[GH-PAGES] Updated website

docs

@@ -0,0 +1 @@
+master

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: 0b3571d18ebacb7d725e34a920cd2c6d
+config: efe76ce9e535cabfcb79f7c25516b7d2
 tags: 645f666f9bcd5a90fca523b33c5a78b7

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

@@ -244,7 +244,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
     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
 
@@ -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  46.338 seconds)
+   **Total running time of the script:** ( 1 minutes  48.510 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

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

@@ -286,17 +286,17 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
 
     softmax-performance:
               N      Triton  Torch (native)  Torch (jit)
-    0     256.0  512.000001      546.133347   190.511628
+    0     256.0  512.000001      546.133347   188.321838
-    1     384.0  585.142862      585.142862   153.600004
+    1     384.0  614.400016      585.142862   153.600004
     2     512.0  655.360017      606.814814   154.566038
     3     640.0  682.666684      640.000002   160.000000
     4     768.0  722.823517      664.216187   162.754967
     ..      ...         ...             ...          ...
-    93  12160.0  814.058574      406.179533   198.936606
+    93  12160.0  814.058574      406.179533   198.834951
-    94  12288.0  814.111783      415.661740   199.197579
+    94  12288.0  814.111783      415.661740   198.995960
-    95  12416.0  812.498981      412.149375   198.755369
+    95  12416.0  812.498981      412.149375   198.556711
-    96  12544.0  812.566838      412.971190   199.012395
+    96  12544.0  812.566838      412.971190   198.913776
-    97  12672.0  812.633240      412.097543   199.069228
+    97  12672.0  812.633240      412.097543   198.971549
 
     [98 rows x 4 columns]
 
@@ -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  24.992 seconds)
+   **Total running time of the script:** ( 3 minutes  23.901 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -462,37 +462,37 @@ 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  ...   3.276800              2.978909
+    0    256.0   2.978909  ...   3.276800              2.978909
     1    384.0   7.372800  ...   8.507077              8.507077
     2    512.0  14.563555  ...  16.384000             16.384000
     3    640.0  22.260869  ...  24.380953             24.380953
     4    768.0  32.768000  ...  34.028308             34.028308
     5    896.0  39.025776  ...  40.140799             39.025776
-    6   1024.0  51.150050  ...  52.428801             52.428801
+    6   1024.0  51.150050  ...  53.773130             52.428801
     7   1152.0  45.242181  ...  46.656000             46.656000
     8   1280.0  51.200001  ...  56.888887             56.888887
-    9   1408.0  64.138541  ...  67.305878             67.305878
+    9   1408.0  64.138541  ...  67.305878             66.485074
-    10  1536.0  79.526831  ...  79.526831             79.526831
+    10  1536.0  80.430545  ...  79.526831             78.643199
     11  1664.0  62.929456  ...  62.492442             62.061463
-    12  1792.0  72.983276  ...  72.512412             72.047592
+    12  1792.0  72.512412  ...  72.512412             71.588687
-    13  1920.0  68.776119  ...  70.172588             70.172588
+    13  1920.0  69.120002  ...  70.172588             70.172588
     14  2048.0  73.584279  ...  76.959706             76.959706
-    15  2176.0  83.500614  ...  86.367588             85.632545
+    15  2176.0  83.155572  ...  86.367588             85.632545
-    16  2304.0  68.643310  ...  76.319081             76.319081
+    16  2304.0  68.446623  ...  77.057651             76.563695
-    17  2432.0  71.125224  ...  82.147552             84.367759
+    17  2432.0  71.487187  ...  85.653855             84.877538
-    18  2560.0  77.283019  ...  80.908642             80.511054
+    18  2560.0  78.019048  ...  80.709358             80.313727
-    19  2688.0  83.369354  ...  89.676257             89.464755
+    19  2688.0  83.369354  ...  88.836198             89.676257
-    20  2816.0  83.552120  ...  82.916747             83.233226
+    20  2816.0  82.916747  ...  83.392363             82.135981
-    21  2944.0  82.373605  ...  80.771529             82.921853
+    21  2944.0  80.380696  ...  79.865439             82.373605
-    22  3072.0  81.589488  ...  88.612060             88.612060
+    22  3072.0  82.181572  ...  88.335577             88.473602
-    23  3200.0  82.368085  ...  94.674553             94.117647
+    23  3200.0  84.768213  ...  95.096582             94.814812
-    24  3328.0  82.369902  ...  83.275067             80.347427
+    24  3328.0  83.034941  ...  84.298943             83.516586
-    25  3456.0  81.849303  ...  84.775569             90.382926
+    25  3456.0  81.108217  ...  87.727494             90.382926
-    26  3584.0  87.381330  ...  98.375705             98.160909
+    26  3584.0  87.381330  ...  98.375705             98.268190
-    27  3712.0  83.386762  ...  88.718781             83.074717
+    27  3712.0  80.757757  ...  88.483034             85.091436
-    28  3840.0  84.356981  ...  92.390975             84.940091
+    28  3840.0  82.778440  ...  89.693434             84.550462
-    29  3968.0  91.885495  ...  84.096442             88.615785
+    29  3968.0  87.535103  ...  84.385406             86.419216
-    30  4096.0  86.480498  ...  92.755862             85.271746
+    30  4096.0  89.478485  ...  92.245860             85.161847
 
