[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: 54c7171a04b6b620e0e6ab5fa0c013ba
+config: e1bb0268286c4d5902ba27e6c58590e0
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -241,11 +241,11 @@ 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  702.171410  702.171410
+    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
-    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  44.788 seconds)
+   **Total running time of the script:** ( 1 minutes  40.669 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   186.181817
+    0     256.0  546.133347      512.000001   190.511628
     1     384.0  614.400016      585.142862   153.600004
     2     512.0  655.360017      585.142849   154.566038
-    3     640.0  682.666684      640.000002   158.759699
+    3     640.0  706.206879      640.000002   158.759699
     4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
-    93  12160.0  812.359066      406.179533   198.631953
-    94  12288.0  812.429770      415.661740   198.995960
-    95  12416.0  810.840807      412.149375   198.556711
-    96  12544.0  810.925276      412.971190   198.815254
-    97  12672.0  811.007961      412.097543   198.873965
+    93  12160.0  812.359066      406.179533   198.530610
+    94  12288.0  812.429770      415.661740   198.794749
+    95  12416.0  812.498981      411.722274   198.457532
+    96  12544.0  810.925276      412.546756   198.716830
+    97  12672.0  811.007961      412.097543   198.776477
 
     [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  23.445 seconds)
+   **Total running time of the script:** ( 3 minutes  22.074 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -459,37 +459,37 @@ 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   2.730667  ...   2.978909              2.978909
-    1    384.0   7.372800  ...   7.899428              7.899428
-    2    512.0  14.563555  ...  15.420235             15.420235
+    0    256.0   2.730667  ...   3.276800              2.978909
+    1    384.0   7.372800  ...   7.899428              8.507077
+    2    512.0  14.563555  ...  15.420235             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
+    4    768.0  32.768000  ...  35.389441             34.028308
+    5    896.0  37.971025  ...  40.140799             39.025776
     6   1024.0  49.932191  ...  53.773130             52.428801
     7   1152.0  45.242181  ...  48.161033             47.396572
     8   1280.0  51.200001  ...  57.690139             57.690139
-    9   1408.0  64.138541  ...  68.147202             65.684049
-    10  1536.0  79.526831  ...  81.355034             78.643199
-    11  1664.0  62.929456  ...  63.372618             62.492442
+    9   1408.0  64.138541  ...  68.147202             66.485074
+    10  1536.0  79.526831  ...  80.430545             78.643199
+    11  1664.0  63.372618  ...  63.372618             62.492442
     12  1792.0  72.983276  ...  73.460287             59.467852
-    13  1920.0  69.120002  ...  71.257735             71.257735
-    14  2048.0  73.584279  ...  78.398206             77.314362
-    15  2176.0  83.500614  ...  87.494120             85.998493
-    16  2304.0  68.446623  ...  78.064941             77.057651
-    17  2432.0  71.305746  ...  86.711310             85.393507
-    18  2560.0  77.833728  ...  82.956960             81.512437
-    19  2688.0  83.369354  ...  90.316801             89.254248
-    20  2816.0  83.873477  ...  84.035084             82.916747
-    21  2944.0  82.646820  ...  82.237674             81.034195
-    22  3072.0  82.301023  ...  89.735509             86.579673
-    23  3200.0  84.880639  ...  96.096095             94.674553
-    24  3328.0  83.905938  ...  85.602017             84.995628
-    25  3456.0  82.015834  ...  91.928814             88.595129
-    26  3584.0  86.540320  ...  96.579370             87.042978
-    27  3712.0  85.675250  ...  89.835744             87.552452
-    28  3840.0  83.528704  ...  87.841141             89.548180
-    29  3968.0  86.053553  ...  92.442373             87.035620
-    30  4096.0  93.792965  ...  85.055593             85.271746
+    13  1920.0  69.467336  ...  71.257735             70.892307
+    14  2048.0  73.262953  ...  78.398206             77.314362
+    15  2176.0  83.500614  ...  87.494120             86.367588
+    16  2304.0  68.446623  ...  78.064941             77.307030
+    17  2432.0  71.305746  ...  86.711310             75.118889
+    18  2560.0  77.833728  ...  82.125311             81.512437
+    19  2688.0  83.737433  ...  91.185232             89.254248
+    20  2816.0  80.617762  ...  84.523664             83.074685
+    21  2944.0  80.767437  ...  83.060049             82.509987
+    22  3072.0  81.121923  ...  89.310890             87.381335
+    23  3200.0  84.656085  ...  96.969694             95.380032
+    24  3328.0  83.226931  ...  85.908470             84.101981
+    25  3456.0  81.766291  ...  87.158452             81.026701
+    26  3584.0  87.000867  ...  98.808123             97.153313
+    27  3712.0  82.355598  ...  89.114488             82.593917
+    28  3840.0  84.615146  ...  92.934455             84.552479
+    29  3968.0  91.816356  ...  87.097744             91.540836
+    30  4096.0  86.482237  ...  89.777746             91.491294
 
