[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: 3878ccda3bb3822822ec2c316fefdba3
+config: 755abcbf8a2d9de4568449f6de84db76
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -241,7 +241,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
     6      262144.0  341.333321  341.333321
     7      524288.0  472.615390  472.615390
     8     1048576.0  614.400016  614.400016
-    9     2097152.0  722.823517  722.823517
+    9     2097152.0  722.823517  702.171410
     10    4194304.0  780.190482  780.190482
     11    8388608.0  812.429770  812.429770
     12   16777216.0  833.084721  833.084721
@@ -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  39.141 seconds)
+   **Total running time of the script:** ( 1 minutes  45.985 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      512.000001   190.511628
+    0     256.0  512.000001      512.000001   184.089886
     1     384.0  614.400016      585.142862   153.600004
     2     512.0  655.360017      585.142849   154.566038
-    3     640.0  706.206879      640.000002   160.000000
-    4     768.0  722.823517      664.216187   163.839992
+    3     640.0  682.666684      640.000002   158.759699
+    4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
-    93  12160.0  812.359066      405.755985   199.038365
-    94  12288.0  812.429770      415.222812   199.298541
-    95  12416.0  812.498981      411.296057   198.954424
-    96  12544.0  812.566838      412.546756   199.111113
-    97  12672.0  811.007961      411.679167   199.264875
+    93  12160.0  812.359066      406.179533   198.834951
+    94  12288.0  812.429770      415.661740   199.096718
+    95  12416.0  812.498981      412.149375   198.755369
+    96  12544.0  812.566838      412.546756   199.012395
+    97  12672.0  811.007961      412.097543   199.167004
 
     [98 rows x 4 columns]
 
@@ -306,7 +306,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  21.844 seconds)
+   **Total running time of the script:** ( 3 minutes  22.172 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -459,9 +459,9 @@ 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   2.849391  ...   3.276800              2.978909
-    1    384.0   7.372800  ...   8.507077              8.507077
-    2    512.0  14.563555  ...  16.384000             16.384000
+    0    256.0   2.730667  ...   2.978909              2.978909
+    1    384.0   7.372800  ...   7.899428              7.899428
+    2    512.0  14.563555  ...  15.420235             15.420235
     3    640.0  22.260869  ...  24.380953             24.380953
     4    768.0  32.768000  ...  35.389441             34.028308
     5    896.0  39.025776  ...  41.321411             39.025776
@@ -470,26 +470,26 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
     8   1280.0  51.200001  ...  57.690139             57.690139
     9   1408.0  64.138541  ...  69.009825             67.305878
     10  1536.0  79.526831  ...  80.430545             78.643199
-    11  1664.0  62.929456  ...  63.372618             62.061463
-    12  1792.0  72.983276  ...  63.499573             63.142831
-    13  1920.0  69.467336  ...  71.626943             70.892307
-    14  2048.0  73.262953  ...  78.033565             76.959706
-    15  2176.0  83.155572  ...  87.115360             85.632545
-    16  2304.0  68.251065  ...  78.064941             76.809875
-    17  2432.0  71.305746  ...  75.522751             74.521127
-    18  2560.0  77.833728  ...  81.920002             81.310171
-    19  2688.0  84.108772  ...  90.966561             90.102270
-    20  2816.0  79.443003  ...  84.687779             82.602666
-    21  2944.0  82.646820  ...  83.337844             82.921853
-    22  3072.0  82.301023  ...  89.310890             88.750943
-    23  3200.0  84.768213  ...  96.385543             94.674553
-    24  3328.0  83.034941  ...  83.808259             86.011103
-    25  3456.0  82.519518  ...  90.281712             88.986281
-    26  3584.0  83.954614  ...  88.496679             95.451583
-    27  3712.0  84.159518  ...  87.552452             86.942857
-    28  3840.0  85.136259  ...  91.625518             86.332554
-    29  3968.0  91.816356  ...  85.091543             91.130650
-    30  4096.0  86.508362  ...  88.098281             92.563952
+    11  1664.0  63.372618  ...  63.372618             62.492442
+    12  1792.0  72.983276  ...  63.142831             63.142831
+    13  1920.0  69.120002  ...  71.626943             70.892307
+    14  2048.0  73.262953  ...  78.033565             77.314362
+    15  2176.0  83.155572  ...  87.494120             85.632545
+    16  2304.0  68.251065  ...  78.320893             77.057651
+    17  2432.0  71.305746  ...  75.522751             75.118889
+    18  2560.0  77.833728  ...  82.125311             80.908642
+    19  2688.0  83.922689  ...  89.676257             89.254248
+    20  2816.0  81.674548  ...  84.523664             82.602666
+    21  2944.0  82.373605  ...  83.337844             82.921853
+    22  3072.0  82.301023  ...  89.170242             88.612060
+    23  3200.0  84.768213  ...  96.530922             94.955488
+    24  3328.0  83.808259  ...  85.602017             85.602017
+    25  3456.0  81.026701  ...  87.536988             86.783176
+    26  3584.0  87.381330  ...  98.375705             96.996106
+    27  3712.0  82.355598  ...  89.674457             87.475786
+    28  3840.0  84.100380  ...  93.090912             86.943395
+    29  3968.0  92.652949  ...  85.932350             91.266964
+    30  4096.0  86.396989  ...  89.181212             82.342167
 
