[GH-PAGES] Updated website

_downloads/034d953b6214fedce6ea03803c712b89/02-fused-softmax.ipynb

@@ -33,7 +33,7 @@
       },
       "outputs": [],
       "source": [
-        "import torch\n\n\n# Compute the row-wise softmax of x\n@torch.jit.script\ndef naive_softmax(x):\n    # read  MN elements ; write M  elements\n    x_max = x.max(dim=1)[0]\n    # read 2MN elements ; write MN elements\n    z = x - x_max[:, None]\n    # read  MN elements ; write MN elements\n    numerator = torch.exp(x)\n    # read  MN elements ; write M  elements\n    denominator = numerator.sum(dim=1)\n    # read 2MN elements ; write MN elements\n    ret = numerator / denominator[:, None]\n    # in total: read 7MN elements ; wrote 3MN + 2M elements\n    return ret"
+        "import torch\n\n\n# Compute the row-wise softmax of x\n@torch.jit.script\ndef naive_softmax(x):\n    # read  MN elements ; write M  elements\n    x_max = x.max(dim=1)[0]\n    # read 2MN elements ; write MN elements\n    z = x - x_max[:, None]\n    # read  MN elements ; write MN elements\n    numerator = torch.exp(z)\n    # read  MN elements ; write M  elements\n    denominator = numerator.sum(dim=1)\n    # read 2MN elements ; write MN elements\n    ret = numerator / denominator[:, None]\n    # in total: read 7MN elements ; wrote 3MN + 2M elements\n    return ret"
       ]
     },
     {

_downloads/d91442ac2982c4e0cc3ab0f43534afbc/02-fused-softmax.py

@@ -25,7 +25,7 @@ def naive_softmax(x):
     # read 2MN elements ; write MN elements
     z = x - x_max[:, None]
     # read  MN elements ; write MN elements
-    numerator = torch.exp(x)
+    numerator = torch.exp(z)
     # read  MN elements ; write M  elements
     denominator = numerator.sum(dim=1)
     # read 2MN elements ; write MN elements

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

@@ -239,7 +239,7 @@ 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:** ( 0 minutes  11.032 seconds)
+   **Total running time of the script:** ( 0 minutes  10.984 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

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

@@ -49,7 +49,7 @@ Let us consider instead the case of a simple (numerically stabilized) softmax op
         # read 2MN elements ; write MN elements
         z = x - x_max[:, None]
         # read  MN elements ; write MN elements
-        numerator = torch.exp(x)
+        numerator = torch.exp(z)
         # read  MN elements ; write M  elements
         denominator = numerator.sum(dim=1)
         # read 2MN elements ; write MN elements
@@ -261,17 +261,17 @@ 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   273.066674
+    0     256.0  512.000001      546.133347   186.181817
-    1     384.0  585.142862      585.142862   267.130429
+    1     384.0  585.142862      585.142862   153.600004
-    2     512.0  630.153853      606.814814   264.258068
+    2     512.0  630.153853      606.814814   154.566038
-    3     640.0  682.666684      640.000002   269.473696
+    3     640.0  682.666684      640.000002   160.000000
-    4     768.0  702.171410      664.216187   273.066663
+    4     768.0  702.171410      664.216187   162.754967
     ..      ...         ...             ...          ...
-    93  12160.0  812.359066      406.179533   329.483481
+    93  12160.0  812.359066      406.179533   198.936606
-    94  12288.0  812.429770      415.661740   329.602681
+    94  12288.0  812.429770      416.101597   199.298541
-    95  12416.0  810.840807      412.149375   329.173158
+    95  12416.0  810.840807      412.149375   198.854847
-    96  12544.0  810.925276      412.546756   329.292871
+    96  12544.0  810.925276      412.971190   199.111113
-    97  12672.0  811.007961      412.097543   329.410251
+    97  12672.0  811.007961      412.097543   199.167004
 
     [98 rows x 4 columns]
 
