[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: 849b30de61a05b5445df85d6d9ce633d
+config: cf684901b57e59ede0e9a6458a97c96b
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -235,17 +235,17 @@ 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   76.800002   76.800002
     4       65536.0  127.999995  127.999995
     5      131072.0  219.428568  219.428568
     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  702.171410
+    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  44.397 seconds)
+   **Total running time of the script:** ( 1 minutes  41.559 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   186.181817
     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   158.759699
+    3     640.0  706.206879      640.000002   160.000000
     4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
-    93  12160.0  812.359066      406.179533   198.631953
-    94  12288.0  812.429770      416.101597   198.895304
-    95  12416.0  812.498981      412.149375   198.556711
-    96  12544.0  812.566838      412.971190   198.864492
-    97  12672.0  811.007961      412.097543   198.873965
+    93  12160.0  812.359066      406.179533   198.429370
+    94  12288.0  812.429770      415.661740   198.794749
+    95  12416.0  812.498981      412.149375   198.457532
+    96  12544.0  812.566838      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  22.202 seconds)
+   **Total running time of the script:** ( 3 minutes  21.850 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  ...   8.507077              8.507077
-    2    512.0  14.563555  ...  16.384000             15.420235
+    0    256.0   2.730667  ...   3.276800              3.276800
+    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  ...  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             66.485074
-    10  1536.0  79.526831  ...  80.430545             78.643199
-    11  1664.0  62.929456  ...  63.372618             62.492442
+    10  1536.0  80.430545  ...  81.355034             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             70.892307
+    13  1920.0  69.467336  ...  71.257735             70.892307
     14  2048.0  73.262953  ...  78.033565             76.959706
-    15  2176.0  83.155572  ...  87.876193             85.998493
+    15  2176.0  83.155572  ...  87.494120             85.998493
     16  2304.0  68.446623  ...  78.064941             77.057651
-    17  2432.0  71.305746  ...  86.711310             84.621881
-    18  2560.0  77.833728  ...  82.331658             81.715711
-    19  2688.0  83.369354  ...  90.966561             89.044730
-    20  2816.0  82.602666  ...  84.197315             83.552120
-    21  2944.0  81.698415  ...  83.477440             82.509987
-    22  3072.0  82.420822  ...  86.053349             88.612060
-    23  3200.0  84.712112  ...  89.387425             95.096582
-    24  3328.0  83.808259  ...  85.703924             84.397770
-    25  3456.0  82.519518  ...  91.928814             89.579522
-    26  3584.0  85.552231  ...  95.756542             95.654673
-    27  3712.0  86.044224  ...  89.353616             83.386762
-    28  3840.0  85.201850  ...  93.012618             85.597527
-    29  3968.0  91.747320  ...  85.330496             89.789505
-    30  4096.0  91.522488  ...  90.687655             90.382307
+    17  2432.0  71.125224  ...  86.444504             84.877538
+    18  2560.0  77.833728  ...  82.956960             81.108913
+    19  2688.0  83.552988  ...  90.966561             89.044730
+    20  2816.0  82.995641  ...  84.197315             83.712490
+    21  2944.0  82.646820  ...  83.758038             82.237674
+    22  3072.0  82.661468  ...  87.787755             88.612060
+    23  3200.0  81.424937  ...  93.704243             93.430660
+    24  3328.0  81.622783  ...  85.703924             84.795401
+    25  3456.0  82.604067  ...  92.033756             90.281712
+    26  3584.0  85.674507  ...  93.273228             95.960933
+    27  3712.0  85.748791  ...  86.118401             87.706180
+    28  3840.0  81.019778  ...  88.900318             89.475729
+    29  3968.0  88.008611  ...  87.315873             88.040360
+    30  4096.0  93.924229  ...  93.727466             87.552332
 
     [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  6.898 seconds)
+   **Total running time of the script:** ( 5 minutes  59.034 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  0.475 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

@@ -41,33 +41,33 @@ Layer Normalization
     0    1024.0  585.142849  277.694907  468.114273
     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  455.111115
-    6    4096.0  728.177767  381.023256  455.111095
-    7    4608.0  676.403666  396.387087  428.651163
-    8    5120.0  688.403381  397.669909  422.268057
-    9    5632.0  704.000002  395.228063  415.262685
+    3    2560.0  694.237267  362.477870  518.481028
+    4    3072.0  712.347810  378.092307  496.484863
+    5    3584.0  725.873439  384.859062  458.751978
+    6    4096.0  728.177767  381.023256  451.972420
+    7    4608.0  670.254540  396.387087  426.173427
+    8    5120.0  694.237267  397.669909  426.666652
+    9    5632.0  704.000002  395.228063  413.357796
     10   6144.0  702.171410  402.885254  411.313806
-    11   6656.0  705.271522  400.360920  400.360920
+    11   6656.0  700.631610  400.360920  398.861429
     12   7168.0  690.891575  396.844306  387.459443
     13   7680.0  682.666656  392.587863  387.634072
     14   8192.0  639.375598  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  587.350922  409.599987  383.369452
+    15   8704.0  630.153861  389.005597  380.502740
+    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  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
+    22  12288.0  516.031509  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  447.098578  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  23.955 seconds)
+   **Total running time of the script:** ( 5 minutes  20.722 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
 =================
-**16:37.927** total execution time for **getting-started_tutorials** files:
+**16:23.634** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:06.898 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:59.034 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:23.955 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:20.722 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:22.202 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:21.850 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:44.397 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:41.559 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.475 | 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