     [31 rows x 5 columns]
 
@@ -499,7 +499,7 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 6 minutes  5.171 seconds)
+   **Total running time of the script:** ( 6 minutes  3.569 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  0.529 seconds)
+   **Total running time of the script:** ( 0 minutes  0.490 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

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

@@ -40,34 +40,34 @@ Layer Normalization
               N      Triton       Torch        Apex
     0    1024.0  585.142849  277.694907  468.114273
     1    1536.0  630.153868  323.368435  511.999982
-    2    2048.0  682.666643  337.814445  520.126988
+    2    2048.0  682.666643  334.367358  520.126988
     3    2560.0  694.237267  362.477870  512.000013
     4    3072.0  712.347810  375.206126  501.551037
-    5    3584.0  725.873439  384.859062  458.751978
+    5    3584.0  725.873439  384.859062  455.111115
     6    4096.0  728.177767  381.023256  455.111095
-    7    4608.0  670.254540  396.387087  426.173427
-    8    5120.0  688.403381  397.669909  424.455959
-    9    5632.0  704.000002  396.969169  411.470331
-    10   6144.0  702.171410  402.885254  409.600010
-    11   6656.0  705.271522  400.360920  398.861429
-    12   7168.0  695.078767  383.571898  382.293315
-    13   7680.0  682.666656  391.337574  386.415087
-    14   8192.0  639.375598  391.259714  376.643677
-    15   8704.0  627.315309  392.292962  381.545190
-    16   9216.0  609.322328  405.098894  382.010363
-    17   9728.0  591.817503  408.524944  383.369452
-    18  10240.0  568.888869  408.578556  382.803739
-    19  10752.0  551.384634  411.559798  380.601764
-    20  11264.0  536.380957  402.285709  371.595879
-    21  11776.0  524.835658  408.711507  377.587162
-    22  12288.0  517.389457  413.042029  382.505826
-    23  12800.0  505.679014  409.599981  377.163903
-    24  13312.0  495.330249  404.159395  376.310952
-    25  13824.0  482.934503  410.359948  378.739711
-    26  14336.0  470.997935  401.007000  372.969090
-    27  14848.0  461.297068  404.715511  374.122832
-    28  15360.0  454.269882  406.214870  377.511515
-    29  15872.0  447.887117  410.261713  377.343238
+    7    4608.0  670.254540  396.387087  428.651163
+    8    5120.0  688.403381  397.669909  422.268057
+    9    5632.0  704.000002  395.228063  415.262685
+    10   6144.0  702.171410  402.885254  411.313806
+    11   6656.0  705.271522  400.360920  400.360920
+    12   7168.0  690.891575  396.844306  387.459443
+    13   7680.0  682.666656  392.587863  387.634072
+    14   8192.0  636.271854  393.609605  371.308771
+    15   8704.0  627.315309  389.005597  380.502740
+    16   9216.0  606.814809  407.337026  383.002605
+    17   9728.0  589.575753  409.599987  383.369452
+    18  10240.0  566.920437  408.578556  382.803739
+    19  10752.0  549.623009  411.559798  381.445676
+    20  11264.0  536.380957  406.826188  373.134567
+    21  11776.0  523.377770  409.599991  377.587162
+    22  12288.0  518.754611  413.911572  383.251457
+    23  12800.0  505.679014  410.420828  376.470582
+    24  13312.0  494.180982  405.699062  376.310952
+    25  13824.0  482.934503  411.888257  379.389355
+    26  14336.0  471.967074  406.695045  374.185964
+    27  14848.0  461.297068  408.192434  375.304904
+    28  15360.0  454.269882  406.214870  378.092307
+    29  15872.0  447.887117  406.974373  376.225175
 
