[GH-PAGES] Updated website

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

@@ -122,7 +122,7 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\n\nM = 4096\nNs = [256 * i for i in range(2, 50)]\ntri_bw = []\nref_bw = []\ndef_bw = []\nfor N in Ns:\n    x = torch.randn(M, N, device='cuda', dtype=torch.float32)\n    gbps = lambda ms: x.nelement() * x.element_size() * 1e-9 / (ms * 1e-3)\n    do_bench = lambda fn: gbps(triton.testing.do_bench(fn, warmup=10, rep=100, clear_l2=True))\n    tri_bw += [do_bench(lambda: softmax(x))]\n    ref_bw += [do_bench(lambda: torch.softmax(x, axis=1))]\n    def_bw += [do_bench(lambda: naive_softmax(x))]\nplt.xlabel('N')\nplt.ylabel('Bandwidth (GB/s)')\nplt.plot(Ns, tri_bw, label='Triton')\nplt.plot(Ns, ref_bw, label='Torch')\nplt.plot(Ns, def_bw, label='Naive')\nplt.legend()\nplt.show()"
+        "@triton.testing.perf_report(\n    triton.testing.Benchmark(\n        x_names=['N'],  # argument names to use as an x-axis for the plot\n        x_vals=[256 * i for i in range(2, 50)],  # different possible values for `x_name`\n        y_name='provider',  # argument name whose value corresponds to a different line in the plot\n        y_vals=['torch', 'triton', 'naive'],  # possible keys for `y_name`\n        y_lines=[\"Torch\", \"Triton\", 'Naive'],  # label name for the lines\n        ylabel=\"GB/s\",  # label name for the y-axis\n        plot_name=\"softmax-performance\",  # name for the plot. Used also as a file name for saving the plot.\n        args={'M': 4096}  # values for function arguments not in `x_names` and `y_name`\n    )\n)\ndef benchmark(M, N, provider):\n    x = torch.randn(M, N, device='cuda', dtype=torch.float32)\n    if provider == 'torch':\n        ms, min_ms, max_ms = triton.testing.do_bench(lambda: torch.softmax(x, axis=-1))\n    if provider == 'triton':\n        ms, min_ms, max_ms = triton.testing.do_bench(lambda: softmax(x))\n    if provider == 'naive':\n        ms, min_ms, max_ms = triton.testing.do_bench(lambda: naive_softmax(x))\n    gbps = lambda ms: 2 * x.nelement() * x.element_size() * 1e-9 / (ms * 1e-3)\n    return gbps(ms), gbps(max_ms), gbps(min_ms)\n\n\nbenchmark.run(show_plots=True)"
       ]
     },
     {

_downloads/62d97d49a32414049819dd8bb8378080/01-vector-add.py

@@ -147,33 +147,35 @@ print(f'The maximum difference between torch and triton is ' f'{torch.max(torch.
 # Benchmarking
 # --------------------------
 # We can now benchmark our custom op for vectors of increasing sizes to get a sense of how it does relative to PyTorch.
+# To make things easier, Triton has a set of built-in utilities that allow us to concisely plot the performance of our custom op.
+# for different problem sizes.
 
-import matplotlib.pyplot as plt
 
-# There are three tensors of 4N bytes each. So the bandwidth of a given kernel
+@triton.testing.perf_report(
-# is 12N / time_ms * 1e-6 GB/s
+    triton.testing.Benchmark(
-gbps = lambda N, ms: 12 * N / ms * 1e-6
+        x_names=['size'],  # argument names to use as an x-axis for the plot
-# We want to benchmark small and large vector alike
+        x_vals=[2**i for i in range(12, 28, 1)],  # different possible values for `x_name`
-sizes = [2**i for i in range(12, 25, 1)]
+        x_log=True,  # x axis is logarithmic
-triton_bw = []
+        y_name='provider',  # argument name whose value corresponds to a different line in the plot
-torch_bw = []
+        y_vals=['torch', 'triton'],  # possible keys for `y_name`
-for N in sizes:
+        y_lines=["Torch", "Triton"],  # label name for the lines
-    x = torch.rand(N, device='cuda', dtype=torch.float32)
+        ylabel="GB/s",  # label name for the y-axis
-    y = torch.rand(N, device='cuda', dtype=torch.float32)
+        plot_name="vector-add-performance",  # name for the plot. Used also as a file name for saving the plot.
-    # Triton provide a do_bench utility function that can be used to benchmark
+        args={}  # values for function arguments not in `x_names` and `y_name`
-    # arbitrary workloads. It supports a `warmup` parameter that is used to stabilize
+    )
-    # GPU clock speeds as well as a `rep` parameter that controls the number of times
+)
-    # the benchmark is repeated. Importantly, we set `clear_l2 = True` to make sure
+def benchmark(size, provider):
-    # that the L2 cache does not contain any element of x before each kernel call when
+    x = torch.rand(size, device='cuda', dtype=torch.float32)
-    # N is small.
+    y = torch.rand(size, device='cuda', dtype=torch.float32)
-    do_bench = lambda fn: gbps(N, triton.testing.do_bench(fn, warmup=10, rep=100, clear_l2=True))
+    if provider == 'torch':
-    triton_bw += [do_bench(lambda: add(x, y))]
+        ms, min_ms, max_ms = triton.testing.do_bench(lambda: x + y)
-    torch_bw += [do_bench(lambda: x + y)]
+    if provider == 'triton':
-# We plot the results as a semi-log
+        ms, min_ms, max_ms = triton.testing.do_bench(lambda: add(x, y))
-plt.semilogx(sizes, triton_bw, label='Triton')
+    gbps = lambda ms: 12 * size / ms * 1e-6
-plt.semilogx(sizes, torch_bw, label='Torch')
+    return gbps(ms), gbps(max_ms), gbps(min_ms)
-plt.legend()
+
-plt.show()
 
