gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[GH-PAGES] Updated website

Browse Source
This commit is contained in:
Philippe Tillet
2022-04-23 00:44:46 +00:00
parent cb69ba73a9
commit 31dd4ab60e
158 changed files with 334 additions and 334 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -565,41 +565,41 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>matmul-performance:
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 256.0 2.730667 ... 2.978909 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 15.420235 15.420235
1 384.0 7.372800 ... 7.899428 8.507077
2 512.0 14.563555 ... 15.420235 16.384000
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 34.028308 34.028308
5 896.0 37.971025 ... 40.140799 40.140799
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 45.242181 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 69.009825 68.147202
10 1536.0 80.430545 ... 80.430545 79.526831
11 1664.0 62.929456 ... 62.929456 62.929456
12 1792.0 72.983276 ... 63.142831 63.142831
13 1920.0 68.776119 ... 71.257735 71.257735
14 2048.0 73.584279 ... 78.398206 78.033565
15 2176.0 82.813365 ... 86.739860 86.367588
16 2304.0 68.251065 ... 77.558029 77.307030
17 2432.0 71.125224 ... 75.726318 75.522751
18 2560.0 77.283019 ... 82.331658 82.125311
19 2688.0 83.552988 ... 91.185232 90.748936
20 2816.0 79.443003 ... 83.792906 83.552120
21 2944.0 82.237674 ... 84.040530 83.899046
22 3072.0 81.589488 ... 85.598037 89.451983
23 3200.0 84.432717 ... 88.520058 95.952022
24 3328.0 81.854799 ... 85.703924 82.275764
25 3456.0 80.220468 ... 92.244355 87.632137
26 3584.0 83.101104 ... 91.284657 94.250936
27 3712.0 85.675250 ... 82.902362 87.552452
28 3840.0 81.079177 ... 87.493673 91.625518
29 3968.0 87.035620 ... 90.388098 84.915752
30 4096.0 91.366730 ... 83.208386 90.626421
4 768.0 31.597714 ... 34.028308 34.028308
5 896.0 36.971791 ... 40.140799 39.025776
6 1024.0 48.770977 ... 52.428801 52.428801
7 1152.0 43.911529 ... 46.656000 46.656000
8 1280.0 49.951220 ... 56.888887 56.109587
9 1408.0 62.664092 ... 67.305878 66.485074
10 1536.0 78.643199 ... 78.643199 77.778988
11 1664.0 61.636381 ... 62.061463 61.636381
12 1792.0 71.588687 ... 67.707374 67.707374
13 1920.0 67.764707 ... 70.172588 69.818184
14 2048.0 72.005219 ... 76.608294 76.260072
15 2176.0 81.803444 ... 85.632545 85.269692
16 2304.0 67.100763 ... 76.563695 76.319081
17 2432.0 69.886725 ... 74.323979 73.932798
18 2560.0 76.382283 ... 80.908642 80.511054
19 2688.0 82.642823 ... 89.676257 89.254248
20 2816.0 82.602666 ... 82.916747 82.759409
21 2944.0 81.166173 ... 82.509987 82.169877
22 3072.0 81.005868 ... 88.197981 88.060814
23 3200.0 83.660130 ... 95.522391 95.096582
24 3328.0 82.369902 ... 84.795401 84.596116
25 3456.0 81.026701 ... 91.304157 90.994998
26 3584.0 86.374055 ... 98.699661 98.375705
27 3712.0 84.874549 ... 88.876645 88.483034
28 3840.0 84.036474 ... 92.545605 92.159996
29 3968.0 92.232760 ... 91.062642 91.403695
30 4096.0 93.206754 ... 93.012976 92.820009
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 21.623 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 41.514 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>