diff --git a/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip b/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip index be1666a0e..a7fd8212d 100644 Binary files a/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip and b/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip differ diff --git a/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip b/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip index d29225c8f..79f84e7f6 100644 Binary files a/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip and b/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip differ diff --git a/_images/sphx_glr_01-vector-add_001.png b/_images/sphx_glr_01-vector-add_001.png index fb88dfc21..a23b004e0 100644 Binary files a/_images/sphx_glr_01-vector-add_001.png and b/_images/sphx_glr_01-vector-add_001.png differ diff --git a/_images/sphx_glr_01-vector-add_thumb.png b/_images/sphx_glr_01-vector-add_thumb.png index c9fb5db49..0b63763c9 100644 Binary files a/_images/sphx_glr_01-vector-add_thumb.png and b/_images/sphx_glr_01-vector-add_thumb.png differ diff --git a/_images/sphx_glr_02-fused-softmax_001.png b/_images/sphx_glr_02-fused-softmax_001.png index bc8c6024c..93ddee2d3 100644 Binary files a/_images/sphx_glr_02-fused-softmax_001.png and b/_images/sphx_glr_02-fused-softmax_001.png differ diff --git a/_images/sphx_glr_02-fused-softmax_thumb.png b/_images/sphx_glr_02-fused-softmax_thumb.png index 385a7aba5..c76e7560a 100644 Binary files a/_images/sphx_glr_02-fused-softmax_thumb.png and b/_images/sphx_glr_02-fused-softmax_thumb.png differ diff --git a/_images/sphx_glr_03-matrix-multiplication_001.png b/_images/sphx_glr_03-matrix-multiplication_001.png index d71a197f9..84979b1b0 100644 Binary files a/_images/sphx_glr_03-matrix-multiplication_001.png and b/_images/sphx_glr_03-matrix-multiplication_001.png differ diff --git a/_images/sphx_glr_03-matrix-multiplication_thumb.png b/_images/sphx_glr_03-matrix-multiplication_thumb.png index 4116a6a8e..8acc66163 100644 Binary files a/_images/sphx_glr_03-matrix-multiplication_thumb.png and b/_images/sphx_glr_03-matrix-multiplication_thumb.png differ diff --git a/_sources/getting-started/tutorials/01-vector-add.rst.txt b/_sources/getting-started/tutorials/01-vector-add.rst.txt index 39abc38fc..aad574e3d 100644 --- a/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -232,12 +232,12 @@ We can now run the decorated function above. Pass `print_data=True` to see the p vector-add-performance: size Triton Torch 0 4096.0 9.600000 9.600000 - 1 8192.0 19.200000 15.999999 + 1 8192.0 15.999999 19.200000 2 16384.0 38.400001 38.400001 3 32768.0 76.800002 76.800002 4 65536.0 127.999995 127.999995 5 131072.0 219.428568 219.428568 - 6 262144.0 384.000001 341.333321 + 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 @@ -254,7 +254,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 0 minutes 11.086 seconds) + **Total running time of the script:** ( 0 minutes 11.024 seconds) .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py: diff --git a/_sources/getting-started/tutorials/02-fused-softmax.rst.txt b/_sources/getting-started/tutorials/02-fused-softmax.rst.txt index 3725f5459..8b99f7293 100644 --- a/_sources/getting-started/tutorials/02-fused-softmax.rst.txt +++ b/_sources/getting-started/tutorials/02-fused-softmax.rst.txt @@ -301,16 +301,16 @@ 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 186.181817 - 1 384.0 585.142862 585.142862 153.600004 - 2 512.0 630.153853 606.814814 154.566038 + 1 384.0 585.142862 558.545450 151.703707 + 2 512.0 630.153853 585.142849 154.566038 3 640.0 682.666684 640.000002 160.000000 4 768.0 702.171410 664.216187 163.839992 .. ... ... ... ... - 93 12160.0 812.359066 405.755985 199.140227 - 94 12288.0 812.429770 415.661740 199.399583 - 95 12416.0 810.840807 411.722274 199.054102 - 96 12544.0 810.925276 412.546756 199.308841 - 97 12672.0 811.007961 412.097543 199.362843 + 93 12160.0 812.359066 406.179533 199.038365 + 94 12288.0 812.429770 415.222812 199.399583 + 95 12416.0 810.840807 412.149375 198.854847 + 96 12544.0 809.290334 412.971190 199.209928 + 97 12672.0 809.389265 412.097543 199.362843 [98 rows x 4 columns] @@ -328,7 +328,7 @@ In the above plot, we can see that: .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 1 minutes 12.683 seconds) + **Total running time of the script:** ( 1 minutes 12.613 seconds) .