     [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:** ( 5 minutes  35.980 seconds)
+   **Total running time of the script:** ( 6 minutes  1.565 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  0.010 seconds)
+   **Total running time of the script:** ( 0 minutes  0.108 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   98.303995  303.407414
+    0    1024.0  307.200008   98.303995  303.407414
-    1    1536.0  351.085717  134.050910  341.333333
+    1    1536.0  351.085717  134.540150  341.333333
-    2    2048.0  423.724127  161.684218  334.367350
+    2    2048.0  420.102553  161.684218  325.509933
-    3    2560.0  465.454542  181.238943  330.322572
+    3    2560.0  465.454542  181.238943  326.808501
-    4    3072.0  511.999982  191.999993  320.556515
+    4    3072.0  511.999982  192.501302  316.429186
-    5    3584.0  551.384634  208.271186  310.527060
+    5    3584.0  551.384634  208.271186  309.410081
-    6    4096.0  568.231237  219.919464  298.796351
+    6    4096.0  568.231237  220.412561  298.796351
-    7    4608.0  500.416301  232.825259  286.507772
+    7    4608.0  500.416301  232.825259  289.507855
-    8    5120.0  525.128191  242.845844  284.444444
+    8    5120.0  525.128191  242.366855  287.102804
-    9    5632.0  540.671974  243.107920  289.438969
+    9    5632.0  542.843364  243.545956  288.820505
-    10   6144.0  544.118087  248.242431  285.767458
+    10   6144.0  544.118087  248.242431  286.322318
     11   6656.0  532.479975  256.000009  285.767438
-    12   7168.0  505.976473  260.260201  286.242939
+    12   7168.0  505.976473  260.654538  286.242939
-    13   7680.0  481.253256  262.190612  279.272719
+    13   7680.0  481.253256  262.564106  279.272719
     14   8192.0  463.698115  267.130429  284.526763
-    15   8704.0  416.958106  267.472468  284.987724
+    15   8704.0  417.791980  267.815384  284.987724
-    16   9216.0  430.319054  272.394084  288.751954
+    16   9216.0  429.483477  272.729961  288.751954
     17   9728.0  438.857162  280.278512  289.667485
-    18  10240.0  447.650282  286.767793  290.496460
+    18  10240.0  447.650282  286.433562  290.496460
     19  10752.0  428.651173  246.935876  290.594591
-    20  11264.0  429.786952  245.536784  286.676558
+    20  11264.0  429.104745  245.536784  286.676558
-    21  11776.0  423.089806  249.888595  288.686414
+    21  11776.0  423.089806  249.667843  288.981596
-    22  12288.0  420.102570  254.673582  294.617366
+    22  12288.0  420.102570  254.673582  294.323369
-    23  12800.0  414.574901  253.674644  288.450715
+    23  12800.0  414.574901  253.674644  289.811310
-    24  13312.0  412.242569  252.759501  289.916513
+    24  13312.0  412.242569  252.959629  289.916513
-    25  13824.0  406.090579  257.190689  292.056329
+    25  13824.0  406.090579  257.190689  291.799461
-    26  14336.0  396.387109  254.297107  286.719986
+    26  14336.0  395.930964  254.297107  286.719986
     27  14848.0  386.498925  257.665934  289.481735
-    28  15360.0  373.495460  257.970599  287.326580
+    28  15360.0  373.306347  257.970599  288.000007
-    29  15872.0  370.192407  261.806182  289.899545
+    29  15872.0  369.832994  261.806182  290.120338
 
 
 