 # %%
-# Seems like our simple element-wise operation operates at peak bandwidth. While this is a fairly low bar for a custom GPU programming language, this is a good start before we move to more advanced operations.
+# We can now run the decorated function above. Pass `show_plots=True` to see the plots and/or
+# `save_path='/path/to/results/' to save them to disk along with raw CSV data
+benchmark.run(show_plots=True)

_downloads/d91442ac2982c4e0cc3ab0f43534afbc/02-fused-softmax.py

@@ -179,27 +179,32 @@ print(torch.allclose(y_tri, y_ref))
 # Here we will benchmark our operation as a function of the number of columns in the input matrix -- assuming 4096 rows.
 # We will then compare its performance against (1) :code:`torch.softmax` and (2) the :code:`naive_softmax` defined above.
 
-import matplotlib.pyplot as plt
 
-M = 4096
+@triton.testing.perf_report(
-Ns = [256 * i for i in range(2, 50)]
+    triton.testing.Benchmark(
-tri_bw = []
+        x_names=['N'],  # argument names to use as an x-axis for the plot
-ref_bw = []
+        x_vals=[256 * i for i in range(2, 50)],  # different possible values for `x_name`
-def_bw = []
+        y_name='provider',  # argument name whose value corresponds to a different line in the plot
-for N in Ns:
+        y_vals=['torch', 'triton', 'naive'],  # possible keys for `y_name`
+        y_lines=["Torch", "Triton", 'Naive'],  # label name for the lines
+        ylabel="GB/s",  # label name for the y-axis
+        plot_name="softmax-performance",  # name for the plot. Used also as a file name for saving the plot.
+        args={'M': 4096}  # values for function arguments not in `x_names` and `y_name`
+    )
+)
+def benchmark(M, N, provider):
     x = torch.randn(M, N, device='cuda', dtype=torch.float32)
-    gbps = lambda ms: x.nelement() * x.element_size() * 1e-9 / (ms * 1e-3)
+    if provider == 'torch':
-    do_bench = lambda fn: gbps(triton.testing.do_bench(fn, warmup=10, rep=100, clear_l2=True))
+        ms, min_ms, max_ms = triton.testing.do_bench(lambda: torch.softmax(x, axis=-1))
-    tri_bw += [do_bench(lambda: softmax(x))]
+    if provider == 'triton':
-    ref_bw += [do_bench(lambda: torch.softmax(x, axis=1))]
+        ms, min_ms, max_ms = triton.testing.do_bench(lambda: softmax(x))
-    def_bw += [do_bench(lambda: naive_softmax(x))]
+    if provider == 'naive':
-plt.xlabel('N')
+        ms, min_ms, max_ms = triton.testing.do_bench(lambda: naive_softmax(x))
-plt.ylabel('Bandwidth (GB/s)')
+    gbps = lambda ms: 2 * x.nelement() * x.element_size() * 1e-9 / (ms * 1e-3)
-plt.plot(Ns, tri_bw, label='Triton')
+    return gbps(ms), gbps(max_ms), gbps(min_ms)
-plt.plot(Ns, ref_bw, label='Torch')
+
-plt.plot(Ns, def_bw, label='Naive')
+
-plt.legend()
+benchmark.run(show_plots=True)
-plt.show()
 
