[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: ae6382d0c6dcb078734471a10c08ed2c
+config: 3c4cc7001576fc9b955791cc71cb01bc
 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   76.800002   76.800002
+    3       32768.0   63.999998   63.999998
     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  722.823517
+    9     2097152.0  722.823517  702.171410
     10    4194304.0  780.190482  780.190482
     11    8388608.0  812.429770  812.429770
     12   16777216.0  833.084721  833.084721
-    13   33554432.0  842.004273  842.906750
+    13   33554432.0  842.004273  842.004273
     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  26.773 seconds)
+   **Total running time of the script:** ( 1 minutes  40.930 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  546.133347      512.000001   188.321838
+    0     256.0  546.133347      512.000001   186.181817
     1     384.0  614.400016      585.142862   153.600004
-    2     512.0  655.360017      606.814814   154.566038
-    3     640.0  706.206879      640.000002   160.000000
+    2     512.0  655.360017      585.142849   154.566038
+    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   198.429370
-    94  12288.0  812.429770      415.661740   198.794749
-    95  12416.0  812.498981      412.149375   198.358474
-    96  12544.0  812.566838      412.546756   198.716830
-    97  12672.0  812.633240      412.097543   198.776477
+    93  12160.0  812.359066      406.179533   198.936606
+    94  12288.0  812.429770      415.222812   199.197579
+    95  12416.0  812.498981      412.149375   198.854847
+    96  12544.0  812.566838      412.758863   199.111113
+    97  12672.0  811.007961      412.097543   199.167004
 
     [98 rows x 4 columns]
 
@@ -306,7 +306,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 3 minutes  13.971 seconds)
+   **Total running time of the script:** ( 3 minutes  22.248 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  ...   3.276800              3.276800
-    1    384.0   7.372800  ...   8.507077              8.507077
-    2    512.0  14.563555  ...  15.887515             15.420235
+    0    256.0   2.730667  ...   2.978909              3.276800
+    1    384.0   7.372800  ...   7.899428              7.899428
+    2    512.0  14.563555  ...  15.420235             16.384000
     3    640.0  22.260869  ...  24.380953             24.380953
-    4    768.0  32.768000  ...  35.389441             34.028308
-    5    896.0  39.025776  ...  41.321411             39.025776
+    4    768.0  32.768000  ...  34.028308             34.028308
+    5    896.0  39.025776  ...  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             67.305878
-    10  1536.0  79.526831  ...  80.430545             78.643199
+    9   1408.0  64.138541  ...  69.009825             67.305878
+    10  1536.0  79.526831  ...  79.526831             78.643199
     11  1664.0  63.372618  ...  63.372618             62.492442
     12  1792.0  72.983276  ...  63.499573             63.142831
     13  1920.0  68.776119  ...  71.257735             70.892307
     14  2048.0  73.262953  ...  78.033565             76.959706
-    15  2176.0  83.155572  ...  87.115360             85.632545
+    15  2176.0  83.155572  ...  87.494120             85.998493
     16  2304.0  68.446623  ...  78.064941             76.809875
-    17  2432.0  71.125224  ...  75.522751             74.521127
-    18  2560.0  77.833728  ...  82.125311             81.512437
-    19  2688.0  83.737433  ...  90.102270             90.102270
-    20  2816.0  79.733474  ...  84.523664             82.916747
-    21  2944.0  81.967162  ...  83.758038             83.758038
-    22  3072.0  81.707223  ...  89.451983             87.924073
-    23  3200.0  84.321474  ...  93.023256             95.167286
-    24  3328.0  83.516586  ...  85.806075             86.011103
-    25  3456.0  82.519518  ...  92.297157             91.407671
-    26  3584.0  85.552231  ...  91.467482             98.268190
-    27  3712.0  85.675250  ...  88.876645             87.399253
-    28  3840.0  83.528704  ...  89.403396             87.424508
-    29  3968.0  88.040360  ...  87.976885             90.388098
-    30  4096.0  86.592080  ...  90.260743             93.401342
+    17  2432.0  71.305746  ...  75.522751             74.521127
+    18  2560.0  77.833728  ...  82.331658             81.310171
+    19  2688.0  83.737433  ...  91.185232             89.888756
+    20  2816.0  83.873477  ...  84.523664             81.067298
+    21  2944.0  81.967162  ...  83.477440             82.237674
+    22  3072.0  82.301023  ...  88.960098             87.651868
+    23  3200.0  84.656085  ...  96.240602             94.814812
+    24  3328.0  83.130825  ...  84.995628             84.496824
+    25  3456.0  82.604067  ...  84.686523             81.189898
+    26  3584.0  87.381330  ...  99.684470             97.311031
+    27  3712.0  85.055211  ...  88.015279             87.552452
+    28  3840.0  84.940091  ...  93.090912             84.164384
+    29  3968.0  92.793868  ...  84.917596             91.403695
+    30  4096.0  88.272097  ...  89.299883             93.206754
 