@@ -329,7 +329,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 2 minutes  15.279 seconds)
+   **Total running time of the script:** ( 2 minutes  13.439 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
 =================
-**13:02.599** total execution time for **getting-started_tutorials** files:
+**13:27.523** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:35.980 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:01.565 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:24.992 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:23.901 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:15.279 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 02:13.439 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:46.338 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:48.510 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.010 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.108 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -334,12 +334,12 @@ for different problem sizes.</p>
 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  46.338 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  48.510 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

@@ -374,17 +374,17 @@ We will then compare its performance against (1) <code class="code docutils lite
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>softmax-performance:
           N      Triton  Torch (native)  Torch (jit)
-0     256.0  512.000001      546.133347   190.511628
+0     256.0  512.000001      546.133347   188.321838
-1     384.0  585.142862      585.142862   153.600004
+1     384.0  614.400016      585.142862   153.600004
 2     512.0  655.360017      606.814814   154.566038
 3     640.0  682.666684      640.000002   160.000000
 4     768.0  722.823517      664.216187   162.754967
 ..      ...         ...             ...          ...
-93  12160.0  814.058574      406.179533   198.936606
+93  12160.0  814.058574      406.179533   198.834951
-94  12288.0  814.111783      415.661740   199.197579
+94  12288.0  814.111783      415.661740   198.995960
-95  12416.0  812.498981      412.149375   198.755369
+95  12416.0  812.498981      412.149375   198.556711
-96  12544.0  812.566838      412.971190   199.012395
+96  12544.0  812.566838      412.971190   198.913776
-97  12672.0  812.633240      412.097543   199.069228
+97  12672.0  812.633240      412.097543   198.971549
 
 [98 rows x 4 columns]
 </pre></div>
@@ -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  24.992 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  23.901 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