     [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  5.069 seconds)
+   **Total running time of the script:** ( 6 minutes  4.553 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  0.476 seconds)
+   **Total running time of the script:** ( 0 minutes  0.469 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

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

@@ -38,26 +38,26 @@ Layer Normalization
 
     layer-norm:
               N      Triton       Torch        Apex
-    0    1024.0  585.142849  277.694907  468.114273
+    0    1024.0  585.142849  277.694907  481.882344
     1    1536.0  630.153868  323.368435  511.999982
     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
-    6    4096.0  728.177767  381.023256  458.293714
-    7    4608.0  670.254540  394.267384  426.173427
-    8    5120.0  688.403381  397.669909  424.455959
-    9    5632.0  704.000002  395.228063  413.357796
+    5    3584.0  725.873439  384.859062  455.111115
+    6    4096.0  728.177767  381.023256  455.111095
+    7    4608.0  676.403666  394.267384  428.651163
+    8    5120.0  688.403381  397.669909  422.268057
+    9    5632.0  704.000002  395.228063  417.185184
     10   6144.0  702.171410  402.885254  411.313806
     11   6656.0  705.271522  398.861429  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  630.153861  389.005597  380.502740
-    16   9216.0  606.814809  407.337026  383.002605
-    17   9728.0  589.575753  409.599987  382.427505
+    16   9216.0  609.322328  407.337026  383.999986
+    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  380.601764
+    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  516.031509  413.911572  383.251457
@@ -67,7 +67,7 @@ Layer Normalization
     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  447.098578  406.974373  376.225175
+    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  24.552 seconds)
+   **Total running time of the script:** ( 5 minutes  23.550 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
 =================
-**16:38.329** total execution time for **getting-started_tutorials** files:
+**16:31.316** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:05.069 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:04.553 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:24.552 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:23.550 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:23.445 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:22.074 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:44.788 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:40.669 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.476 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.469 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -331,16 +331,16 @@ 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  702.171410  702.171410
+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
-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  44.788 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  40.669 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   186.181817
+0     256.0  546.133347      512.000001   190.511628
 1     384.0  614.400016      585.142862   153.600004
 2     512.0  655.360017      585.142849   154.566038
-3     640.0  682.666684      640.000002   158.759699
+3     640.0  706.206879      640.000002   158.759699
 4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
-93  12160.0  812.359066      406.179533   198.631953
-94  12288.0  812.429770      415.661740   198.995960
-95  12416.0  810.840807      412.149375   198.556711
-96  12544.0  810.925276      412.971190   198.815254
-97  12672.0  811.007961      412.097543   198.873965
+93  12160.0  812.359066      406.179533   198.530610
+94  12288.0  812.429770      415.661740   198.794749
+95  12416.0  812.498981      411.722274   198.457532
+96  12544.0  810.925276      412.546756   198.716830
+97  12672.0  811.007961      412.097543   198.776477
 
 [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  23.445 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  22.074 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