     [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:** ( 5 minutes  41.088 seconds)
+   **Total running time of the script:** ( 6 minutes  9.260 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  0.548 seconds)
+   **Total running time of the script:** ( 0 minutes  0.484 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py:

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

@@ -42,25 +42,25 @@ Layer Normalization
     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  376.643666  501.551037
-    5    3584.0  725.873439  384.859062  455.111115
-    6    4096.0  728.177767  381.023256  455.111095
-    7    4608.0  670.254540  396.387087  428.651163
-    8    5120.0  688.403381  397.669909  422.268057
-    9    5632.0  704.000002  395.228063  417.185184
+    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  396.387087  426.173427
+    8    5120.0  688.403381  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
-    12   7168.0  690.891575  396.844306  387.459443
-    13   7680.0  682.666656  392.587863  386.415087
-    14   8192.0  639.375598  393.609605  371.308771
-    15   8704.0  630.153861  389.005597  380.502740
-    16   9216.0  609.322328  407.337026  383.999986
+    11   6656.0  705.271522  398.861429  398.861429
+    12   7168.0  695.078767  396.844306  388.772874
+    13   7680.0  682.666656  392.587863  387.634072
+    14   8192.0  642.509816  393.609605  372.363633
+    15   8704.0  627.315309  389.005597  380.502740
+    16   9216.0  606.814809  407.337026  383.002605
     17   9728.0  589.575753  409.599987  383.369452
-    18  10240.0  568.888869  408.578556  381.911416
+    18  10240.0  566.920437  408.578556  382.803739
     19  10752.0  551.384634  411.559798  381.445676
     20  11264.0  536.380957  406.826188  373.134567
-    21  11776.0  524.835658  409.599991  377.587162
-    22  12288.0  517.389457  413.911572  383.251457
+    21  11776.0  523.377770  409.599991  377.587162
+    22  12288.0  518.754611  413.911572  383.251457
     23  12800.0  505.679014  410.420828  376.470582
     24  13312.0  494.180982  405.699062  376.310952
     25  13824.0  482.934503  411.888257  379.389355
@@ -389,7 +389,7 @@ Layer Normalization
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 5 minutes  12.730 seconds)
+   **Total running time of the script:** ( 5 minutes  19.676 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
 =================
-**15:35.109** total execution time for **getting-started_tutorials** files:
+**16:32.599** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:41.088 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:09.260 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:12.730 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``)                       | 05:19.676 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:13.971 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 03:22.248 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:26.773 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 01:40.930 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.548 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``)       | 00:00.484 | 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   76.800002   76.800002
+3       32768.0   63.999998   63.999998
 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  722.823517
+9     2097152.0  722.823517  702.171410
 10    4194304.0  780.190482  780.190482
 11    8388608.0  812.429770  812.429770
 12   16777216.0  833.084721  833.084721
-13   33554432.0  842.004273  842.906750
+13   33554432.0  842.004273  842.004273
 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  26.773 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  40.930 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  546.133347      512.000001   188.321838
+0     256.0  546.133347      512.000001   186.181817
 1     384.0  614.400016      585.142862   153.600004
-2     512.0  655.360017      606.814814   154.566038
-3     640.0  706.206879      640.000002   160.000000
+2     512.0  655.360017      585.142849   154.566038
+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   198.429370
-94  12288.0  812.429770      415.661740   198.794749
-95  12416.0  812.498981      412.149375   198.358474
-96  12544.0  812.566838      412.546756   198.716830
-97  12672.0  812.633240      412.097543   198.776477
+93  12160.0  812.359066      406.179533   198.936606
+94  12288.0  812.429770      415.222812   199.197579
+95  12416.0  812.498981      412.149375   198.854847
+96  12544.0  812.566838      412.758863   199.111113
+97  12672.0  811.007961      412.097543   199.167004
 