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py: diff --git a/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt b/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt index d264afbd6..a1570acc4 100644 --- a/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt +++ b/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt @@ -463,37 +463,37 @@ 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 2.730667 ... 3.276800 2.978909 - 2 384.0 7.372800 ... 8.507077 7.899428 - 3 512.0 14.563555 ... 15.420235 15.420235 + 1 256.0 2.978909 ... 2.978909 2.978909 + 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 ... 40.140799 39.025776 + 6 896.0 37.971025 ... 40.140799 39.025776 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 ... 64.902096 64.138541 - 11 1536.0 79.526831 ... 76.106321 75.296679 + 9 1280.0 51.200001 ... 56.888887 56.109587 + 10 1408.0 64.138541 ... 64.902096 64.902096 + 11 1536.0 80.430545 ... 76.933564 76.106321 12 1664.0 63.372618 ... 62.492442 62.492442 13 1792.0 72.983276 ... 70.246402 69.810085 - 14 1920.0 66.782607 ... 68.435645 69.467336 - 15 2048.0 73.262953 ... 75.234154 68.191406 - 16 2176.0 82.813365 ... 81.143743 77.398646 - 17 2304.0 68.056616 ... 73.501144 73.051599 - 18 2432.0 71.125224 ... 80.731218 80.499895 - 19 2560.0 77.649287 ... 77.283019 76.382283 - 20 2688.0 81.752274 ... 82.642823 81.752274 - 21 2816.0 83.873477 ... 79.298560 79.154642 - 22 2944.0 81.431424 ... 79.993627 76.907458 - 23 3072.0 81.825298 ... 83.514905 82.782312 - 24 3200.0 80.604535 ... 85.106381 89.510493 - 25 3328.0 83.905938 ... 82.558825 81.622783 - 26 3456.0 81.849303 ... 84.244062 84.244062 - 27 3584.0 87.211821 ... 90.458141 92.887804 - 28 3712.0 85.601834 ... 88.955779 88.797643 - 29 3840.0 84.874902 ... 83.214447 85.136259 - 30 3968.0 88.938731 ... 88.487262 87.723894 - 31 4096.0 93.727466 ... 88.709668 88.475759 + 14 1920.0 69.467336 ... 70.892307 70.530615 + 15 2048.0 73.908442 ... 75.234154 74.898285 + 16 2176.0 83.500614 ... 80.817862 80.173899 + 17 2304.0 68.446623 ... 73.501144 73.051599 + 18 2432.0 71.125224 ... 80.499895 79.587714 + 19 2560.0 77.833728 ... 77.283019 76.740048 + 20 2688.0 84.108772 ... 83.552988 84.108772 + 21 2816.0 81.674548 ... 77.882512 79.733474 + 22 2944.0 81.832567 ... 78.235527 77.990663 + 23 3072.0 81.121923 ... 83.761985 80.544956 + 24 3200.0 84.768213 ... 89.635851 89.635851 + 25 3328.0 79.812967 ... 84.200347 87.580655 + 26 3456.0 81.189898 ... 84.420490 85.404201 + 27 3584.0 86.707226 ... 95.047985 90.549237 + 28 3712.0 84.159518 ... 84.301560 82.423549 + 29 3840.0 83.655065 ... 87.562949 87.493673 + 30 3968.0 93.076994 ... 88.040360 87.913500 + 31 4096.0 93.596744 ... 86.816123 83.571059 [32 rows x 5 columns] @@ -503,7 +503,7 @@ 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 9.474 seconds) + **Total running time of the script:** ( 2 minutes 2.006 seconds) .. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py: diff --git a/_sources/getting-started/tutorials/sg_execution_times.rst.txt b/_sources/getting-started/tutorials/sg_execution_times.rst.txt index 9f9f76feb..9426fe390 100644 --- a/_sources/getting-started/tutorials/sg_execution_times.rst.txt +++ b/_sources/getting-started/tutorials/sg_execution_times.rst.txt @@ -5,12 +5,12 @@ Computation times ================= -**03:33.244** total execution time for **getting-started_tutorials** files: +**03:25.643** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 02:09.474 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 02:02.006 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 01:12.683 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 01:12.613 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 00:11.086 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 00:11.024 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/getting-started/tutorials/01-vector-add.html b/getting-started/tutorials/01-vector-add.html index fd3f29266..d85ee463c 100644 --- a/getting-started/tutorials/01-vector-add.html +++ b/getting-started/tutorials/01-vector-add.html @@ -320,12 +320,12 @@ for different problem sizes.
vector-add-performance:
size Triton Torch
0 4096.0 9.600000 9.600000
-1 8192.0 19.200000 15.999999
+1 8192.0 15.999999 19.200000
2 16384.0 38.400001 38.400001
3 32768.0 76.800002 76.800002
4 65536.0 127.999995 127.999995
5 131072.0 219.428568 219.428568
-6 262144.0 384.000001 341.333321
+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
@@ -337,7 +337,7 @@ for different problem sizes.
15 134217728.0 851.577704 850.656574
Total running time of the script: ( 0 minutes 11.086 seconds)
+Total running time of the script: ( 0 minutes 11.024 seconds)