[GH-PAGES] Updated website

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: 28cad3eff84505032c4f1aeab6ffde38
+config: e6dd4093d222d862b66c8001bd347f4e
 tags: 645f666f9bcd5a90fca523b33c5a78b7

v1.1.2/_sources/getting-started/tutorials/01-vector-add.rst.txt

@@ -231,7 +231,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
 
     vector-add-performance:
                size      Triton       Torch
-    0        4096.0    8.000000    9.600000
+    0        4096.0    9.600000    9.600000
     1        8192.0   19.200000   19.200000
     2       16384.0   38.400001   38.400001
     3       32768.0   76.800002   76.800002
@@ -254,7 +254,7 @@ 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  52.927 seconds)
+   **Total running time of the script:** ( 1 minutes  42.276 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

v1.1.2/_sources/getting-started/tutorials/02-fused-softmax.rst.txt

@@ -287,14 +287,14 @@ 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
-    1     384.0  585.142862      585.142862   151.703707
+    1     384.0  585.142862      558.545450   151.703707
     2     512.0  655.360017      585.142849   154.566038
     3     640.0  682.666684      640.000002   160.000000
-    4     768.0  722.823517      664.216187   162.754967
+    4     768.0  702.171410      664.216187   162.754967
     ..      ...         ...             ...          ...
     93  12160.0  812.359066      406.179533   198.530610
-    94  12288.0  814.111783      415.661740   198.895304
-    95  12416.0  814.163950      412.149375   198.358474
+    94  12288.0  814.111783      415.661740   198.794749
+    95  12416.0  812.498981      412.149375   198.457532
     96  12544.0  812.566838      412.971190   198.716830
     97  12672.0  812.633240      412.097543   198.776477
 
@@ -314,7 +314,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  27.294 seconds)
+   **Total running time of the script:** ( 3 minutes  21.471 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

v1.1.2/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt

@@ -464,35 +464,35 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
              M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
     0    256.0   2.730667  ...   2.978909              2.978909
     1    384.0   7.372800  ...   8.507077              7.899428
-    2    512.0  14.563555  ...  16.384000             16.384000
+    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
-    6   1024.0  51.150050  ...  53.773130             52.428801
+    5    896.0  37.971025  ...  39.025776             37.971025
+    6   1024.0  49.932191  ...  53.773130             52.428801
     7   1152.0  45.242181  ...  46.656000             46.656000
-    8   1280.0  51.200001  ...  56.888887             56.888887
+    8   1280.0  51.200001  ...  56.888887             56.109587
     9   1408.0  64.138541  ...  67.305878             66.485074
     10  1536.0  80.430545  ...  79.526831             78.643199
-    11  1664.0  62.929456  ...  62.492442             62.061463
-    12  1792.0  72.983276  ...  59.154861             71.588687
-    13  1920.0  69.120002  ...  70.172588             70.172588
-    14  2048.0  73.908442  ...  76.959706             76.608294
+    11  1664.0  63.372618  ...  62.492442             62.061463
+    12  1792.0  72.983276  ...  72.047592             71.588687
+    13  1920.0  69.120002  ...  69.818184             70.172588
+    14  2048.0  73.584279  ...  76.959706             76.608294
     15  2176.0  83.155572  ...  85.998493             85.269692
-    16  2304.0  68.251065  ...  77.057651             76.809875
-    17  2432.0  71.305746  ...  74.918570             84.877538
+    16  2304.0  68.446623  ...  76.809875             76.563695
+    17  2432.0  71.125224  ...  83.490234             84.877538
     18  2560.0  77.833728  ...  81.310171             80.908642
-    19  2688.0  83.922689  ...  90.102270             89.464755
-    20  2816.0  83.074685  ...  83.074685             82.916747
-    21  2944.0  82.646820  ...  81.564701             82.921853
-    22  3072.0  81.589488  ...  88.473602             87.516392
-    23  3200.0  80.706181  ...  93.704243             95.665176
-    24  3328.0  82.796202  ...  83.857070             84.895397
-    25  3456.0  81.766291  ...  91.304157             91.719645
-    26  3584.0  87.551500  ...  96.891584             98.160909
-    27  3712.0  85.601834  ...  91.397382             87.399253
-    28  3840.0  84.874902  ...  90.798032             87.910967
-    29  3968.0  91.954739  ...  90.859224             85.871877
-    30  4096.0  93.401342  ...  92.372834             90.200084
+    19  2688.0  84.108772  ...  90.102270             89.676257
+    20  2816.0  82.916747  ...  83.074685             82.916747
+    21  2944.0  82.646820  ...  83.198715             82.102191
+    22  3072.0  82.420822  ...  86.978653             89.030036
+    23  3200.0  81.012662  ...  92.888243             94.674553
+    24  3328.0  83.371507  ...  84.995628             84.695641
+    25  3456.0  82.773682  ...  91.304157             90.484366
+    26  3584.0  86.623693  ...  95.249353             95.350361
+    27  3712.0  83.317214  ...  88.797643             84.802499
+    28  3840.0  84.356981  ...  91.739529             86.670843
+    29  3968.0  93.361844  ...  86.911637             91.301109
+    30  4096.0  88.592559  ...  84.840533             90.443212
 