 [98 rows x 4 columns]
 </pre></div>
@@ -392,7 +392,7 @@ We will then compare its performance against (1) <code class="code docutils lite
 Note however that the PyTorch <cite>softmax</cite> operation is more general and will works on tensors of any shape.</p></li>
 </ul>
 </div></blockquote>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  13.971 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  22.248 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  ...   3.276800              3.276800
-1    384.0   7.372800  ...   8.507077              8.507077
-2    512.0  14.563555  ...  15.887515             15.420235
+0    256.0   2.730667  ...   2.978909              3.276800
+1    384.0   7.372800  ...   7.899428              7.899428
+2    512.0  14.563555  ...  15.420235             16.384000
 3    640.0  22.260869  ...  24.380953             24.380953
-4    768.0  32.768000  ...  35.389441             34.028308
-5    896.0  39.025776  ...  41.321411             39.025776
+4    768.0  32.768000  ...  34.028308             34.028308
+5    896.0  39.025776  ...  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             67.305878
-10  1536.0  79.526831  ...  80.430545             78.643199
+9   1408.0  64.138541  ...  69.009825             67.305878
+10  1536.0  79.526831  ...  79.526831             78.643199
 11  1664.0  63.372618  ...  63.372618             62.492442
 12  1792.0  72.983276  ...  63.499573             63.142831
 13  1920.0  68.776119  ...  71.257735             70.892307
 14  2048.0  73.262953  ...  78.033565             76.959706
-15  2176.0  83.155572  ...  87.115360             85.632545
+15  2176.0  83.155572  ...  87.494120             85.998493
 16  2304.0  68.446623  ...  78.064941             76.809875
-17  2432.0  71.125224  ...  75.522751             74.521127
-18  2560.0  77.833728  ...  82.125311             81.512437
-19  2688.0  83.737433  ...  90.102270             90.102270
-20  2816.0  79.733474  ...  84.523664             82.916747
-21  2944.0  81.967162  ...  83.758038             83.758038
-22  3072.0  81.707223  ...  89.451983             87.924073
-23  3200.0  84.321474  ...  93.023256             95.167286
-24  3328.0  83.516586  ...  85.806075             86.011103
-25  3456.0  82.519518  ...  92.297157             91.407671
-26  3584.0  85.552231  ...  91.467482             98.268190
-27  3712.0  85.675250  ...  88.876645             87.399253
-28  3840.0  83.528704  ...  89.403396             87.424508
-29  3968.0  88.040360  ...  87.976885             90.388098
-30  4096.0  86.592080  ...  90.260743             93.401342
+17  2432.0  71.305746  ...  75.522751             74.521127
+18  2560.0  77.833728  ...  82.331658             81.310171
+19  2688.0  83.737433  ...  91.185232             89.888756
+20  2816.0  83.873477  ...  84.523664             81.067298
+21  2944.0  81.967162  ...  83.477440             82.237674
+22  3072.0  82.301023  ...  88.960098             87.651868
+23  3200.0  84.656085  ...  96.240602             94.814812
+24  3328.0  83.130825  ...  84.995628             84.496824
+25  3456.0  82.604067  ...  84.686523             81.189898
+26  3584.0  87.381330  ...  99.684470             97.311031
+27  3712.0  85.055211  ...  88.015279             87.552452
+28  3840.0  84.940091  ...  93.090912             84.164384
+29  3968.0  92.793868  ...  84.917596             91.403695
+30  4096.0  88.272097  ...  89.299883             93.206754
 
 [31 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  41.088 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes  9.260 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  0.548 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.484 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

@@ -198,25 +198,25 @@ to download the full example code</p>
 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  376.643666  501.551037
-5    3584.0  725.873439  384.859062  455.111115
-6    4096.0  728.177767  381.023256  455.111095
-7    4608.0  670.254540  396.387087  428.651163
-8    5120.0  688.403381  397.669909  422.268057
-9    5632.0  704.000002  395.228063  417.185184
+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  396.387087  426.173427
+8    5120.0  688.403381  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
-12   7168.0  690.891575  396.844306  387.459443
-13   7680.0  682.666656  392.587863  386.415087
-14   8192.0  639.375598  393.609605  371.308771
-15   8704.0  630.153861  389.005597  380.502740
-16   9216.0  609.322328  407.337026  383.999986
+11   6656.0  705.271522  398.861429  398.861429
+12   7168.0  695.078767  396.844306  388.772874
+13   7680.0  682.666656  392.587863  387.634072
+14   8192.0  642.509816  393.609605  372.363633
+15   8704.0  627.315309  389.005597  380.502740
+16   9216.0  606.814809  407.337026  383.002605
 17   9728.0  589.575753  409.599987  383.369452
-18  10240.0  568.888869  408.578556  381.911416
+18  10240.0  566.920437  408.578556  382.803739
 19  10752.0  551.384634  411.559798  381.445676
 20  11264.0  536.380957  406.826188  373.134567
-21  11776.0  524.835658  409.599991  377.587162
-22  12288.0  517.389457  413.911572  383.251457
+21  11776.0  523.377770  409.599991  377.587162
+22  12288.0  518.754611  413.911572  383.251457
 23  12800.0  505.679014  410.420828  376.470582
 24  13312.0  494.180982  405.699062  376.310952
 25  13824.0  482.934503  411.888257  379.389355
@@ -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  12.730 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  19.676 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>15:35.109</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>16:32.599</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>05:41.088</p></td>
+<td><p>06:09.260</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>05:12.730</p></td>
+<td><p>05:19.676</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>03:13.971</p></td>
+<td><p>03:22.248</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>01:26.773</p></td>
+<td><p>01:40.930</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>00:00.548</p></td>
+<td><p>00:00.484</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: 21d2fcdf45d510000722199a9dcc7f4c
+config: 85e0647b01929cd83a01edb54c07fdf6
 tags: 645f666f9bcd5a90fca523b33c5a78b7