 
 
@@ -389,7 +389,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 5 minutes  24.150 seconds)
+   **Total running time of the script:** ( 5 minutes  24.288 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
 =================
-**16:30.835** total execution time for **getting-started_tutorials** files:
+**16:36.505** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:05.171 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:03.569 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:24.150 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:24.288 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:21.844 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:22.172 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:39.141 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:45.985 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.529 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.490 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -331,7 +331,7 @@ for different problem sizes.</p>
 6      262144.0  341.333321  341.333321
 7      524288.0  472.615390  472.615390
 8     1048576.0  614.400016  614.400016
-9     2097152.0  722.823517  722.823517
+9     2097152.0  722.823517  702.171410
 10    4194304.0  780.190482  780.190482
 11    8388608.0  812.429770  812.429770
 12   16777216.0  833.084721  833.084721
@@ -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  39.141 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  45.985 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      512.000001   190.511628
+0     256.0  512.000001      512.000001   184.089886
 1     384.0  614.400016      585.142862   153.600004
 2     512.0  655.360017      585.142849   154.566038
-3     640.0  706.206879      640.000002   160.000000
-4     768.0  722.823517      664.216187   163.839992
+3     640.0  682.666684      640.000002   158.759699
+4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
-93  12160.0  812.359066      405.755985   199.038365
-94  12288.0  812.429770      415.222812   199.298541
-95  12416.0  812.498981      411.296057   198.954424
-96  12544.0  812.566838      412.546756   199.111113
-97  12672.0  811.007961      411.679167   199.264875
+93  12160.0  812.359066      406.179533   198.834951
+94  12288.0  812.429770      415.661740   199.096718
+95  12416.0  812.498981      412.149375   198.755369
+96  12544.0  812.566838      412.546756   199.012395
+97  12672.0  811.007961      412.097543   199.167004
 
 [98 rows x 4 columns]
 </pre></div>
@@ -392,7 +392,7 @@ We will then compare its performance against (1) <code class="code docutils lite
 Note however that the PyTorch <cite>softmax</cite> operation is more general and will works on tensors of any shape.</p></li>
 </ul>
 </div></blockquote>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  21.844 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  22.172 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