     [31 rows x 5 columns]
 
@@ -502,7 +502,7 @@ 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  12.411 seconds)
+   **Total running time of the script:** ( 6 minutes  7.444 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

v1.1.2/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt

@@ -238,7 +238,7 @@ References
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  0.216 seconds)
+   **Total running time of the script:** ( 0 minutes  0.116 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

v1.1.2/_sources/getting-started/tutorials/05-layer-norm.rst.txt

@@ -38,36 +38,36 @@ Layer Normalization
 
     layer-norm-backward:
               N      Triton       Torch        Apex
-    0    1024.0  311.088617   99.497980  311.088617
-    1    1536.0  351.085717  134.050910  341.333333
-    2    2048.0  423.724127  159.067963  332.108094
-    3    2560.0  465.454542  181.775141  330.322572
-    4    3072.0  511.999982  191.501303  313.736171
-    5    3584.0  551.384634  207.267476  310.527060
-    6    4096.0  568.231237  218.939860  298.796351
-    7    4608.0  498.162157  233.316456  289.507855
-    8    5120.0  527.381977  240.469672  285.104413
-    9    5632.0  542.843364  244.426754  290.683877
-    10   6144.0  544.118087  250.349744  287.438593
-    11   6656.0  532.479975  255.590406  286.279570
-    12   7168.0  513.528374  257.147993  282.019678
-    13   7680.0  486.332448  263.690977  282.699379
-    14   8192.0  464.794337  262.143998  282.077471
-    15   8704.0  416.127506  266.789264  285.377055
-    16   9216.0  430.319054  272.394084  289.129410
+    0    1024.0  311.088617   98.303995  303.407414
+    1    1536.0  351.085717  133.083026  341.333333
+    2    2048.0  420.102553  161.684218  334.367350
+    3    2560.0  461.954908  182.314537  326.808501
+    4    3072.0  511.999982  191.501303  317.793096
+    5    3584.0  551.384634  207.768111  309.410081
+    6    4096.0  568.231237  219.919464  296.096389
+    7    4608.0  498.162157  232.336141  286.507772
+    8    5120.0  525.128191  242.366855  284.444444
+    9    5632.0  538.517949  243.107920  290.060087
+    10   6144.0  542.117638  248.242431  286.322318
+    11   6656.0  527.207907  256.000009  285.767438
+    12   7168.0  507.469040  261.446807  287.678923
+    13   7680.0  482.513091  261.076480  278.429013
+    14   8192.0  461.521112  268.223740  287.438585
+    15   8704.0  417.791980  267.130429  284.987724
+    16   9216.0  430.319054  272.059034  288.751954
     17   9728.0  438.857162  280.278512  289.308559
-    18  10240.0  447.650282  286.767793  288.112552
-    19  10752.0  430.079980  246.935876  290.267711
-    20  11264.0  427.746848  245.983625  288.204696
-    21  11776.0  421.826879  249.227509  288.686414
-    22  12288.0  421.302872  254.673582  295.207195
-    23  12800.0  415.135142  253.465340  290.359162
-    24  13312.0  411.181478  252.959629  290.443638
-    25  13824.0  405.594132  257.190689  292.056329
-    26  14336.0  394.568805  254.485198  288.402346
-    27  14848.0  384.829370  256.922861  289.246765
-    28  15360.0  374.253788  257.970599  287.550706
-    29  15872.0  366.982663  262.347108  291.006885
+    18  10240.0  445.217381  286.433562  290.496460
+    19  10752.0  427.940303  246.464170  290.267711
+    20  11264.0  428.424741  245.091565  286.676558
+    21  11776.0  421.826879  249.447482  288.391833
+    22  12288.0  419.504980  254.453844  294.617366
+    23  12800.0  414.016170  253.674644  289.538159
+    24  13312.0  412.242569  252.360194  289.653667
+    25  13824.0  405.594132  256.991469  291.543045
+    26  14336.0  397.761846  254.297107  286.481278
+    27  14848.0  386.498925  257.479779  289.717061
+    28  15360.0  376.932517  257.970599  288.000007
+    29  15872.0  366.629453  262.708969  291.229369
 
 
 
