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
2022-08-11 00:50:19 +00:00
parent 4b51054036
commit ca12a57c3b
168 changed files with 289 additions and 289 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 2.730667 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
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
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 34.028308 34.028308
5 896.0 39.025776 ... 39.025776 39.025776
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 56.109587
9 1408.0 64.138541 ... 67.305878 66.485074
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 68.776119 ... 70.172588 70.172588
14 2048.0 73.908442 ... 76.959706 76.959706
15 2176.0 83.500614 ... 86.367588 85.632545
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 63.372618 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.047592 71.588687
13 1920.0 69.120002 ... 70.172588 70.530615
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.500614 ... 85.998493 85.269692
16 2304.0 68.251065 ... 76.809875 76.563695
17 2432.0 71.305746 ... 85.393507 84.367759
18 2560.0 77.833728 ... 81.310171 80.908642
19 2688.0 83.369354 ... 88.836198 89.464755
20 2816.0 79.733474 ... 83.552120 82.602666
21 2944.0 82.237674 ... 83.060049 81.298583
22 3072.0 79.638683 ... 88.473602 87.924073
23 3200.0 84.656085 ... 95.665176 95.238096
24 3328.0 84.003845 ... 84.695641 83.516586
25 3456.0 81.849303 ... 84.508982 88.790274
26 3584.0 86.958797 ... 98.591437 94.548254
27 3712.0 85.019017 ... 85.748791 86.716441
28 3840.0 85.005380 ... 86.164395 88.615388
29 3968.0 92.793868 ... 85.093402 90.926929
30 4096.0 88.592559 ... 86.480498 93.045216
17 2432.0 71.305746 ... 85.134737 84.877538
18 2560.0 78.019048 ... 81.310171 80.511054
19 2688.0 83.737433 ... 89.254248 89.888756
20 2816.0 81.218262 ... 83.552120 82.759409
21 2944.0 82.237674 ... 79.865439 82.921853
22 3072.0 81.825298 ... 88.542777 86.579673
23 3200.0 79.701121 ... 91.822093 92.352095
24 3328.0 80.707733 ... 84.895397 84.596116
25 3456.0 82.099354 ... 91.304157 85.585527
26 3584.0 85.633710 ... 91.610178 95.502274
27 3712.0 84.372753 ... 87.170458 86.716441
28 3840.0 84.292684 ... 91.853823 85.399230
29 3968.0 92.372393 ... 89.068569 84.915752
30 4096.0 91.553703 ... 83.468735 86.844210
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 22.058 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.923 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>