@@ -565,9 +565,9 @@ 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   2.849391  ...   3.276800              2.978909
-1    384.0   7.372800  ...   8.507077              8.507077
-2    512.0  14.563555  ...  16.384000             16.384000
+0    256.0   2.730667  ...   2.978909              2.978909
+1    384.0   7.372800  ...   7.899428              7.899428
+2    512.0  14.563555  ...  15.420235             15.420235
 3    640.0  22.260869  ...  24.380953             24.380953
 4    768.0  32.768000  ...  35.389441             34.028308
 5    896.0  39.025776  ...  41.321411             39.025776
@@ -576,31 +576,31 @@ torch_output=tensor([[  1.1045, -36.9688,  31.4688,  ..., -11.3906,  24.4531, -3
 8   1280.0  51.200001  ...  57.690139             57.690139
 9   1408.0  64.138541  ...  69.009825             67.305878
 10  1536.0  79.526831  ...  80.430545             78.643199
-11  1664.0  62.929456  ...  63.372618             62.061463
-12  1792.0  72.983276  ...  63.499573             63.142831
-13  1920.0  69.467336  ...  71.626943             70.892307
-14  2048.0  73.262953  ...  78.033565             76.959706
-15  2176.0  83.155572  ...  87.115360             85.632545
-16  2304.0  68.251065  ...  78.064941             76.809875
-17  2432.0  71.305746  ...  75.522751             74.521127
-18  2560.0  77.833728  ...  81.920002             81.310171
-19  2688.0  84.108772  ...  90.966561             90.102270
-20  2816.0  79.443003  ...  84.687779             82.602666
-21  2944.0  82.646820  ...  83.337844             82.921853
-22  3072.0  82.301023  ...  89.310890             88.750943
-23  3200.0  84.768213  ...  96.385543             94.674553
-24  3328.0  83.034941  ...  83.808259             86.011103
-25  3456.0  82.519518  ...  90.281712             88.986281
-26  3584.0  83.954614  ...  88.496679             95.451583
-27  3712.0  84.159518  ...  87.552452             86.942857
-28  3840.0  85.136259  ...  91.625518             86.332554
-29  3968.0  91.816356  ...  85.091543             91.130650
-30  4096.0  86.508362  ...  88.098281             92.563952
+11  1664.0  63.372618  ...  63.372618             62.492442
+12  1792.0  72.983276  ...  63.142831             63.142831
+13  1920.0  69.120002  ...  71.626943             70.892307
+14  2048.0  73.262953  ...  78.033565             77.314362
+15  2176.0  83.155572  ...  87.494120             85.632545
+16  2304.0  68.251065  ...  78.320893             77.057651
+17  2432.0  71.305746  ...  75.522751             75.118889
+18  2560.0  77.833728  ...  82.125311             80.908642
+19  2688.0  83.922689  ...  89.676257             89.254248
+20  2816.0  81.674548  ...  84.523664             82.602666
+21  2944.0  82.373605  ...  83.337844             82.921853
+22  3072.0  82.301023  ...  89.170242             88.612060
+23  3200.0  84.768213  ...  96.530922             94.955488
+24  3328.0  83.808259  ...  85.602017             85.602017
+25  3456.0  81.026701  ...  87.536988             86.783176
+26  3584.0  87.381330  ...  98.375705             96.996106
+27  3712.0  82.355598  ...  89.674457             87.475786
+28  3840.0  84.100380  ...  93.090912             86.943395
+29  3968.0  92.652949  ...  85.932350             91.266964
+30  4096.0  86.396989  ...  89.181212             82.342167
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  5.171 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  3.569 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  0.529 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.490 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

