.791980  267.815384  284.987724
+    16   9216.0  432.845409  272.394084  288.751954
+    17   9728.0  439.683593  280.278512  289.667485
+    18  10240.0  448.467168  286.433562  290.153487
+    19  10752.0  425.821771  247.172406  290.922209
+    20  11264.0  427.071098  245.760001  286.676558
+    21  11776.0  423.724129  249.667843  288.981596
+    22  12288.0  419.504980  254.673582  294.323369
+    23  12800.0  413.458944  253.674644  288.180121
+    24  13312.0  412.242569  252.859526  289.916513
+    25  13824.0  405.594132  257.190689  292.056329
+    26  14336.0  394.568805  254.297107  286.719986
+    27  14848.0  386.498925  257.665934  289.246765
+    28  15360.0  373.117425  257.970599  286.211174
+    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  11.911 seconds)
+   **Total running time of the script:** ( 2 minutes  12.550 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
 =================
-**13:28.393** total execution time for **getting-started_tutorials** files:
+**13:15.622** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:08.116 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:00.645 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:23.498 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:19.345 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:11.911 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:12.550 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:44.385 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:42.600 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.483 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.482 | 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  341.333321  384.000001
+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
 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  44.385 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  42.600 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   186.181817
 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   163.839992
+3     640.0  706.206879      640.000002   158.759699
+4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
-93  12160.0  814.058574      405.755985   198.936606
+93  12160.0  814.058574      406.179533   198.834951
 94  12288.0  814.111783      415.661740   199.096718
-95  12416.0  814.163950      411.296057   198.755369
+95  12416.0  814.163950      412.149375   198.655991
 96  12544.0  814.214963      412.971190   198.913776
-97  12672.0  814.265046      412.097543   199.069228
+97  12672.0  814.265046      411.679167   198.971549
 
 [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  23.498 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  19.345 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  ...   3.276800              2.978909
-1    384.0   7.372800  ...   7.899428              7.899428
-2    512.0  14.563555  ...  15.420235             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  39.025776  ...  40.140799             39.025776
-6   1024.0  49.932191  ...  52.428801             51.150050
+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  ...  62.929456             62.492442
-12  1792.0  72.983276  ...  72.047592             72.047592
-13  1920.0  68.776119  ...  70.172588             69.818184
+11  1664.0  62.929456  ...  62.492442             61.636381
+12  1792.0  72.512412  ...  72.512412             72.047592
+13  1920.0  69.467336  ...  70.172588             69.818184
 14  2048.0  73.262953  ...  76.608294             76.608294
-15  2176.0  83.155572  ...  85.998493             85.632545
-16  2304.0  68.251065  ...  76.809875             76.809875
-17  2432.0  71.305746  ...  85.393507             85.393507
-18  2560.0  77.283019  ...  80.908642             81.108913
-19  2688.0  83.369354  ...  90.532356             89.464755
-20  2816.0  83.873477  ...  83.233226             83.392363
-21  2944.0  82.034625  ...  82.373605             82.373605
-22  3072.0  82.062468  ...  88.890270             86.712254
-23  3200.0  81.632656  ...  94.955488             95.380032
-24  3328.0  83.034941  ...  84.200347             84.695641
-25  3456.0  81.766291  ...  90.586029             91.097818
-26  3584.0  85.879071  ...  92.600816             95.451583
-27  3712.0  85.601834  ...  89.835744             91.606915
-28  3840.0  84.679936  ...  85.996889             83.718392
-29  3968.0  92.864488  ...  85.034103             90.859224
-30  4096.0  85.818678  ...  84.947927             91.056800
+15  2176.0  83.500614  ...  85.998493             85.632545
+16  2304.0  68.643310  ...  77.057651             76.319081
+17  2432.0  71.305746  ...  85.393507             85.134737
+18  2560.0  78.019048  ...  80.709358             81.108913
