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
2022-04-14 00:44:57 +00:00
parent 9d65bf62fb
commit 2a53636c23
158 changed files with 346 additions and 346 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
v1.1.2/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -569,41 +569,41 @@ 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 ... 16.384000 15.420235
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 15.420235 15.420235
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 34.028308 34.028308
4 768.0 31.597714 ... 34.028308 34.028308
5 896.0 37.971025 ... 39.025776 37.971025
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 44.566925 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.888887
9 1408.0 64.138541 ... 67.305878 67.305878
10 1536.0 80.430545 ... 79.526831 79.526831
11 1664.0 63.372618 ... 62.929456 62.061463
12 1792.0 72.983276 ... 72.047592 71.588687
13 1920.0 68.776119 ... 70.172588 70.172588
14 2048.0 73.908442 ... 76.959706 76.608294
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.251065 ... 76.809875 76.319081
17 2432.0 71.125224 ... 84.621881 84.115159
18 2560.0 77.833728 ... 81.310171 80.313727
19 2688.0 83.369354 ... 89.782378 89.254248
20 2816.0 83.552120 ... 83.792906 82.446516
21 2944.0 81.967162 ... 81.698415 82.102191
22 3072.0 81.943708 ... 88.473602 88.197981
23 3200.0 84.432717 ... 95.522391 94.955488
24 3328.0 83.516586 ... 83.226931 83.710812
25 3456.0 81.683457 ... 90.994998 84.597660
26 3584.0 83.954614 ... 95.553020 87.299148
27 3712.0 84.159518 ... 83.178475 88.248537
28 3840.0 80.255442 ... 87.424508 91.549669
29 3968.0 86.973584 ... 89.988156 83.980685
30 4096.0 92.627833 ... 86.258181 85.298843
6 1024.0 49.932191 ... 52.428801 51.150050
7 1152.0 43.911529 ... 45.938215 45.242181
8 1280.0 49.951220 ... 55.351349 55.351349
9 1408.0 62.664092 ... 65.684049 65.684049
10 1536.0 78.643199 ... 77.778988 77.778988
11 1664.0 62.061463 ... 61.217089 60.803457
12 1792.0 71.588687 ... 70.246402 70.246402
13 1920.0 68.098521 ... 68.776119 68.776119
14 2048.0 72.315584 ... 75.234154 75.234154
15 2176.0 81.472263 ... 84.199364 83.500614
16 2304.0 67.100763 ... 75.119093 74.883608
17 2432.0 69.713308 ... 83.614477 83.119713
18 2560.0 76.204654 ... 79.533982 79.341404
19 2688.0 82.823267 ... 88.216412 88.011732
20 2816.0 82.759409 ... 81.827785 81.674548
21 2944.0 81.034195 ... 81.431424 81.166173
22 3072.0 81.121923 ... 87.381335 87.516392
23 3200.0 83.550913 ... 94.814812 94.256261
24 3328.0 82.369902 ... 83.808259 83.613586
25 3456.0 80.783132 ... 90.484366 90.281712
26 3584.0 86.498694 ... 97.840469 97.416461
27 3712.0 84.730571 ... 89.674457 92.156222
28 3840.0 84.228485 ... 91.247522 91.172297
29 3968.0 92.372393 ... 90.555796 90.354633
30 4096.0 93.142072 ... 92.372834 91.678778
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 54.053 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 33.271 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>