 # %%
 # In the above plot, we can see that:

_downloads/f191ee1e78dc52eb5f7cba88f71cef2f/01-vector-add.ipynb

@@ -79,7 +79,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Benchmarking\nWe can now benchmark our custom op for vectors of increasing sizes to get a sense of how it does relative to PyTorch.\n\n"
+        "## Benchmarking\nWe can now benchmark our custom op for vectors of increasing sizes to get a sense of how it does relative to PyTorch.\nTo make things easier, Triton has a set of built-in utilities that allow us to concisely plot the performance of our custom op.\nfor different problem sizes.\n\n"
       ]
     },
     {
@@ -90,14 +90,25 @@
       },
       "outputs": [],
       "source": [
-        "import matplotlib.pyplot as plt\n\n# There are three tensors of 4N bytes each. So the bandwidth of a given kernel\n# is 12N / time_ms * 1e-6 GB/s\ngbps = lambda N, ms: 12 * N / ms * 1e-6\n# We want to benchmark small and large vector alike\nsizes = [2**i for i in range(12, 25, 1)]\ntriton_bw = []\ntorch_bw = []\nfor N in sizes:\n    x = torch.rand(N, device='cuda', dtype=torch.float32)\n    y = torch.rand(N, device='cuda', dtype=torch.float32)\n    # Triton provide a do_bench utility function that can be used to benchmark\n    # arbitrary workloads. It supports a `warmup` parameter that is used to stabilize\n    # GPU clock speeds as well as a `rep` parameter that controls the number of times\n    # the benchmark is repeated. Importantly, we set `clear_l2 = True` to make sure\n    # that the L2 cache does not contain any element of x before each kernel call when\n    # N is small.\n    do_bench = lambda fn: gbps(N, triton.testing.do_bench(fn, warmup=10, rep=100, clear_l2=True))\n    triton_bw += [do_bench(lambda: add(x, y))]\n    torch_bw += [do_bench(lambda: x + y)]\n# We plot the results as a semi-log\nplt.semilogx(sizes, triton_bw, label='Triton')\nplt.semilogx(sizes, torch_bw, label='Torch')\nplt.legend()\nplt.show()"
+        "@triton.testing.perf_report(\n    triton.testing.Benchmark(\n        x_names=['size'],  # argument names to use as an x-axis for the plot\n        x_vals=[2**i for i in range(12, 28, 1)],  # different possible values for `x_name`\n        x_log=True,  # x axis is logarithmic\n        y_name='provider',  # argument name whose value corresponds to a different line in the plot\n        y_vals=['torch', 'triton'],  # possible keys for `y_name`\n        y_lines=[\"Torch\", \"Triton\"],  # label name for the lines\n        ylabel=\"GB/s\",  # label name for the y-axis\n        plot_name=\"vector-add-performance\",  # name for the plot. Used also as a file name for saving the plot.\n        args={}  # values for function arguments not in `x_names` and `y_name`\n    )\n)\ndef benchmark(size, provider):\n    x = torch.rand(size, device='cuda', dtype=torch.float32)\n    y = torch.rand(size, device='cuda', dtype=torch.float32)\n    if provider == 'torch':\n        ms, min_ms, max_ms = triton.testing.do_bench(lambda: x + y)\n    if provider == 'triton':\n        ms, min_ms, max_ms = triton.testing.do_bench(lambda: add(x, y))\n    gbps = lambda ms: 12 * size / ms * 1e-6\n    return gbps(ms), gbps(max_ms), gbps(min_ms)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Seems like our simple element-wise operation operates at peak bandwidth. While this is a fairly low bar for a custom GPU programming language, this is a good start before we move to more advanced operations.\n"
+        "We can now run the decorated function above. Pass `show_plots=True` to see the plots and/or\n`save_path='/path/to/results/' to save them to disk along with raw CSV data\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "benchmark.run(show_plots=True)"
       ]
     }
   ],

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

@@ -200,63 +200,75 @@ Of course, the first thing that we should check is that whether kernel is correc
 
 Seems like we're good to go!
 
-.. GENERATED FROM PYTHON SOURCE LINES 147-150
+.. GENERATED FROM PYTHON SOURCE LINES 147-152
 
 Benchmarking
 --------------------------
 We can now benchmark our custom op for vectors of increasing sizes to get a sense of how it does relative to PyTorch.
+To make things easier, Triton has a set of built-in utilities that allow us to concisely plot the performance of our custom op.
+for different problem sizes.
 