@@ -329,7 +329,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  14.015 seconds)
+   **Total running time of the script:** ( 2 minutes  12.961 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

v1.1.2/_sources/getting-started/tutorials/sg_execution_times.rst.txt

@@ -5,16 +5,16 @@
 
 Computation times
 =================
-**13:46.864** total execution time for **getting-started_tutorials** files:
+**13:24.269** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:12.411 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:07.444 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:27.294 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:21.471 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:14.015 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:12.961 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:52.927 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:42.276 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.216 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.116 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

v1.1.2/getting-started/tutorials/01-vector-add.html

@@ -321,7 +321,7 @@ for different problem sizes.</p>
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector-add-performance:
            size      Triton       Torch
-0        4096.0    8.000000    9.600000
+0        4096.0    9.600000    9.600000
 1        8192.0   19.200000   19.200000
 2       16384.0   38.400001   38.400001
 3       32768.0   76.800002   76.800002
@@ -339,7 +339,7 @@ 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  52.927 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  42.276 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>

v1.1.2/getting-started/tutorials/02-fused-softmax.html

@@ -375,14 +375,14 @@ We will then compare its performance against (1) <code class="code docutils lite
 <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
-1     384.0  585.142862      585.142862   151.703707
+1     384.0  585.142862      558.545450   151.703707
 2     512.0  655.360017      585.142849   154.566038
 3     640.0  682.666684      640.000002   160.000000
-4     768.0  722.823517      664.216187   162.754967
+4     768.0  702.171410      664.216187   162.754967
 ..      ...         ...             ...          ...
 93  12160.0  812.359066      406.179533   198.530610
-94  12288.0  814.111783      415.661740   198.895304
-95  12416.0  814.163950      412.149375   198.358474
+94  12288.0  814.111783      415.661740   198.794749
+95  12416.0  812.498981      412.149375   198.457532
 96  12544.0  812.566838      412.971190   198.716830
 97  12672.0  812.633240      412.097543   198.776477
 
@@ -397,7 +397,7 @@ 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  27.294 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  21.471 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>

v1.1.2/getting-started/tutorials/03-matrix-multiplication.html

@@ -570,40 +570,40 @@ torch_output=tensor([[  1.1045, -36.9688,  31.4688,  ..., -11.3906,  24.4531, -3
          M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
 0    256.0   2.730667  ...   2.978909              2.978909
 1    384.0   7.372800  ...   8.507077              7.899428
-2    512.0  14.563555  ...  16.384000             16.384000
+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
-6   1024.0  51.150050  ...  53.773130             52.428801
+5    896.0  37.971025  ...  39.025776             37.971025
+6   1024.0  49.932191  ...  53.773130             52.428801
 7   1152.0  45.242181  ...  46.656000             46.656000
-8   1280.0  51.200001  ...  56.888887             56.888887
+8   1280.0  51.200001  ...  56.888887             56.109587
 9   1408.0  64.138541  ...  67.305878             66.485074
 10  1536.0  80.430545  ...  79.526831             78.643199
-11  1664.0  62.929456  ...  62.492442             62.061463
-12  1792.0  72.983276  ...  59.154861             71.588687
-13  1920.0  69.120002  ...  70.172588             70.172588
-14  2048.0  73.908442  ...  76.959706             76.608294
+11  1664.0  63.372618  ...  62.492442             62.061463
+12  1792.0  72.983276  ...  72.047592             71.588687
+13  1920.0  69.120002  ...  69.818184             70.172588
+14  2048.0  73.584279  ...  76.959706             76.608294
 15  2176.0  83.155572  ...  85.998493             85.269692
-16  2304.0  68.251065  ...  77.057651             76.809875
-17  2432.0  71.305746  ...  74.918570             84.877538
+16  2304.0  68.446623  ...  76.809875             76.563695
+17  2432.0  71.125224  ...  83.490234             84.877538
 18  2560.0  77.833728  ...  81.310171             80.908642
-19  2688.0  83.922689  ...  90.102270             89.464755
-20  2816.0  83.074685  ...  83.074685             82.916747
-21  2944.0  82.646820  ...  81.564701             82.921853
-22  3072.0  81.589488  ...  88.473602             87.516392
-23  3200.0  80.706181  ...  93.704243             95.665176
-24  3328.0  82.796202  ...  83.857070             84.895397
-25  3456.0  81.766291  ...  91.304157             91.719645
-26  3584.0  87.551500  ...  96.891584             98.160909
-27  3712.0  85.601834  ...  91.397382             87.399253
-28  3840.0  84.874902  ...  90.798032             87.910967
-29  3968.0  91.954739  ...  90.859224             85.871877
-30  4096.0  93.401342  ...  92.372834             90.200084
+19  2688.0  84.108772  ...  90.102270             89.676257
+20  2816.0  82.916747  ...  83.074685             82.916747
+21  2944.0  82.646820  ...  83.198715             82.102191
+22  3072.0  82.420822  ...  86.978653             89.030036
+23  3200.0  81.012662  ...  92.888243             94.674553
+24  3328.0  83.371507  ...  84.995628             84.695641
+25  3456.0  82.773682  ...  91.304157             90.484366
+26  3584.0  86.623693  ...  95.249353             95.350361
+27  3712.0  83.317214  ...  88.797643             84.802499
+28  3840.0  84.356981  ...  91.739529             86.670843
+29  3968.0  93.361844  ...  86.911637             91.301109
+30  4096.0  88.592559  ...  84.840533             90.443212
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  12.411 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  7.444 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>