@@ -290,7 +290,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 1 minutes  8.174 seconds)
+   **Total running time of the script:** ( 1 minutes  13.269 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -371,37 +371,37 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
     matmul-performance:
              M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
     0    128.0   0.455111  ...   0.512000              0.512000
-    1    256.0   2.978909  ...   2.978909              2.978909
+    1    256.0   2.730667  ...   2.978909              2.978909
-    2    384.0   7.372800  ...   7.899428              7.899428
+    2    384.0   7.372800  ...   8.507077              8.507077
     3    512.0  14.563555  ...  16.384000             15.420235
     4    640.0  22.260869  ...  24.380953             24.380953
     5    768.0  32.768000  ...  34.028308             34.028308
     6    896.0  39.025776  ...  39.025776             39.025776
-    7   1024.0  51.150050  ...  52.428801             52.428801
+    7   1024.0  49.932191  ...  52.428801             52.428801
     8   1152.0  44.566925  ...  46.656000             46.656000
     9   1280.0  51.200001  ...  56.109587             56.109587
-    10  1408.0  64.138541  ...  65.684049             65.684049
+    10  1408.0  64.138541  ...  65.684049             64.902096
-    11  1536.0  80.430545  ...  76.106321             75.296679
+    11  1536.0  80.430545  ...  76.106321             76.106321
-    12  1664.0  63.372618  ...  62.061463             61.636381
+    12  1664.0  63.372618  ...  61.636381             61.636381
-    13  1792.0  72.983276  ...  68.953520             68.533074
+    13  1792.0  72.983276  ...  69.379162             68.953520
-    14  1920.0  69.120002  ...  68.435645             68.435645
+    14  1920.0  68.435645  ...  69.818184             68.776119
-    15  2048.0  73.908442  ...  75.573044             75.234154
+    15  2048.0  73.584279  ...  75.915006             75.234154
-    16  2176.0  83.500614  ...  80.173899             79.855747
+    16  2176.0  83.500614  ...  78.608000             79.540109
-    17  2304.0  68.446623  ...  73.051599             72.607513
+    17  2304.0  68.251065  ...  73.051599             72.607513
-    18  2432.0  71.125224  ...  81.197876             80.963875
+    18  2432.0  71.125224  ...  81.669953             80.269900
-    19  2560.0  77.649287  ...  76.027843             76.740048
+    19  2560.0  77.833728  ...  75.328737             74.812787
-    20  2688.0  83.552988  ...  83.186525             82.823267
+    20  2688.0  81.576466  ...  81.227100             82.823267
-    21  2816.0  84.035084  ...  76.921000             79.733474
+    21  2816.0  83.392363  ...  78.868366             77.330158
-    22  2944.0  82.102191  ...  80.122235             78.729910
+    22  2944.0  81.698415  ...  80.122235             79.356738
-    23  3072.0  82.540970  ...  82.661468             82.661468
+    23  3072.0  80.890151  ...  81.589488             83.391907
-    24  3200.0  84.432717  ...  89.385477             84.432717
+    24  3200.0  84.656085  ...  85.447263             88.033012
-    25  3328.0  83.905938  ...  86.113988             86.528001
+    25  3328.0  82.939284  ...  86.632127             82.558825
-    26  3456.0  82.015834  ...  83.545665             84.156124
+    26  3456.0  81.518272  ...  84.954233             84.420490
-    27  3584.0  87.466332  ...  92.600816             84.988707
+    27  3584.0  83.254996  ...  94.747514             95.654673
-    28  3712.0  85.163978  ...  82.902362             83.666116
+    28  3712.0  86.192706  ...  88.955779             88.797643
-    29  3840.0  84.292684  ...  84.550462             85.070769
+    29  3840.0  84.809814  ...  84.874902             84.356981
-    30  3968.0  89.921841  ...  87.472354             87.409694
+    30  3968.0  89.593789  ...  84.738843             84.212518
-    31  4096.0  93.792965  ...  89.478485             90.260743
+    31  4096.0  93.596744  ...  83.833686             90.933423
 
     [32 rows x 5 columns]
 
@@ -411,7 +411,7 @@ 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:** ( 2 minutes  2.376 seconds)
+   **Total running time of the script:** ( 2 minutes  16.432 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

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

@@ -5,12 +5,12 @@
 
 Computation times
 =================
-**03:21.583** total execution time for **getting-started_tutorials** files:
+**03:40.685** total execution time for **getting-started_tutorials** files:
 
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 02:02.376 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 02:16.432 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 01:08.174 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``)                 | 01:13.269 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 00:11.032 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)                       | 00:10.984 | 0.0 MB |
 +---------------------------------------------------------------------------------------------------------+-----------+--------+

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

@@ -323,7 +323,7 @@ for different problem sizes.</p>
 15  134217728.0  851.577704  850.656574
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  11.032 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  10.984 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>

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

@@ -216,7 +216,7 @@ Let us consider instead the case of a simple (numerically stabilized) softmax op
     <span class="c1"># read 2MN elements ; write MN elements</span>
     <span class="n">z</span> <span class="o">=</span> <span class="n">x</span> <span class="o">-</span> <span class="n">x_max</span><span class="p">[:,</span> <span class="kc">None</span><span class="p">]</span>
     <span class="c1"># read  MN elements ; write MN elements</span>
-    <span class="n">numerator</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
+    <span class="n">numerator</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="n">z</span><span class="p">)</span>
     <span class="c1"># read  MN elements ; write M  elements</span>
     <span class="n">denominator</span> <span class="o">=</span> <span class="n">numerator</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
     <span class="c1"># read 2MN elements ; write MN elements</span>
@@ -346,17 +346,17 @@ 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   273.066674
+0     256.0  512.000001      546.133347   186.181817
-1     384.0  585.142862      585.142862   267.130429
+1     384.0  585.142862      585.142862   153.600004
-2     512.0  630.153853      606.814814   264.258068
+2     512.0  630.153853      606.814814   154.566038
-3     640.0  682.666684      640.000002   269.473696
+3     640.0  682.666684      640.000002   160.000000
-4     768.0  702.171410      664.216187   273.066663
+4     768.0  702.171410      664.216187   162.754967
 ..      ...         ...             ...          ...
-93  12160.0  812.359066      406.179533   329.483481
+93  12160.0  812.359066      406.179533   198.936606
-94  12288.0  812.429770      415.661740   329.602681
+94  12288.0  812.429770      416.101597   199.298541
-95  12416.0  810.840807      412.149375   329.173158
+95  12416.0  810.840807      412.149375   198.854847
-96  12544.0  810.925276      412.546756   329.292871
+96  12544.0  810.925276      412.971190   199.111113
-97  12672.0  811.007961      412.097543   329.410251
+97  12672.0  811.007961      412.097543   199.167004
 