-.. GENERATED FROM PYTHON SOURCE LINES 150-178
+.. GENERATED FROM PYTHON SOURCE LINES 152-178
 
 .. code-block:: default
 
 
-    import matplotlib.pyplot as plt
 
-    # There are three tensors of 4N bytes each. So the bandwidth of a given kernel
+    @triton.testing.perf_report(
-    # is 12N / time_ms * 1e-6 GB/s
+        triton.testing.Benchmark(
-    gbps = lambda N, ms: 12 * N / ms * 1e-6
+            x_names=['size'],  # argument names to use as an x-axis for the plot
-    # We want to benchmark small and large vector alike
+            x_vals=[2**i for i in range(12, 28, 1)],  # different possible values for `x_name`
-    sizes = [2**i for i in range(12, 25, 1)]
+            x_log=True,  # x axis is logarithmic
-    triton_bw = []
+            y_name='provider',  # argument name whose value corresponds to a different line in the plot
-    torch_bw = []
+            y_vals=['torch', 'triton'],  # possible keys for `y_name`
-    for N in sizes:
+            y_lines=["Torch", "Triton"],  # label name for the lines
-        x = torch.rand(N, device='cuda', dtype=torch.float32)
+            ylabel="GB/s",  # label name for the y-axis
-        y = torch.rand(N, device='cuda', dtype=torch.float32)
+            plot_name="vector-add-performance",  # name for the plot. Used also as a file name for saving the plot.
-        # Triton provide a do_bench utility function that can be used to benchmark
+            args={}  # values for function arguments not in `x_names` and `y_name`
-        # arbitrary workloads. It supports a `warmup` parameter that is used to stabilize
+        )
-        # GPU clock speeds as well as a `rep` parameter that controls the number of times
+    )
-        # the benchmark is repeated. Importantly, we set `clear_l2 = True` to make sure
+    def benchmark(size, provider):
-        # that the L2 cache does not contain any element of x before each kernel call when
+        x = torch.rand(size, device='cuda', dtype=torch.float32)
-        # N is small.
+        y = torch.rand(size, device='cuda', dtype=torch.float32)
-        do_bench = lambda fn: gbps(N, triton.testing.do_bench(fn, warmup=10, rep=100, clear_l2=True))
+        if provider == 'torch':
-        triton_bw += [do_bench(lambda: add(x, y))]
+            ms, min_ms, max_ms = triton.testing.do_bench(lambda: x + y)
-        torch_bw += [do_bench(lambda: x + y)]
+        if provider == 'triton':
-    # We plot the results as a semi-log
+            ms, min_ms, max_ms = triton.testing.do_bench(lambda: add(x, y))
-    plt.semilogx(sizes, triton_bw, label='Triton')
+        gbps = lambda ms: 12 * size / ms * 1e-6
-    plt.semilogx(sizes, torch_bw, label='Torch')
+        return gbps(ms), gbps(max_ms), gbps(min_ms)
-    plt.legend()
-    plt.show()
 
 
 
 
+
+
+
+
+
+.. GENERATED FROM PYTHON SOURCE LINES 179-181
+
+We can now run the decorated function above. Pass `show_plots=True` to see the plots and/or
+`save_path='/path/to/results/' to save them to disk along with raw CSV data
+
+.. GENERATED FROM PYTHON SOURCE LINES 181-181
+
+.. code-block:: default
+
+    benchmark.run(show_plots=True)
+
+
 .. image:: /getting-started/tutorials/images/sphx_glr_01-vector-add_001.png
-    :alt: 01 vector add
+    :alt: vector-add-performance
     :class: sphx-glr-single-img
 
 
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 179-179
-
-Seems like our simple element-wise operation operates at peak bandwidth. While this is a fairly low bar for a custom GPU programming language, this is a good start before we move to more advanced operations.
-
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  4.784 seconds)
+   **Total running time of the script:** ( 0 minutes  5.768 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

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

@@ -250,45 +250,50 @@ Benchmarking
 Here we will benchmark our operation as a function of the number of columns in the input matrix -- assuming 4096 rows.
 We will then compare its performance against (1) :code:`torch.softmax` and (2) the :code:`naive_softmax` defined above.
 
