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
2022-08-19 00:50:31 +00:00
parent db7b163cb5
commit a7462d444b
163 changed files with 270 additions and 270 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
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 ... 2.978909 3.276800
0 256.0 2.730667 ... 2.978909 2.978909
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 16.384000 16.384000
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 ... 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 67.305878
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.061463 62.061463
12 1792.0 72.512412 ... 59.310944 71.588687
13 1920.0 69.120002 ... 70.530615 70.530615
14 2048.0 73.908442 ... 76.959706 76.959706
15 2176.0 83.155572 ... 86.367588 85.269692
16 2304.0 68.251065 ... 76.809875 76.319081
17 2432.0 71.305746 ... 82.388456 84.877538
18 2560.0 77.833728 ... 81.310171 81.108913
19 2688.0 83.552988 ... 89.044730 89.464755
20 2816.0 79.733474 ... 83.712490 82.446516
21 2944.0 81.698415 ... 81.832567 82.102191
22 3072.0 82.062468 ... 88.612060 89.170242
23 3200.0 82.262212 ... 93.704243 94.395283
24 3328.0 84.003845 ... 84.101981 83.905938
25 3456.0 79.508447 ... 84.775569 91.304157
26 3584.0 87.042978 ... 90.365811 97.522120
27 3712.0 85.601834 ... 87.208507 87.552452
28 3840.0 80.960466 ... 88.900318 90.095313
29 3968.0 88.873953 ... 85.271796 87.723894
30 4096.0 93.498941 ... 93.336389 86.258181
10 1536.0 80.430545 ... 79.526831 79.526831
11 1664.0 63.372618 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.047592 71.588687
13 1920.0 69.120002 ... 70.530615 70.172588
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.500614 ... 86.367588 85.632545
16 2304.0 68.251065 ... 76.319081 76.319081
17 2432.0 71.305746 ... 74.918570 84.877538
18 2560.0 78.019048 ... 80.908642 81.108913
19 2688.0 83.186525 ... 89.464755 89.254248
20 2816.0 79.879498 ... 82.602666 82.602666
21 2944.0 82.921853 ... 82.784108 82.921853
22 3072.0 81.825298 ... 88.473602 89.310890
23 3200.0 82.901554 ... 94.674553 94.117647
24 3328.0 83.226931 ... 84.200347 83.905938
25 3456.0 80.380430 ... 91.097818 86.596744
26 3584.0 84.745889 ... 94.250936 94.947616
27 3712.0 81.548851 ... 87.706180 86.754095
28 3840.0 82.654712 ... 90.723546 86.030338
29 3968.0 91.816356 ... 85.211320 91.130650
30 4096.0 86.258181 ... 93.239129 89.240508
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.620 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 26.200 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>