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
2022-02-11 00:40:00 +00:00
parent 30f8e01add
commit 7c47f3e043
158 changed files with 262 additions and 262 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
v1.1.2/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -568,42 +568,42 @@ 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
0 256.0 2.730667 ... 3.276800 2.978909
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 39.025776 ... 40.140799 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
6 1024.0 51.150050 ... 52.428801 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 79.526831 ... 79.526831 79.526831
11 1664.0 62.929456 ... 62.492442 62.061463
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.061463 62.061463
12 1792.0 72.512412 ... 72.047592 71.588687
13 1920.0 69.467336 ... 70.172588 69.818184
14 2048.0 73.584279 ... 76.959706 76.959706
15 2176.0 83.500614 ... 85.632545 85.269692
16 2304.0 68.446623 ... 76.809875 76.563695
17 2432.0 71.305746 ... 84.877538 84.877538
18 2560.0 78.019048 ... 81.008654 80.908642
13 1920.0 69.120002 ... 70.172588 69.818184
14 2048.0 73.584279 ... 76.608294 76.608294
15 2176.0 82.813365 ... 85.998493 85.269692
16 2304.0 68.446623 ... 76.809875 76.319081
17 2432.0 71.305746 ... 74.521127 84.367759
18 2560.0 77.833728 ... 81.310171 80.908642
19 2688.0 83.186525 ... 89.676257 89.464755
20 2816.0 83.873477 ... 82.759409 81.981598
21 2944.0 82.373605 ... 82.373605 81.298583
22 3072.0 81.238312 ... 88.612060 89.030036
23 3200.0 83.989503 ... 95.096582 93.979441
24 3328.0 83.130825 ... 84.397770 83.710812
25 3456.0 81.766291 ... 83.893412 90.382926
26 3584.0 87.211821 ... 98.483450 92.505546
27 3712.0 84.230479 ... 88.718781 84.017953
28 3840.0 84.421376 ... 91.398346 87.286505
29 3968.0 92.093539 ... 84.447457 87.787005
30 4096.0 91.678778 ... 92.691803 86.258181
20 2816.0 83.552120 ... 82.135981 82.602666
21 2944.0 81.832567 ... 82.509987 82.373605
22 3072.0 81.825298 ... 86.845249 83.146995
23 3200.0 84.600132 ... 94.955488 94.534716
24 3328.0 83.710812 ... 82.275764 83.808259
25 3456.0 81.849303 ... 87.347312 88.986281
26 3584.0 87.722333 ... 90.368655 95.654673
27 3712.0 85.528545 ... 84.230479 85.822459
28 3840.0 84.940091 ... 92.313853 84.230487
29 3968.0 92.232760 ... 81.186915 84.680037
30 4096.0 93.336389 ... 92.309303 85.163532
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 33.411 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 49.922 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>