@@ -568,42 +568,42 @@ 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  ...   3.276800              2.978909
+0    256.0   2.978909  ...   3.276800              2.978909
 1    384.0   7.372800  ...   8.507077              8.507077
 2    512.0  14.563555  ...  16.384000             16.384000
 3    640.0  22.260869  ...  24.380953             24.380953
 4    768.0  32.768000  ...  34.028308             34.028308
 5    896.0  39.025776  ...  40.140799             39.025776
-6   1024.0  51.150050  ...  52.428801             52.428801
+6   1024.0  51.150050  ...  53.773130             52.428801
 7   1152.0  45.242181  ...  46.656000             46.656000
 8   1280.0  51.200001  ...  56.888887             56.888887
-9   1408.0  64.138541  ...  67.305878             67.305878
+9   1408.0  64.138541  ...  67.305878             66.485074
-10  1536.0  79.526831  ...  79.526831             79.526831
+10  1536.0  80.430545  ...  79.526831             78.643199
 11  1664.0  62.929456  ...  62.492442             62.061463
-12  1792.0  72.983276  ...  72.512412             72.047592
+12  1792.0  72.512412  ...  72.512412             71.588687
-13  1920.0  68.776119  ...  70.172588             70.172588
+13  1920.0  69.120002  ...  70.172588             70.172588
 14  2048.0  73.584279  ...  76.959706             76.959706
-15  2176.0  83.500614  ...  86.367588             85.632545
+15  2176.0  83.155572  ...  86.367588             85.632545
-16  2304.0  68.643310  ...  76.319081             76.319081
+16  2304.0  68.446623  ...  77.057651             76.563695
-17  2432.0  71.125224  ...  82.147552             84.367759
+17  2432.0  71.487187  ...  85.653855             84.877538
-18  2560.0  77.283019  ...  80.908642             80.511054
+18  2560.0  78.019048  ...  80.709358             80.313727
-19  2688.0  83.369354  ...  89.676257             89.464755
+19  2688.0  83.369354  ...  88.836198             89.676257
-20  2816.0  83.552120  ...  82.916747             83.233226
+20  2816.0  82.916747  ...  83.392363             82.135981
-21  2944.0  82.373605  ...  80.771529             82.921853
+21  2944.0  80.380696  ...  79.865439             82.373605
-22  3072.0  81.589488  ...  88.612060             88.612060
+22  3072.0  82.181572  ...  88.335577             88.473602
-23  3200.0  82.368085  ...  94.674553             94.117647
+23  3200.0  84.768213  ...  95.096582             94.814812
-24  3328.0  82.369902  ...  83.275067             80.347427
+24  3328.0  83.034941  ...  84.298943             83.516586
-25  3456.0  81.849303  ...  84.775569             90.382926
+25  3456.0  81.108217  ...  87.727494             90.382926
-26  3584.0  87.381330  ...  98.375705             98.160909
+26  3584.0  87.381330  ...  98.375705             98.268190
-27  3712.0  83.386762  ...  88.718781             83.074717
+27  3712.0  80.757757  ...  88.483034             85.091436
-28  3840.0  84.356981  ...  92.390975             84.940091
+28  3840.0  82.778440  ...  89.693434             84.550462
-29  3968.0  91.885495  ...  84.096442             88.615785
+29  3968.0  87.535103  ...  84.385406             86.419216
-30  4096.0  86.480498  ...  92.755862             85.271746
+30  4096.0  89.478485  ...  92.245860             85.161847
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  35.980 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  1.565 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  0.010 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.108 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   98.303995  303.407414
+0    1024.0  307.200008   98.303995  303.407414
-1    1536.0  351.085717  134.050910  341.333333
+1    1536.0  351.085717  134.540150  341.333333
-2    2048.0  423.724127  161.684218  334.367350
+2    2048.0  420.102553  161.684218  325.509933
-3    2560.0  465.454542  181.238943  330.322572
+3    2560.0  465.454542  181.238943  326.808501
-4    3072.0  511.999982  191.999993  320.556515
+4    3072.0  511.999982  192.501302  316.429186
-5    3584.0  551.384634  208.271186  310.527060
+5    3584.0  551.384634  208.271186  309.410081
-6    4096.0  568.231237  219.919464  298.796351
+6    4096.0  568.231237  220.412561  298.796351
-7    4608.0  500.416301  232.825259  286.507772
+7    4608.0  500.416301  232.825259  289.507855
-8    5120.0  525.128191  242.845844  284.444444
+8    5120.0  525.128191  242.366855  287.102804
-9    5632.0  540.671974  243.107920  289.438969
+9    5632.0  542.843364  243.545956  288.820505
-10   6144.0  544.118087  248.242431  285.767458
+10   6144.0  544.118087  248.242431  286.322318
 11   6656.0  532.479975  256.000009  285.767438
-12   7168.0  505.976473  260.260201  286.242939
+12   7168.0  505.976473  260.654538  286.242939
-13   7680.0  481.253256  262.190612  279.272719
+13   7680.0  481.253256  262.564106  279.272719
 14   8192.0  463.698115  267.130429  284.526763
-15   8704.0  416.958106  267.472468  284.987724
+15   8704.0  417.791980  267.815384  284.987724
-16   9216.0  430.319054  272.394084  288.751954
+16   9216.0  429.483477  272.729961  288.751954
 17   9728.0  438.857162  280.278512  289.667485
-18  10240.0  447.650282  286.767793  290.496460
+18  10240.0  447.650282  286.433562  290.496460
 19  10752.0  428.651173  246.935876  290.594591
-20  11264.0  429.786952  245.536784  286.676558
+20  11264.0  429.104745  245.536784  286.676558
-21  11776.0  423.089806  249.888595  288.686414
+21  11776.0  423.089806  249.667843  288.981596
-22  12288.0  420.102570  254.673582  294.617366
+22  12288.0  420.102570  254.673582  294.323369
-23  12800.0  414.574901  253.674644  288.450715
+23  12800.0  414.574901  253.674644  289.811310
-24  13312.0  412.242569  252.759501  289.916513
+24  13312.0  412.242569  252.959629  289.916513
-25  13824.0  406.090579  257.190689  292.056329
+25  13824.0  406.090579  257.190689  291.799461
-26  14336.0  396.387109  254.297107  286.719986
+26  14336.0  395.930964  254.297107  286.719986
 27  14848.0  386.498925  257.665934  289.481735
-28  15360.0  373.495460  257.970599  287.326580
+28  15360.0  373.306347  257.970599  288.000007
-29  15872.0  370.192407  261.806182  289.899545
+29  15872.0  369.832994  261.806182  290.120338
 </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  15.279 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  13.439 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>13:02.599</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>13:27.523</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>05:35.980</p></td>
+<td><p>06:01.565</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>03:24.992</p></td>
+<td><p>03:23.901</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>02:15.279</p></td>
+<td><p>02:13.439</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>01:46.338</p></td>
+<td><p>01:48.510</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>00:00.010</p></td>
+<td><p>00:00.108</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>