@@ -565,42 +565,42 @@ 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   2.730667  ...   2.978909              2.978909
-1    384.0   7.372800  ...   7.899428              7.899428
-2    512.0  14.563555  ...  15.420235             15.420235
+0    256.0   2.730667  ...   3.276800              2.978909
+1    384.0   7.372800  ...   7.899428              8.507077
+2    512.0  14.563555  ...  15.420235             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
+4    768.0  32.768000  ...  35.389441             34.028308
+5    896.0  37.971025  ...  40.140799             39.025776
 6   1024.0  49.932191  ...  53.773130             52.428801
 7   1152.0  45.242181  ...  48.161033             47.396572
 8   1280.0  51.200001  ...  57.690139             57.690139
-9   1408.0  64.138541  ...  68.147202             65.684049
-10  1536.0  79.526831  ...  81.355034             78.643199
-11  1664.0  62.929456  ...  63.372618             62.492442
+9   1408.0  64.138541  ...  68.147202             66.485074
+10  1536.0  79.526831  ...  80.430545             78.643199
+11  1664.0  63.372618  ...  63.372618             62.492442
 12  1792.0  72.983276  ...  73.460287             59.467852
-13  1920.0  69.120002  ...  71.257735             71.257735
-14  2048.0  73.584279  ...  78.398206             77.314362
-15  2176.0  83.500614  ...  87.494120             85.998493
-16  2304.0  68.446623  ...  78.064941             77.057651
-17  2432.0  71.305746  ...  86.711310             85.393507
-18  2560.0  77.833728  ...  82.956960             81.512437
-19  2688.0  83.369354  ...  90.316801             89.254248
-20  2816.0  83.873477  ...  84.035084             82.916747
-21  2944.0  82.646820  ...  82.237674             81.034195
-22  3072.0  82.301023  ...  89.735509             86.579673
-23  3200.0  84.880639  ...  96.096095             94.674553
-24  3328.0  83.905938  ...  85.602017             84.995628
-25  3456.0  82.015834  ...  91.928814             88.595129
-26  3584.0  86.540320  ...  96.579370             87.042978
-27  3712.0  85.675250  ...  89.835744             87.552452
-28  3840.0  83.528704  ...  87.841141             89.548180
-29  3968.0  86.053553  ...  92.442373             87.035620
-30  4096.0  93.792965  ...  85.055593             85.271746
+13  1920.0  69.467336  ...  71.257735             70.892307
+14  2048.0  73.262953  ...  78.398206             77.314362
+15  2176.0  83.500614  ...  87.494120             86.367588
+16  2304.0  68.446623  ...  78.064941             77.307030
+17  2432.0  71.305746  ...  86.711310             75.118889
+18  2560.0  77.833728  ...  82.125311             81.512437
+19  2688.0  83.737433  ...  91.185232             89.254248
+20  2816.0  80.617762  ...  84.523664             83.074685
+21  2944.0  80.767437  ...  83.060049             82.509987
+22  3072.0  81.121923  ...  89.310890             87.381335
+23  3200.0  84.656085  ...  96.969694             95.380032
+24  3328.0  83.226931  ...  85.908470             84.101981
+25  3456.0  81.766291  ...  87.158452             81.026701
+26  3584.0  87.000867  ...  98.808123             97.153313
+27  3712.0  82.355598  ...  89.114488             82.593917
+28  3840.0  84.615146  ...  92.934455             84.552479
+29  3968.0  91.816356  ...  87.097744             91.540836
+30  4096.0  86.482237  ...  89.777746             91.491294
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  5.069 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  4.553 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  0.476 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.469 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

@@ -194,26 +194,26 @@ 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:
           N      Triton       Torch        Apex
-0    1024.0  585.142849  277.694907  468.114273
+0    1024.0  585.142849  277.694907  481.882344
 1    1536.0  630.153868  323.368435  511.999982
 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
-6    4096.0  728.177767  381.023256  458.293714
-7    4608.0  670.254540  394.267384  426.173427
-8    5120.0  688.403381  397.669909  424.455959
-9    5632.0  704.000002  395.228063  413.357796
+5    3584.0  725.873439  384.859062  455.111115
+6    4096.0  728.177767  381.023256  455.111095
+7    4608.0  676.403666  394.267384  428.651163
+8    5120.0  688.403381  397.669909  422.268057
+9    5632.0  704.000002  395.228063  417.185184
 10   6144.0  702.171410  402.885254  411.313806
 11   6656.0  705.271522  398.861429  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  630.153861  389.005597  380.502740
-16   9216.0  606.814809  407.337026  383.002605
-17   9728.0  589.575753  409.599987  382.427505
+16   9216.0  609.322328  407.337026  383.999986
+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  380.601764
+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  516.031509  413.911572  383.251457
@@ -223,7 +223,7 @@ to download the full example code</p>
 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  447.098578  406.974373  376.225175
+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  24.552 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  23.550 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>16:38.329</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>16:31.316</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>06:05.069</p></td>
+<td><p>06:04.553</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>05:24.552</p></td>
+<td><p>05:23.550</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>03:23.445</p></td>
+<td><p>03:22.074</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>01:44.788</p></td>
+<td><p>01:40.669</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>00:00.476</p></td>
+<td><p>00:00.469</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: 92c59131bdc1644d4af6bcba6e247150
+config: e822ff792fcc42efa5c048599d2f55c7
 tags: 645f666f9bcd5a90fca523b33c5a78b7