-.. GENERATED FROM PYTHON SOURCE LINES 181-204
+.. GENERATED FROM PYTHON SOURCE LINES 181-209
 
 .. code-block:: default
 
 
-    import matplotlib.pyplot as plt
 
-    M = 4096
+    @triton.testing.perf_report(
-    Ns = [256 * i for i in range(2, 50)]
+        triton.testing.Benchmark(
-    tri_bw = []
+            x_names=['N'],  # argument names to use as an x-axis for the plot
-    ref_bw = []
+            x_vals=[256 * i for i in range(2, 50)],  # different possible values for `x_name`
-    def_bw = []
+            y_name='provider',  # argument name whose value corresponds to a different line in the plot
-    for N in Ns:
+            y_vals=['torch', 'triton', 'naive'],  # possible keys for `y_name`
+            y_lines=["Torch", "Triton", 'Naive'],  # label name for the lines
+            ylabel="GB/s",  # label name for the y-axis
+            plot_name="softmax-performance",  # name for the plot. Used also as a file name for saving the plot.
+            args={'M': 4096}  # values for function arguments not in `x_names` and `y_name`
+        )
+    )
+    def benchmark(M, N, provider):
         x = torch.randn(M, N, device='cuda', dtype=torch.float32)
-        gbps = lambda ms: x.nelement() * x.element_size() * 1e-9 / (ms * 1e-3)
+        if provider == 'torch':
-        do_bench = lambda fn: gbps(triton.testing.do_bench(fn, warmup=10, rep=100, clear_l2=True))
+            ms, min_ms, max_ms = triton.testing.do_bench(lambda: torch.softmax(x, axis=-1))
-        tri_bw += [do_bench(lambda: softmax(x))]
+        if provider == 'triton':
-        ref_bw += [do_bench(lambda: torch.softmax(x, axis=1))]
+            ms, min_ms, max_ms = triton.testing.do_bench(lambda: softmax(x))
-        def_bw += [do_bench(lambda: naive_softmax(x))]
+        if provider == 'naive':
-    plt.xlabel('N')
+            ms, min_ms, max_ms = triton.testing.do_bench(lambda: naive_softmax(x))
-    plt.ylabel('Bandwidth (GB/s)')
+        gbps = lambda ms: 2 * x.nelement() * x.element_size() * 1e-9 / (ms * 1e-3)
-    plt.plot(Ns, tri_bw, label='Triton')
+        return gbps(ms), gbps(max_ms), gbps(min_ms)
-    plt.plot(Ns, ref_bw, label='Torch')
+
-    plt.plot(Ns, def_bw, label='Naive')
+
-    plt.legend()
+    benchmark.run(show_plots=True)
-    plt.show()
 
 
 
 
 .. image:: /getting-started/tutorials/images/sphx_glr_02-fused-softmax_001.png
-    :alt: 02 fused softmax
+    :alt: softmax-performance
     :class: sphx-glr-single-img
 
 
 
 
 
-.. GENERATED FROM PYTHON SOURCE LINES 205-210
+.. GENERATED FROM PYTHON SOURCE LINES 210-215
 
 In the above plot, we can see that:
 
@@ -300,7 +305,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  33.773 seconds)
+   **Total running time of the script:** ( 0 minutes  21.653 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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

@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:33.773** total execution time for **getting-started_tutorials** files:
+**00:27.420** total execution time for **getting-started_tutorials** files:
 
 +-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 00:33.773 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 00:21.653 | 0.0 MB |
 +-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)       | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)       | 00:05.768 | 0.0 MB |
 +-----------------------------------------------------------------------------------------+-----------+--------+

