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
2022-08-04 00:49:04 +00:00
parent d84d42ef8d
commit b254e2b165
167 changed files with 284 additions and 284 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
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 2.730667 ... 2.978909 2.978909
0 256.0 2.978909 ... 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
7 1152.0 45.242181 ... 46.656000 46.656000
7 1152.0 45.242181 ... 47.396572 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 ... 80.430545 79.526831
11 1664.0 63.372618 ... 62.492442 62.061463
11 1664.0 62.929456 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.047592 71.588687
13 1920.0 69.120002 ... 70.530615 70.172588
13 1920.0 69.120002 ... 70.530615 70.530615
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.500614 ... 86.367588 84.909907
15 2176.0 83.500614 ... 86.367588 85.632545
16 2304.0 68.251065 ... 76.809875 76.563695
17 2432.0 71.305746 ... 74.918570 84.877538
18 2560.0 78.019048 ... 81.310171 80.412266
19 2688.0 83.552988 ... 89.464755 90.102270
20 2816.0 79.587973 ... 80.617762 82.602666
21 2944.0 82.921853 ... 78.979452 82.441740
22 3072.0 81.472093 ... 85.792579 83.269271
23 3200.0 84.656085 ... 92.888243 95.096582
24 3328.0 82.041364 ... 83.130825 84.695641
25 3456.0 81.518272 ... 91.511426 90.892410
26 3584.0 86.457107 ... 91.563533 94.947616
27 3712.0 83.806497 ... 86.192706 88.443856
28 3840.0 80.255442 ... 90.574940 89.043476
29 3968.0 92.512459 ... 83.807647 80.015697
30 4096.0 93.271527 ... 84.360608 86.424811
17 2432.0 71.305746 ... 74.719317 84.877538
18 2560.0 78.019048 ... 81.310171 80.511054
19 2688.0 83.369354 ... 89.888756 89.254248
20 2816.0 81.067298 ... 83.552120 82.602666
21 2944.0 82.237674 ... 82.373605 81.967162
22 3072.0 81.121923 ... 88.335577 88.473602
23 3200.0 84.768213 ... 95.238096 94.814812
24 3328.0 83.905938 ... 84.496824 84.596116
25 3456.0 78.502012 ... 85.223646 85.858966
26 3584.0 87.169547 ... 98.483450 90.273669
27 3712.0 81.548851 ... 86.044224 86.791782
28 3840.0 84.809814 ... 92.083268 86.197974
29 3968.0 93.112506 ... 83.980685 91.198760
30 4096.0 87.495257 ... 93.336389 86.313653
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.119 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 16.961 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>