@@ -325,22 +325,22 @@ 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   76.800002   76.800002
 4       65536.0  127.999995  127.999995
 5      131072.0  219.428568  219.428568
 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  702.171410
+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  44.397 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  41.559 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   186.181817
 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   158.759699
+3     640.0  706.206879      640.000002   160.000000
 4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
-93  12160.0  812.359066      406.179533   198.631953
-94  12288.0  812.429770      416.101597   198.895304
-95  12416.0  812.498981      412.149375   198.556711
-96  12544.0  812.566838      412.971190   198.864492
-97  12672.0  811.007961      412.097543   198.873965
+93  12160.0  812.359066      406.179533   198.429370
+94  12288.0  812.429770      415.661740   198.794749
+95  12416.0  812.498981      412.149375   198.457532
+96  12544.0  812.566838      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  22.202 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  21.850 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  ...   8.507077              8.507077
-2    512.0  14.563555  ...  16.384000             15.420235
+0    256.0   2.730667  ...   3.276800              3.276800
+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  ...  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             66.485074
-10  1536.0  79.526831  ...  80.430545             78.643199
-11  1664.0  62.929456  ...  63.372618             62.492442
+10  1536.0  80.430545  ...  81.355034             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             70.892307
+13  1920.0  69.467336  ...  71.257735             70.892307
 14  2048.0  73.262953  ...  78.033565             76.959706
-15  2176.0  83.155572  ...  87.876193             85.998493
+15  2176.0  83.155572  ...  87.494120             85.998493
 16  2304.0  68.446623  ...  78.064941             77.057651
-17  2432.0  71.305746  ...  86.711310             84.621881
-18  2560.0  77.833728  ...  82.331658             81.715711
-19  2688.0  83.369354  ...  90.966561             89.044730
-20  2816.0  82.602666  ...  84.197315             83.552120
-21  2944.0  81.698415  ...  83.477440             82.509987
-22  3072.0  82.420822  ...  86.053349             88.612060
-23  3200.0  84.712112  ...  89.387425             95.096582
-24  3328.0  83.808259  ...  85.703924             84.397770
-25  3456.0  82.519518  ...  91.928814             89.579522
-26  3584.0  85.552231  ...  95.756542             95.654673
-27  3712.0  86.044224  ...  89.353616             83.386762
-28  3840.0  85.201850  ...  93.012618             85.597527
-29  3968.0  91.747320  ...  85.330496             89.789505
-30  4096.0  91.522488  ...  90.687655             90.382307
+17  2432.0  71.125224  ...  86.444504             84.877538
+18  2560.0  77.833728  ...  82.956960             81.108913
+19  2688.0  83.552988  ...  90.966561             89.044730
+20  2816.0  82.995641  ...  84.197315             83.712490
+21  2944.0  82.646820  ...  83.758038             82.237674
+22  3072.0  82.661468  ...  87.787755             88.612060
+23  3200.0  81.424937  ...  93.704243             93.430660
+24  3328.0  81.622783  ...  85.703924             84.795401
+25  3456.0  82.604067  ...  92.033756             90.281712
+26  3584.0  85.674507  ...  93.273228             95.960933
+27  3712.0  85.748791  ...  86.118401             87.706180
+28  3840.0  81.019778  ...  88.900318             89.475729
+29  3968.0  88.008611  ...  87.315873             88.040360
+30  4096.0  93.924229  ...  93.727466             87.552332
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  6.898 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  59.034 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  0.475 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

@@ -197,33 +197,33 @@ to download the full example code</p>
 0    1024.0  585.142849  277.694907  468.114273
 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  455.111115
-6    4096.0  728.177767  381.023256  455.111095
-7    4608.0  676.403666  396.387087  428.651163
-8    5120.0  688.403381  397.669909  422.268057
-9    5632.0  704.000002  395.228063  415.262685
+3    2560.0  694.237267  362.477870  518.481028
+4    3072.0  712.347810  378.092307  496.484863
+5    3584.0  725.873439  384.859062  458.751978
+6    4096.0  728.177767  381.023256  451.972420
+7    4608.0  670.254540  396.387087  426.173427
+8    5120.0  694.237267  397.669909  426.666652
+9    5632.0  704.000002  395.228063  413.357796
 10   6144.0  702.171410  402.885254  411.313806
-11   6656.0  705.271522  400.360920  400.360920
+11   6656.0  700.631610  400.360920  398.861429
 12   7168.0  690.891575  396.844306  387.459443
 13   7680.0  682.666656  392.587863  387.634072
 14   8192.0  639.375598  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  587.350922  409.599987  383.369452
+15   8704.0  630.153861  389.005597  380.502740
+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  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
+22  12288.0  516.031509  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  447.098578  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  23.955 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  20.722 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>16:37.927</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>16:23.634</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>06:06.898</p></td>
+<td><p>05:59.034</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>05:23.955</p></td>
+<td><p>05:20.722</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>03:22.202</p></td>
+<td><p>03:21.850</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>01:44.397</p></td>
+<td><p>01:41.559</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>00:00.475</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: e1b0add0ce377ae76c0d9c72af9c5768
+config: 8705e0b6ca05bb201c2a730123908cbb
 tags: 645f666f9bcd5a90fca523b33c5a78b7