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

@@ -322,38 +322,40 @@ The maximum difference between torch and triton is 0.0
 </div>
 <div class="section" id="benchmarking">
 <h2>Benchmarking<a class="headerlink" href="#benchmarking" title="Permalink to this headline">¶</a></h2>
-<p>We can now benchmark our custom op for vectors of increasing sizes to get a sense of how it does relative to PyTorch.</p>
+<p>We can now benchmark our custom op for vectors of increasing sizes to get a sense of how it does relative to PyTorch.
-<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
+To make things easier, Triton has a set of built-in utilities that allow us to concisely plot the performance of our custom op.
-
+for different problem sizes.</p>
-<span class="c1"># There are three tensors of 4N bytes each. So the bandwidth of a given kernel</span>
+<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nd">@triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">perf_report</span><span class="p">(</span>
-<span class="c1"># is 12N / time_ms * 1e-6 GB/s</span>
+    <span class="n">triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">Benchmark</span><span class="p">(</span>
-<span class="n">gbps</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">N</span><span class="p">,</span> <span class="n">ms</span><span class="p">:</span> <span class="mi">12</span> <span class="o">*</span> <span class="n">N</span> <span class="o">/</span> <span class="n">ms</span> <span class="o">*</span> <span class="mf">1e-6</span>
+        <span class="n">x_names</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;size&#39;</span><span class="p">],</span>  <span class="c1"># argument names to use as an x-axis for the plot</span>
-<span class="c1"># We want to benchmark small and large vector alike</span>
+        <span class="n">x_vals</span><span class="o">=</span><span class="p">[</span><span class="mi">2</span><span class="o">**</span><span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">12</span><span class="p">,</span> <span class="mi">28</span><span class="p">,</span> <span class="mi">1</span><span class="p">)],</span>  <span class="c1"># different possible values for `x_name`</span>
-<span class="n">sizes</span> <span class="o">=</span> <span class="p">[</span><span class="mi">2</span><span class="o">**</span><span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">12</span><span class="p">,</span> <span class="mi">25</span><span class="p">,</span> <span class="mi">1</span><span class="p">)]</span>
+        <span class="n">x_log</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>  <span class="c1"># x axis is logarithmic</span>
-<span class="n">triton_bw</span> <span class="o">=</span> <span class="p">[]</span>
+        <span class="n">y_name</span><span class="o">=</span><span class="s1">&#39;provider&#39;</span><span class="p">,</span>  <span class="c1"># argument name whose value corresponds to a different line in the plot</span>
-<span class="n">torch_bw</span> <span class="o">=</span> <span class="p">[]</span>
+        <span class="n">y_vals</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;torch&#39;</span><span class="p">,</span> <span class="s1">&#39;triton&#39;</span><span class="p">],</span>  <span class="c1"># possible keys for `y_name`</span>
-<span class="k">for</span> <span class="n">N</span> <span class="ow">in</span> <span class="n">sizes</span><span class="p">:</span>
+        <span class="n">y_lines</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;Torch&quot;</span><span class="p">,</span> <span class="s2">&quot;Triton&quot;</span><span class="p">],</span>  <span class="c1"># label name for the lines</span>
-    <span class="n">x</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s1">&#39;cuda&#39;</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
+        <span class="n">ylabel</span><span class="o">=</span><span class="s2">&quot;GB/s&quot;</span><span class="p">,</span>  <span class="c1"># label name for the y-axis</span>
-    <span class="n">y</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s1">&#39;cuda&#39;</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
+        <span class="n">plot_name</span><span class="o">=</span><span class="s2">&quot;vector-add-performance&quot;</span><span class="p">,</span>  <span class="c1"># name for the plot. Used also as a file name for saving the plot.</span>
-    <span class="c1"># Triton provide a do_bench utility function that can be used to benchmark</span>
+        <span class="n">args</span><span class="o">=</span><span class="p">{}</span>  <span class="c1"># values for function arguments not in `x_names` and `y_name`</span>
-    <span class="c1"># arbitrary workloads. It supports a `warmup` parameter that is used to stabilize</span>
+    <span class="p">)</span>
-    <span class="c1"># GPU clock speeds as well as a `rep` parameter that controls the number of times</span>
+<span class="p">)</span>
-    <span class="c1"># the benchmark is repeated. Importantly, we set `clear_l2 = True` to make sure</span>
+<span class="k">def</span> <span class="nf">benchmark</span><span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="n">provider</span><span class="p">):</span>
-    <span class="c1"># that the L2 cache does not contain any element of x before each kernel call when</span>
+    <span class="n">x</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s1">&#39;cuda&#39;</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
-    <span class="c1"># N is small.</span>
+    <span class="n">y</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">rand</span><span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s1">&#39;cuda&#39;</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
-    <span class="n">do_bench</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">fn</span><span class="p">:</span> <span class="n">gbps</span><span class="p">(</span><span class="n">N</span><span class="p">,</span> <span class="n">triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">do_bench</span><span class="p">(</span><span class="n">fn</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">rep</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">clear_l2</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span>
+    <span class="k">if</span> <span class="n">provider</span> <span class="o">==</span> <span class="s1">&#39;torch&#39;</span><span class="p">:</span>
-    <span class="n">triton_bw</span> <span class="o">+=</span> <span class="p">[</span><span class="n">do_bench</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">add</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">))]</span>
+        <span class="n">ms</span><span class="p">,</span> <span class="n">min_ms</span><span class="p">,</span> <span class="n">max_ms</span> <span class="o">=</span> <span class="n">triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">do_bench</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">x</span> <span class="o">+</span> <span class="n">y</span><span class="p">)</span>
-    <span class="n">torch_bw</span> <span class="o">+=</span> <span class="p">[</span><span class="n">do_bench</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">x</span> <span class="o">+</span> <span class="n">y</span><span class="p">)]</span>
+    <span class="k">if</span> <span class="n">provider</span> <span class="o">==</span> <span class="s1">&#39;triton&#39;</span><span class="p">:</span>
-<span class="c1"># We plot the results as a semi-log</span>
+        <span class="n">ms</span><span class="p">,</span> <span class="n">min_ms</span><span class="p">,</span> <span class="n">max_ms</span> <span class="o">=</span> <span class="n">triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">do_bench</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">add</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">))</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">semilogx</span><span class="p">(</span><span class="n">sizes</span><span class="p">,</span> <span class="n">triton_bw</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">&#39;Triton&#39;</span><span class="p">)</span>
+    <span class="n">gbps</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">ms</span><span class="p">:</span> <span class="mi">12</span> <span class="o">*</span> <span class="n">size</span> <span class="o">/</span> <span class="n">ms</span> <span class="o">*</span> <span class="mf">1e-6</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">semilogx</span><span class="p">(</span><span class="n">sizes</span><span class="p">,</span> <span class="n">torch_bw</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">&#39;Torch&#39;</span><span class="p">)</span>
+    <span class="k">return</span> <span class="n">gbps</span><span class="p">(</span><span class="n">ms</span><span class="p">),</span> <span class="n">gbps</span><span class="p">(</span><span class="n">max_ms</span><span class="p">),</span> <span class="n">gbps</span><span class="p">(</span><span class="n">min_ms</span><span class="p">)</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">legend</span><span class="p">()</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
-<img alt="01 vector add" class="sphx-glr-single-img" src="../../_images/sphx_glr_01-vector-add_001.png" />
+<p>We can now run the decorated function above. Pass <cite>show_plots=True</cite> to see the plots and/or
-<p>Seems like our simple element-wise operation operates at peak bandwidth. While this is a fairly low bar for a custom GPU programming language, this is a good start before we move to more advanced operations.</p>
+<a href="#id1"><span class="problematic" id="id2">`</span></a>save_path=’/path/to/results/’ to save them to disk along with raw CSV data</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  4.784 seconds)</p>
+<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">benchmark</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">show_plots</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+</pre></div>
+</div>
+<img alt="vector-add-performance" class="sphx-glr-single-img" src="../../_images/sphx_glr_01-vector-add_001.png" />
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  5.768 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

