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
2022-08-25 00:51:52 +00:00
parent aaf54f10e5
commit a1fd5d2238
167 changed files with 270 additions and 270 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
v1.1.2/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -568,12 +568,12 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
<p class="sphx-glr-script-out">Out:</p>
<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 2.978909 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
0 256.0 2.730667 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 7.899428
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 39.025776 ... 40.140799 39.025776
5 896.0 37.971025 ... 39.025776 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
7 1152.0 45.242181 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.109587
@@ -582,28 +582,28 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
11 1664.0 62.929456 ... 62.061463 62.061463
12 1792.0 72.512412 ... 72.047592 71.588687
13 1920.0 69.120002 ... 70.530615 70.530615
14 2048.0 73.908442 ... 76.959706 76.959706
15 2176.0 83.500614 ... 85.998493 85.269692
16 2304.0 68.251065 ... 76.563695 76.563695
17 2432.0 71.305746 ... 75.118889 84.877538
18 2560.0 78.019048 ... 81.512437 80.511054
19 2688.0 83.277839 ... 88.628636 89.044730
20 2816.0 80.916902 ... 83.233226 83.233226
21 2944.0 81.631503 ... 82.921853 82.102191
22 3072.0 81.825298 ... 83.453353 88.197981
23 3200.0 84.321474 ... 95.238096 95.096582
24 3328.0 82.748617 ... 85.703924 81.994643
25 3456.0 82.688790 ... 90.994998 90.790053
26 3584.0 85.879071 ... 90.367227 97.522120
27 3712.0 85.748791 ... 91.147215 87.170458
28 3840.0 81.798814 ... 84.098385 91.398346
29 3968.0 86.973584 ... 91.472214 83.692683
30 4096.0 93.792965 ... 92.245860 85.215917
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.500614 ... 85.632545 85.269692
16 2304.0 68.446623 ... 76.809875 76.076024
17 2432.0 71.305746 ... 75.018596 84.877538
18 2560.0 78.019048 ... 80.908642 81.108913
19 2688.0 83.369354 ... 89.676257 88.422041
20 2816.0 83.074685 ... 83.074685 82.602666
21 2944.0 82.237674 ... 82.784108 82.921853
22 3072.0 80.430545 ... 88.197981 88.335577
23 3200.0 83.009080 ... 95.238096 94.814812
24 3328.0 82.843841 ... 84.298943 84.101981
25 3456.0 81.026701 ... 87.064328 87.252780
26 3584.0 87.042978 ... 91.470385 96.579370
27 3712.0 85.528545 ... 87.170458 88.170647
28 3840.0 84.228485 ... 92.083268 85.399230
29 3968.0 92.442373 ... 83.924734 91.096633
30 4096.0 86.259911 ... 88.417474 92.691803
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.771 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.833 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>