diff --git a/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip b/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip index ee4ec089f..f534b81d1 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 8ccde5d2a..a993026c2 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 b5835159f..a6710a55f 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 598456739..04b59a7e4 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 681b5e657..351071914 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 c90c8669f..4b36de9bd 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 d49f278c7..68310cbe6 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 7fb5aca1e..f214a566a 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 da55befe2..b852d5f0e 100644 --- a/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -216,10 +216,10 @@ We can now run the decorated function above. Pass `show_plots=True` to see the p vector-add-performance: size Triton Torch - 0 4096.0 8.000000 9.600000 + 0 4096.0 9.540372 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 384.000001 @@ -239,7 +239,7 @@ We can now run the decorated function above. Pass `show_plots=True` to see the p .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 0 minutes 10.970 seconds) + **Total running time of the script:** ( 0 minutes 11.008 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 2e79d68b3..96f725a7f 100644 --- a/_sources/getting-started/tutorials/02-fused-softmax.rst.txt +++ b/_sources/getting-started/tutorials/02-fused-softmax.rst.txt @@ -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 264.258068 1 384.0 585.142862 585.142862 267.130429 2 512.0 630.153853 606.814814 264.258068 - 3 640.0 682.666684 640.000002 269.473696 + 3 640.0 682.666684 640.000002 265.974036 4 768.0 702.171410 664.216187 273.066663 .. ... ... ... ... - 93 12160.0 812.359066 405.755985 329.483481 + 93 12160.0 812.359066 406.179533 329.483481 94 12288.0 812.429770 415.661740 329.602681 - 95 12416.0 810.840807 411.722274 329.173158 + 95 12416.0 810.840807 412.149375 328.900662 96 12544.0 810.925276 412.971190 329.292871 - 97 12672.0 811.007961 412.097543 329.142870 + 97 12672.0 811.007961 412.516771 329.142870 [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 8.170 seconds) + **Total running time of the script:** ( 1 minutes 8.191 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 7d41e3168..2d6335de7 100644 --- a/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt +++ b/_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 ... 3.276800 3.276800 + 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 ... 23.272727 23.272727 + 3 512.0 14.563555 ... 15.420235 15.420235 + 4 640.0 22.260869 ... 24.380953 24.380953 5 768.0 32.768000 ... 34.028308 34.028308 - 6 896.0 37.971025 ... 39.025776 37.971025 - 7 1024.0 51.150050 ... 52.428801 52.428801 + 6 896.0 39.025776 ... 39.025776 39.025776 + 7 1024.0 49.932191 ... 52.428801 52.428801 8 1152.0 44.566925 ... 45.938215 45.938215 9 1280.0 51.200001 ... 56.109587 56.109587 - 10 1408.0 64.138541 ... 64.902096 58.621246 - 11 1536.0 77.778988 ... 76.106321 75.296679 + 10 1408.0 64.138541 ... 65.684049 58.621246 + 11 1536.0 79.526831 ... 75.296679 75.296679 12 1664.0 62.929456 ... 61.636381 61.636381 - 13 1792.0 72.983276 ... 68.953520 68.533074 - 14 1920.0 69.120002 ... 69.467336 69.120002 - 15 2048.0 73.584279 ... 75.573044 74.898285 - 16 2176.0 82.137338 ... 80.173899 78.916269 - 17 2304.0 68.446623 ... 73.275679 72.828879 - 18 2432.0 71.305746 ... 80.041209 79.362895 - 19 2560.0 78.019048 ... 76.920185 76.382283 - 20 2688.0 81.928846 ... 80.708630 83.369354 - 21 2816.0 82.446516 ... 78.868366 78.584162 - 22 2944.0 82.102191 ... 79.356738 78.854483 - 23 3072.0 81.121923 ... 80.544956 82.301023 - 24 3200.0 84.432717 ... 89.887639 87.431696 - 25 3328.0 81.622783 ... 85.297742 86.528001 - 26 3456.0 79.823334 ... 86.134151 81.683457 - 27 3584.0 85.797134 ... 96.063450 87.808000 - 28 3712.0 85.163978 ... 83.736248 81.480261 - 29 3840.0 83.655065 ... 82.716526 84.228485 - 30 3968.0 89.003603 ... 82.337339 80.017334 - 31 4096.0 93.271527 ... 90.443212 87.324485 + 13 1792.0 72.983276 ... 68.533074 68.533074 + 14 1920.0 66.461539 ... 67.106797 69.467336 + 15 2048.0 73.584279 ... 75.573044 75.573044 + 16 2176.0 81.472263 ... 78.608000 80.173899 + 17 2304.0 68.446623 ... 72.387489 72.607513 + 18 2432.0 71.125224 ... 81.197876 81.433227 + 19 2560.0 78.019048 ... 75.676673 76.920185 + 20 2688.0 81.752274 ... 84.483418 85.051697 + 21 2816.0 81.981598 ... 79.298560 79.587973 + 22 2944.0 82.102191 ... 80.902653 78.235527 + 23 3072.0 81.238312 ... 84.135370 83.269271 + 24 3200.0 83.224970 ... 83.989503 89.887639 + 25 3328.0 83.905938 ... 83.323259 84.298943 + 26 3456.0 82.266905 ... 86.689860 86.503829 + 27 3584.0 84.033077 ... 91.656871 96.475743 + 28 3712.0 85.528545 ... 83.526206 88.561477 + 29 3840.0 82.716526 ... 81.738356 85.399230 + 30 3968.0 92.793868 ... 86.849777 87.159957 + 31 4096.0 93.531519 ... 92.056052 92.372834 [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 16.316 seconds) + **Total running time of the script:** ( 2 minutes 16.809 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 7af0eb1c4..55b339f1a 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 ================= -**03:35.456** total execution time for **getting-started_tutorials** files: +**03:36.008** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 02:16.316 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 02:16.809 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 01:08.170 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 01:08.191 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 00:10.970 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 00:11.008 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/getting-started/tutorials/01-vector-add.html b/getting-started/tutorials/01-vector-add.html index dc11a1326..c0112f0de 100644 --- a/getting-started/tutorials/01-vector-add.html +++ b/getting-started/tutorials/01-vector-add.html @@ -305,10 +305,10 @@ for different problem sizes.
Out:
vector-add-performance:
size Triton Torch
-0 4096.0 8.000000 9.600000
+0 4096.0 9.540372 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 384.000001
@@ -323,7 +323,7 @@ for different problem sizes.
15 134217728.0 851.577704 850.656574
Total running time of the script: ( 0 minutes 10.970 seconds)
+Total running time of the script: ( 0 minutes 11.008 seconds)