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
2022-02-28 00:41:59 +00:00
parent a64f41ab97
commit 11bcbd3d04
156 changed files with 276 additions and 276 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -564,42 +564,42 @@ 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 3.276800
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 16.384000 16.384000
0 256.0 2.978909 ... 3.276800 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 24.380953
4 768.0 32.768000 ... 34.028308 34.028308
5 896.0 39.025776 ... 40.140799 39.025776
6 1024.0 51.150050 ... 52.428801 52.428801
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 56.888887
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.492442 62.061463
12 1792.0 72.512412 ... 72.047592 72.047592
13 1920.0 68.776119 ... 70.172588 69.818184
14 2048.0 73.262953 ... 76.608294 76.260072
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.446623 ... 76.319081 76.319081
17 2432.0 71.487187 ... 74.918570 84.621881
18 2560.0 77.833728 ... 81.108913 80.908642
19 2688.0 83.737433 ... 89.888756 89.676257
20 2816.0 82.290955 ... 82.916747 82.602666
21 2944.0 82.102191 ... 79.865439 82.921853
22 3072.0 81.355034 ... 87.516392 86.184329
23 3200.0 83.224970 ... 90.909090 89.260810
24 3328.0 80.798314 ... 83.226931 84.596116
25 3456.0 82.266905 ... 90.382926 90.994998
26 3584.0 84.111686 ... 92.600816 94.448944
27 3712.0 85.528545 ... 85.163978 88.170647
28 3840.0 80.197243 ... 86.197974 91.473945
29 3968.0 85.991957 ... 90.791620 85.093402
30 4096.0 92.852115 ... 82.493991 82.241256
10 1536.0 79.526831 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.492442 62.492442
12 1792.0 72.983276 ... 72.047592 72.047592
13 1920.0 69.467336 ... 70.172588 69.818184
14 2048.0 73.262953 ... 76.608294 76.608294
15 2176.0 83.500614 ... 86.367588 85.632545
16 2304.0 68.446623 ... 76.809875 76.809875
17 2432.0 71.396351 ... 83.614477 85.393507
18 2560.0 78.019048 ... 81.108913 80.709358
19 2688.0 83.737433 ... 89.676257 89.676257
20 2816.0 82.135981 ... 82.916747 82.916747
21 2944.0 82.237674 ... 82.237674 82.102191
22 3072.0 80.089253 ... 88.473602 88.335577
23 3200.0 83.116885 ... 95.238096 95.380032
24 3328.0 82.369902 ... 84.003845 84.200347
25 3456.0 80.220468 ... 86.503829 87.536988
26 3584.0 86.457107 ... 98.268190 98.268190
27 3712.0 80.757757 ... 87.783251 84.946722
28 3840.0 83.027026 ... 90.574940 84.613126
29 3968.0 87.976885 ... 85.212248 87.035620
30 4096.0 91.992956 ... 92.755862 86.092193
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 0.809 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 2.552 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>