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
2022-04-16 00:44:44 +00:00
parent 824d060dfb
commit 9b0ee317d9
160 changed files with 365 additions and 380 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 7.899428
2 512.0 14.563555 ... 16.384000 15.420235
3 640.0 22.260869 ... 24.380953 23.272727
4 768.0 31.597714 ... 34.028308 34.028308
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 16.384000 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 ... 39.025776 37.971025
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 ... 71.135597 70.688200
13 1920.0 68.098521 ... 69.120002 69.120002
14 2048.0 72.628641 ... 75.573044 75.234154
15 2176.0 81.803444 ... 84.199364 83.500614
16 2304.0 67.100763 ... 75.119093 75.119093
17 2432.0 69.886725 ... 83.614477 83.119713
18 2560.0 76.204654 ... 79.727497 79.341404
19 2688.0 82.284288 ... 88.216412 88.011732
20 2816.0 82.759409 ... 82.135981 81.674548
21 2944.0 81.166173 ... 81.431424 81.166173
22 3072.0 81.121923 ... 87.381335 86.845249
23 3200.0 83.660130 ... 94.395283 93.910490
24 3328.0 82.181847 ... 83.808259 83.565058
25 3456.0 80.864158 ... 90.484366 90.079964
26 3584.0 86.291162 ... 97.628001 97.575029
27 3712.0 84.730571 ... 87.860458 87.552452
28 3840.0 84.228485 ... 91.322872 90.649182
29 3968.0 92.442373 ... 90.522206 90.354633
30 4096.0 93.142072 ... 91.929947 92.182504
7 1152.0 44.566925 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.109587
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 79.526831 ... 79.526831 78.643199
11 1664.0 63.372618 ... 62.492442 62.492442
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 ... 76.441192 76.563695
17 2432.0 71.305746 ... 79.587714 84.621881
18 2560.0 77.833728 ... 80.908642 80.313727
19 2688.0 83.369354 ... 89.676257 89.254248
20 2816.0 84.035084 ... 82.759409 82.602666
21 2944.0 82.373605 ... 83.198715 82.921853
22 3072.0 81.943708 ... 87.855861 88.335577
23 3200.0 84.321474 ... 89.761569 94.674553
24 3328.0 82.939284 ... 79.548391 83.710812
25 3456.0 81.683457 ... 89.480098 90.790053
26 3584.0 87.211821 ... 98.591437 90.367227
27 3712.0 85.019017 ... 88.718781 84.017953
28 3840.0 84.679936 ... 92.390975 84.228485
29 3968.0 92.723355 ... 85.271796 89.657558
30 4096.0 92.787924 ... 92.372834 86.258181
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 23.021 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 34.991 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>