@@ -196,34 +196,34 @@ to download the full example code</p>
           N      Triton       Torch        Apex
 0    1024.0  585.142849  277.694907  468.114273
 1    1536.0  630.153868  323.368435  511.999982
-2    2048.0  682.666643  337.814445  520.126988
+2    2048.0  682.666643  334.367358  520.126988
 3    2560.0  694.237267  362.477870  512.000013
 4    3072.0  712.347810  375.206126  501.551037
-5    3584.0  725.873439  384.859062  458.751978
+5    3584.0  725.873439  384.859062  455.111115
 6    4096.0  728.177767  381.023256  455.111095
-7    4608.0  670.254540  396.387087  426.173427
-8    5120.0  688.403381  397.669909  424.455959
-9    5632.0  704.000002  396.969169  411.470331
-10   6144.0  702.171410  402.885254  409.600010
-11   6656.0  705.271522  400.360920  398.861429
-12   7168.0  695.078767  383.571898  382.293315
-13   7680.0  682.666656  391.337574  386.415087
-14   8192.0  639.375598  391.259714  376.643677
-15   8704.0  627.315309  392.292962  381.545190
-16   9216.0  609.322328  405.098894  382.010363
-17   9728.0  591.817503  408.524944  383.369452
-18  10240.0  568.888869  408.578556  382.803739
-19  10752.0  551.384634  411.559798  380.601764
-20  11264.0  536.380957  402.285709  371.595879
-21  11776.0  524.835658  408.711507  377.587162
-22  12288.0  517.389457  413.042029  382.505826
-23  12800.0  505.679014  409.599981  377.163903
-24  13312.0  495.330249  404.159395  376.310952
-25  13824.0  482.934503  410.359948  378.739711
-26  14336.0  470.997935  401.007000  372.969090
-27  14848.0  461.297068  404.715511  374.122832
-28  15360.0  454.269882  406.214870  377.511515
-29  15872.0  447.887117  410.261713  377.343238
+7    4608.0  670.254540  396.387087  428.651163
+8    5120.0  688.403381  397.669909  422.268057
+9    5632.0  704.000002  395.228063  415.262685
+10   6144.0  702.171410  402.885254  411.313806
+11   6656.0  705.271522  400.360920  400.360920
+12   7168.0  690.891575  396.844306  387.459443
+13   7680.0  682.666656  392.587863  387.634072
+14   8192.0  636.271854  393.609605  371.308771
+15   8704.0  627.315309  389.005597  380.502740
+16   9216.0  606.814809  407.337026  383.002605
+17   9728.0  589.575753  409.599987  383.369452
+18  10240.0  566.920437  408.578556  382.803739
+19  10752.0  549.623009  411.559798  381.445676
+20  11264.0  536.380957  406.826188  373.134567
+21  11776.0  523.377770  409.599991  377.587162
+22  12288.0  518.754611  413.911572  383.251457
+23  12800.0  505.679014  410.420828  376.470582
+24  13312.0  494.180982  405.699062  376.310952
+25  13824.0  482.934503  411.888257  379.389355
+26  14336.0  471.967074  406.695045  374.185964
+27  14848.0  461.297068  408.192434  375.304904
+28  15360.0  454.269882  406.214870  378.092307
+29  15872.0  447.887117  406.974373  376.225175
 </pre></div>
 </div>
 <div class="line-block">
@@ -537,7 +537,7 @@ to download the full example code</p>
 <span class="n">bench_layer_norm</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">save_path</span><span class="o">=</span><span class="s1">&#39;.&#39;</span><span class="p">,</span> <span class="n">print_data</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  24.150 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  24.288 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>16:30.835</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>16:36.505</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>06:05.171</p></td>
+<td><p>06:03.569</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="05-layer-norm.html#sphx-glr-getting-started-tutorials-05-layer-norm-py"><span class="std std-ref">Layer Normalization</span></a> (<code class="docutils literal notranslate"><span class="pre">05-layer-norm.py</span></code>)</p></td>
-<td><p>05:24.150</p></td>
+<td><p>05:24.288</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="02-fused-softmax.html#sphx-glr-getting-started-tutorials-02-fused-softmax-py"><span class="std std-ref">Fused Softmax</span></a> (<code class="docutils literal notranslate"><span class="pre">02-fused-softmax.py</span></code>)</p></td>
-<td><p>03:21.844</p></td>
+<td><p>03:22.172</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>01:39.141</p></td>
+<td><p>01:45.985</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>00:00.529</p></td>
+<td><p>00:00.490</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: 74da96fc2e2769477842bc3f36a7e78b
+config: a3eaf7d751889cb3cfc2504debd33ded
 tags: 645f666f9bcd5a90fca523b33c5a78b7