+19  2688.0  83.004501  ...  89.464755             89.254248
+20  2816.0  80.767055  ...  83.552120             82.602666
+21  2944.0  81.298583  ...  82.237674             81.967162
+22  3072.0  81.707223  ...  88.473602             87.516392
+23  3200.0  84.377059  ...  94.955488             94.674553
+24  3328.0  83.034941  ...  84.695641             83.905938
+25  3456.0  81.108217  ...  85.133652             81.029251
+26  3584.0  86.623693  ...  98.483450             98.160909
+27  3712.0  81.682211  ...  88.404730             84.017953
+28  3840.0  82.592983  ...  92.006659             85.169042
+29  3968.0  90.791620  ...  86.236000             90.522206
+30  4096.0  86.369197  ...  85.001726             91.304576
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  8.116 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  0.645 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  0.483 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.482 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   99.497980  307.200008
-1    1536.0  347.773587  133.083026  338.201833
-2    2048.0  423.724127  159.067963  321.254900
-3    2560.0  451.764698  183.402991  330.322572
-4    3072.0  508.468972  193.005236  315.076914
-5    3584.0  547.872604  208.271186  308.301075
-6    4096.0  564.965515  220.412561  301.546004
+0    1024.0  311.088617   98.303995  303.407414
+1    1536.0  347.773587  134.050910  341.333333
+2    2048.0  420.102553  161.684218  325.509933
+3    2560.0  455.111129  181.238943  326.808501
+4    3072.0  511.999982  191.999993  317.793096
+5    3584.0  547.872604  207.768111  310.527060
+6    4096.0  564.965515  219.919464  295.207204
 7    4608.0  504.986315  232.825259  291.799469
-8    5120.0  529.655159  240.941184  285.767451
-9    5632.0  547.238891  241.371422  288.820505
-10   6144.0  552.269672  249.502530  286.879370
-11   6656.0  536.053693  254.369423  284.242007
-12   7168.0  515.065851  252.616738  276.134819
-13   7680.0  486.332448  263.314295  280.547947
-14   8192.0  463.698115  263.196793  280.467910
-15   8704.0  416.958106  265.096445  283.440968
-16   9216.0  431.157889  271.724806  287.625496
-17   9728.0  441.345926  280.615388  288.593329
-18  10240.0  446.836366  285.767451  289.469963
-19  10752.0  429.364408  246.464170  289.941565
-20  11264.0  423.724120  244.869560  284.864065
-21  11776.0  421.826879  250.109737  289.573776
-22  12288.0  419.504980  253.796902  294.323369
-23  12800.0  415.696898  253.256381  287.640454
-24  13312.0  409.599999  253.160074  290.707920
-25  13824.0  405.098897  256.593977  291.799461
-26  14336.0  397.761846  254.673567  287.438588
-27  14848.0  381.942121  256.922861  287.612590
-28  15360.0  376.932517  259.971797  288.676598
-29  15872.0  367.691129  264.717162  292.796308
+8    5120.0  527.381977  242.845844  288.450695
+9    5632.0  542.843364  243.107920  288.820505
+10   6144.0  546.133354  248.661056  286.879370
+11   6656.0  532.479975  256.000009  285.767438
+12   7168.0  505.976473  260.654538  286.242939
+13   7680.0  481.253256  262.190612  278.429013
+14   8192.0  463.698115  267.130429  284.939124
+15   8704.0  417.791980  267.815384  284.987724
+16   9216.0  432.845409  272.394084  288.751954
+17   9728.0  439.683593  280.278512  289.667485
+18  10240.0  448.467168  286.433562  290.153487
+19  10752.0  425.821771  247.172406  290.922209
+20  11264.0  427.071098  245.760001  286.676558
+21  11776.0  423.724129  249.667843  288.981596
+22  12288.0  419.504980  254.673582  294.323369
+23  12800.0  413.458944  253.674644  288.180121
+24  13312.0  412.242569  252.859526  289.916513
+25  13824.0  405.594132  257.190689  292.056329
+26  14336.0  394.568805  254.297107  286.719986
+27  14848.0  386.498925  257.665934  289.246765
+28  15360.0  373.117425  257.970599  286.211174
+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  11.911 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  12.550 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>13:28.393</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:15.622</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>06:08.116</p></td>
+<td><p>06:00.645</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>03:23.498</p></td>
+<td><p>03:19.345</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>02:11.911</p></td>
+<td><p>02:12.550</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>01:44.385</p></td>
+<td><p>01:42.600</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>00:00.483</p></td>
+<td><p>00:00.482</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: 549a5851dcb8790c4c62876a551ba451
+config: 27fe8ebc933e4ad0f9352faba2dbdccd
 tags: 645f666f9bcd5a90fca523b33c5a78b7