@@ -349,30 +349,34 @@ This will allow us to verify that our padding mechanism works.</p>
 <h2>Benchmarking<a class="headerlink" href="#benchmarking" title="Permalink to this headline">¶</a></h2>
 <p>Here we will benchmark our operation as a function of the number of columns in the input matrix – assuming 4096 rows.
 We will then compare its performance against (1) <code class="code docutils literal notranslate"><span class="pre">torch.softmax</span></code> and (2) the <code class="code docutils literal notranslate"><span class="pre">naive_softmax</span></code> defined above.</p>
-<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
+<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nd">@triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">perf_report</span><span class="p">(</span>
-
+    <span class="n">triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">Benchmark</span><span class="p">(</span>
-<span class="n">M</span> <span class="o">=</span> <span class="mi">4096</span>
+        <span class="n">x_names</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;N&#39;</span><span class="p">],</span>  <span class="c1"># argument names to use as an x-axis for the plot</span>
-<span class="n">Ns</span> <span class="o">=</span> <span class="p">[</span><span class="mi">256</span> <span class="o">*</span> <span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">50</span><span class="p">)]</span>
+        <span class="n">x_vals</span><span class="o">=</span><span class="p">[</span><span class="mi">256</span> <span class="o">*</span> <span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">50</span><span class="p">)],</span>  <span class="c1"># different possible values for `x_name`</span>
-<span class="n">tri_bw</span> <span class="o">=</span> <span class="p">[]</span>
+        <span class="n">y_name</span><span class="o">=</span><span class="s1">&#39;provider&#39;</span><span class="p">,</span>  <span class="c1"># argument name whose value corresponds to a different line in the plot</span>
-<span class="n">ref_bw</span> <span class="o">=</span> <span class="p">[]</span>
+        <span class="n">y_vals</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;torch&#39;</span><span class="p">,</span> <span class="s1">&#39;triton&#39;</span><span class="p">,</span> <span class="s1">&#39;naive&#39;</span><span class="p">],</span>  <span class="c1"># possible keys for `y_name`</span>
-<span class="n">def_bw</span> <span class="o">=</span> <span class="p">[]</span>
+        <span class="n">y_lines</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;Torch&quot;</span><span class="p">,</span> <span class="s2">&quot;Triton&quot;</span><span class="p">,</span> <span class="s1">&#39;Naive&#39;</span><span class="p">],</span>  <span class="c1"># label name for the lines</span>
-<span class="k">for</span> <span class="n">N</span> <span class="ow">in</span> <span class="n">Ns</span><span class="p">:</span>
+        <span class="n">ylabel</span><span class="o">=</span><span class="s2">&quot;GB/s&quot;</span><span class="p">,</span>  <span class="c1"># label name for the y-axis</span>
+        <span class="n">plot_name</span><span class="o">=</span><span class="s2">&quot;softmax-performance&quot;</span><span class="p">,</span>  <span class="c1"># name for the plot. Used also as a file name for saving the plot.</span>
+        <span class="n">args</span><span class="o">=</span><span class="p">{</span><span class="s1">&#39;M&#39;</span><span class="p">:</span> <span class="mi">4096</span><span class="p">}</span>  <span class="c1"># values for function arguments not in `x_names` and `y_name`</span>
+    <span class="p">)</span>
+<span class="p">)</span>
+<span class="k">def</span> <span class="nf">benchmark</span><span class="p">(</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><span class="p">,</span> <span class="n">provider</span><span class="p">):</span>
     <span class="n">x</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="n">M</span><span class="p">,</span> <span class="n">N</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s1">&#39;cuda&#39;</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
-    <span class="n">gbps</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">ms</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">nelement</span><span class="p">()</span> <span class="o">*</span> <span class="n">x</span><span class="o">.</span><span class="n">element_size</span><span class="p">()</span> <span class="o">*</span> <span class="mf">1e-9</span> <span class="o">/</span> <span class="p">(</span><span class="n">ms</span> <span class="o">*</span> <span class="mf">1e-3</span><span class="p">)</span>
+    <span class="k">if</span> <span class="n">provider</span> <span class="o">==</span> <span class="s1">&#39;torch&#39;</span><span class="p">:</span>
-    <span class="n">do_bench</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">fn</span><span class="p">:</span> <span class="n">gbps</span><span class="p">(</span><span class="n">triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">do_bench</span><span class="p">(</span><span class="n">fn</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">rep</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">clear_l2</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span>