 [98 rows x 4 columns]
 </pre></div>
@@ -370,7 +370,7 @@ This means that – when temporary data is too large to fit entirely in the GPU
 Note that our Triton kernel is not only faster than PyTorch’s CUDA kernel, it is also <strong>easier to read, understand and maintain</strong>.</p></li>
 </ul>
 </div></blockquote>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  8.174 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  13.269 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>

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

@@ -476,42 +476,42 @@ tensor(True, device='cuda:0')
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>matmul-performance:
          M     cuBLAS  ...     Triton  Triton (+ LeakyReLU)
 0    128.0   0.455111  ...   0.512000              0.512000
-1    256.0   2.978909  ...   2.978909              2.978909
+1    256.0   2.730667  ...   2.978909              2.978909
-2    384.0   7.372800  ...   7.899428              7.899428
+2    384.0   7.372800  ...   8.507077              8.507077
 3    512.0  14.563555  ...  16.384000             15.420235
 4    640.0  22.260869  ...  24.380953             24.380953
 5    768.0  32.768000  ...  34.028308             34.028308
 6    896.0  39.025776  ...  39.025776             39.025776
-7   1024.0  51.150050  ...  52.428801             52.428801
+7   1024.0  49.932191  ...  52.428801             52.428801
 8   1152.0  44.566925  ...  46.656000             46.656000
 9   1280.0  51.200001  ...  56.109587             56.109587
-10  1408.0  64.138541  ...  65.684049             65.684049
+10  1408.0  64.138541  ...  65.684049             64.902096
-11  1536.0  80.430545  ...  76.106321             75.296679
+11  1536.0  80.430545  ...  76.106321             76.106321
-12  1664.0  63.372618  ...  62.061463             61.636381
+12  1664.0  63.372618  ...  61.636381             61.636381
-13  1792.0  72.983276  ...  68.953520             68.533074
+13  1792.0  72.983276  ...  69.379162             68.953520
-14  1920.0  69.120002  ...  68.435645             68.435645
+14  1920.0  68.435645  ...  69.818184             68.776119
-15  2048.0  73.908442  ...  75.573044             75.234154
+15  2048.0  73.584279  ...  75.915006             75.234154
-16  2176.0  83.500614  ...  80.173899             79.855747
+16  2176.0  83.500614  ...  78.608000             79.540109
-17  2304.0  68.446623  ...  73.051599             72.607513
+17  2304.0  68.251065  ...  73.051599             72.607513
-18  2432.0  71.125224  ...  81.197876             80.963875
+18  2432.0  71.125224  ...  81.669953             80.269900
-19  2560.0  77.649287  ...  76.027843             76.740048
+19  2560.0  77.833728  ...  75.328737             74.812787
-20  2688.0  83.552988  ...  83.186525             82.823267
+20  2688.0  81.576466  ...  81.227100             82.823267
-21  2816.0  84.035084  ...  76.921000             79.733474
+21  2816.0  83.392363  ...  78.868366             77.330158
-22  2944.0  82.102191  ...  80.122235             78.729910
+22  2944.0  81.698415  ...  80.122235             79.356738
-23  3072.0  82.540970  ...  82.661468             82.661468
+23  3072.0  80.890151  ...  81.589488             83.391907
-24  3200.0  84.432717  ...  89.385477             84.432717
+24  3200.0  84.656085  ...  85.447263             88.033012
-25  3328.0  83.905938  ...  86.113988             86.528001
+25  3328.0  82.939284  ...  86.632127             82.558825
-26  3456.0  82.015834  ...  83.545665             84.156124
+26  3456.0  81.518272  ...  84.954233             84.420490
-27  3584.0  87.466332  ...  92.600816             84.988707
+27  3584.0  83.254996  ...  94.747514             95.654673
-28  3712.0  85.163978  ...  82.902362             83.666116
+28  3712.0  86.192706  ...  88.955779             88.797643
-29  3840.0  84.292684  ...  84.550462             85.070769
+29  3840.0  84.809814  ...  84.874902             84.356981
-30  3968.0  89.921841  ...  87.472354             87.409694
+30  3968.0  89.593789  ...  84.738843             84.212518
-31  4096.0  93.792965  ...  89.478485             90.260743
+31  4096.0  93.596744  ...  83.833686             90.933423
 
 [32 rows x 5 columns]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  2.376 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes  16.432 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>

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>03:21.583</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>03:40.685</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 85%" />
@@ -183,15 +183,15 @@
 </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>02:02.376</p></td>
+<td><p>02:16.432</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>01:08.174</p></td>
+<td><p>01:13.269</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-odd"><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>00:11.032</p></td>
+<td><p>00:10.984</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>