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
2022-04-23 00:44:46 +00:00
parent cb69ba73a9
commit 31dd4ab60e
158 changed files with 334 additions and 334 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
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
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 31.597714 ... 34.028308 34.028308
5 896.0 37.971025 ... 39.025776 39.025776
6 1024.0 49.932191 ... 52.428801 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 62.929456 ... 62.061463 61.636381
12 1792.0 72.512412 ... 71.588687 71.135597
13 1920.0 68.776119 ... 70.172588 70.172588
14 2048.0 73.584279 ... 76.959706 76.608294
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.446623 ... 76.563695 76.319081
17 2432.0 71.125224 ... 79.587714 84.621881
18 2560.0 77.649287 ... 81.310171 80.117359
19 2688.0 83.552988 ... 89.254248 88.836198
20 2816.0 80.617762 ... 82.135981 82.916747
21 2944.0 81.832567 ... 82.921853 82.646820
22 3072.0 82.420822 ... 83.886078 88.197981
23 3200.0 85.106381 ... 95.238096 94.674553
24 3328.0 83.516586 ... 83.082856 84.496824
25 3456.0 82.519518 ... 88.595129 90.281712
26 3584.0 87.127323 ... 92.600816 97.628001
27 3712.0 85.528545 ... 86.044224 87.322855
28 3840.0 82.716526 ... 85.267542 91.625518
29 3968.0 86.053553 ... 91.816356 83.863449
30 4096.0 94.254021 ... 86.258181 85.325956
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 23.272727
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 45.938215
8 1280.0 49.951220 ... 55.351349 55.351349
9 1408.0 62.664092 ... 65.684049 64.902096
10 1536.0 78.643199 ... 77.778988 76.933564
11 1664.0 61.636381 ... 60.803457 60.803457
12 1792.0 71.588687 ... 70.688200 70.246402
13 1920.0 67.764707 ... 68.776119 68.776119
14 2048.0 72.315584 ... 75.573044 75.234154
15 2176.0 81.803444 ... 84.553145 84.199364
16 2304.0 67.100763 ... 75.356064 75.119093
17 2432.0 69.886725 ... 84.115159 83.366361
18 2560.0 76.382283 ... 79.921950 79.533982
19 2688.0 82.642823 ... 88.216412 88.422041
20 2816.0 83.074685 ... 82.213395 81.827785
21 2944.0 81.298583 ... 81.431424 81.298583
22 3072.0 80.890151 ... 87.651868 87.651868
23 3200.0 83.989503 ... 94.674553 93.841640
24 3328.0 82.369902 ... 83.905938 83.905938
25 3456.0 80.945348 ... 90.484366 90.180725
26 3584.0 86.125852 ... 97.311031 97.628001
27 3712.0 85.019017 ... 87.860458 87.706180
28 3840.0 84.292684 ... 91.209894 90.947372
29 3968.0 92.652949 ... 90.522206 90.522206
30 4096.0 93.045216 ... 92.372834 91.867031
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 17.603 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 4.717 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>