v1.1.2/getting-started/tutorials/04-low-memory-dropout.html

@@ -371,7 +371,7 @@ 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  0.216 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.116 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>

v1.1.2/getting-started/tutorials/05-layer-norm.html

@@ -194,36 +194,36 @@ to download the full example code</p>
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>layer-norm-backward:
           N      Triton       Torch        Apex
-0    1024.0  311.088617   99.497980  311.088617
-1    1536.0  351.085717  134.050910  341.333333
-2    2048.0  423.724127  159.067963  332.108094
-3    2560.0  465.454542  181.775141  330.322572
-4    3072.0  511.999982  191.501303  313.736171
-5    3584.0  551.384634  207.267476  310.527060
-6    4096.0  568.231237  218.939860  298.796351
-7    4608.0  498.162157  233.316456  289.507855
-8    5120.0  527.381977  240.469672  285.104413
-9    5632.0  542.843364  244.426754  290.683877
-10   6144.0  544.118087  250.349744  287.438593
-11   6656.0  532.479975  255.590406  286.279570
-12   7168.0  513.528374  257.147993  282.019678
-13   7680.0  486.332448  263.690977  282.699379
-14   8192.0  464.794337  262.143998  282.077471
-15   8704.0  416.127506  266.789264  285.377055
-16   9216.0  430.319054  272.394084  289.129410
+0    1024.0  311.088617   98.303995  303.407414
+1    1536.0  351.085717  133.083026  341.333333
+2    2048.0  420.102553  161.684218  334.367350
+3    2560.0  461.954908  182.314537  326.808501
+4    3072.0  511.999982  191.501303  317.793096
+5    3584.0  551.384634  207.768111  309.410081
+6    4096.0  568.231237  219.919464  296.096389
+7    4608.0  498.162157  232.336141  286.507772
+8    5120.0  525.128191  242.366855  284.444444
+9    5632.0  538.517949  243.107920  290.060087
+10   6144.0  542.117638  248.242431  286.322318
+11   6656.0  527.207907  256.000009  285.767438
+12   7168.0  507.469040  261.446807  287.678923
+13   7680.0  482.513091  261.076480  278.429013
+14   8192.0  461.521112  268.223740  287.438585
+15   8704.0  417.791980  267.130429  284.987724
+16   9216.0  430.319054  272.059034  288.751954
 17   9728.0  438.857162  280.278512  289.308559
-18  10240.0  447.650282  286.767793  288.112552
-19  10752.0  430.079980  246.935876  290.267711
-20  11264.0  427.746848  245.983625  288.204696
-21  11776.0  421.826879  249.227509  288.686414
-22  12288.0  421.302872  254.673582  295.207195
-23  12800.0  415.135142  253.465340  290.359162
-24  13312.0  411.181478  252.959629  290.443638
-25  13824.0  405.594132  257.190689  292.056329
-26  14336.0  394.568805  254.485198  288.402346
-27  14848.0  384.829370  256.922861  289.246765
-28  15360.0  374.253788  257.970599  287.550706
-29  15872.0  366.982663  262.347108  291.006885
+18  10240.0  445.217381  286.433562  290.496460
+19  10752.0  427.940303  246.464170  290.267711
+20  11264.0  428.424741  245.091565  286.676558
+21  11776.0  421.826879  249.447482  288.391833
+22  12288.0  419.504980  254.453844  294.617366
+23  12800.0  414.016170  253.674644  289.538159
+24  13312.0  412.242569  252.360194  289.653667
+25  13824.0  405.594132  256.991469  291.543045
+26  14336.0  397.761846  254.297107  286.481278
+27  14848.0  386.498925  257.479779  289.717061
+28  15360.0  376.932517  257.970599  288.000007
+29  15872.0  366.629453  262.708969  291.229369
 </pre></div>
 </div>
 <div class="line-block">
@@ -477,7 +477,7 @@ 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  14.015 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  12.961 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>

v1.1.2/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>13:46.864</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:24.269</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>06:12.411</p></td>
+<td><p>06:07.444</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>03:27.294</p></td>
+<td><p>03:21.471</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>02:14.015</p></td>
+<td><p>02:12.961</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>01:52.927</p></td>
+<td><p>01:42.276</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>00:00.216</p></td>
+<td><p>00:00.116</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>