+        <span class="n">ms</span><span class="p">,</span> <span class="n">min_ms</span><span class="p">,</span> <span class="n">max_ms</span> <span class="o">=</span> <span class="n">triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">do_bench</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">softmax</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">))</span>
-    <span class="n">tri_bw</span> <span class="o">+=</span> <span class="p">[</span><span class="n">do_bench</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">softmax</span><span class="p">(</span><span class="n">x</span><span class="p">))]</span>
+    <span class="k">if</span> <span class="n">provider</span> <span class="o">==</span> <span class="s1">&#39;triton&#39;</span><span class="p">:</span>
-    <span class="n">ref_bw</span> <span class="o">+=</span> <span class="p">[</span><span class="n">do_bench</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">softmax</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">))]</span>
+        <span class="n">ms</span><span class="p">,</span> <span class="n">min_ms</span><span class="p">,</span> <span class="n">max_ms</span> <span class="o">=</span> <span class="n">triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">do_bench</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">softmax</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
-    <span class="n">def_bw</span> <span class="o">+=</span> <span class="p">[</span><span class="n">do_bench</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">naive_softmax</span><span class="p">(</span><span class="n">x</span><span class="p">))]</span>
+    <span class="k">if</span> <span class="n">provider</span> <span class="o">==</span> <span class="s1">&#39;naive&#39;</span><span class="p">:</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">xlabel</span><span class="p">(</span><span class="s1">&#39;N&#39;</span><span class="p">)</span>
+        <span class="n">ms</span><span class="p">,</span> <span class="n">min_ms</span><span class="p">,</span> <span class="n">max_ms</span> <span class="o">=</span> <span class="n">triton</span><span class="o">.</span><span class="n">testing</span><span class="o">.</span><span class="n">do_bench</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">naive_softmax</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">ylabel</span><span class="p">(</span><span class="s1">&#39;Bandwidth (GB/s)&#39;</span><span class="p">)</span>
+    <span class="n">gbps</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">ms</span><span class="p">:</span> <span class="mi">2</span> <span class="o">*</span> <span class="n">x</span><span class="o">.</span><span class="n">nelement</span><span class="p">()</span> <span class="o">*</span> <span class="n">x</span><span class="o">.</span><span class="n">element_size</span><span class="p">()</span> <span class="o">*</span> <span class="mf">1e-9</span> <span class="o">/</span> <span class="p">(</span><span class="n">ms</span> <span class="o">*</span> <span class="mf">1e-3</span><span class="p">)</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">Ns</span><span class="p">,</span> <span class="n">tri_bw</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">&#39;Triton&#39;</span><span class="p">)</span>
+    <span class="k">return</span> <span class="n">gbps</span><span class="p">(</span><span class="n">ms</span><span class="p">),</span> <span class="n">gbps</span><span class="p">(</span><span class="n">max_ms</span><span class="p">),</span> <span class="n">gbps</span><span class="p">(</span><span class="n">min_ms</span><span class="p">)</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">Ns</span><span class="p">,</span> <span class="n">ref_bw</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">&#39;Torch&#39;</span><span class="p">)</span>
+
-<span class="n">plt</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">Ns</span><span class="p">,</span> <span class="n">def_bw</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">&#39;Naive&#39;</span><span class="p">)</span>
+
-<span class="n">plt</span><span class="o">.</span><span class="n">legend</span><span class="p">()</span>
+<span class="n">benchmark</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">show_plots</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
 </pre></div>
 </div>
-<img alt="02 fused softmax" class="sphx-glr-single-img" src="../../_images/sphx_glr_02-fused-softmax_001.png" />
+<img alt="softmax-performance" class="sphx-glr-single-img" src="../../_images/sphx_glr_02-fused-softmax_001.png" />
 <p>In the above plot, we can see that:</p>
 <blockquote>
 <div><ul class="simple">
@@ -382,7 +386,7 @@ 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> ( 0 minutes  33.773 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  21.653 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/sg_execution_times.html

@@ -160,7 +160,7 @@
             
   <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>00:33.773</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>00:27.420</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 82%" />
@@ -169,11 +169,11 @@
 </colgroup>
 <tbody>
 <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>00:33.773</p></td>
+<td><p>00:21.653</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>00:00.000</p></td>
+<td><p>00:05.768</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>