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
2022-08-27 00:48:56 +00:00
parent 65cfbbabe5
commit 79bb9e69b7
163 changed files with 278 additions and 278 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
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 2.978909
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 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 ... 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 79.526831
11 1664.0 63.372618 ... 62.492442 62.061463
12 1792.0 72.983276 ... 71.588687 71.588687
13 1920.0 68.776119 ... 70.530615 70.530615
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.155572 ... 85.998493 85.632545
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 ... 71.588687 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 85.632545
16 2304.0 68.251065 ... 76.809875 76.563695
17 2432.0 71.305746 ... 85.393507 85.134737
17 2432.0 71.305746 ... 85.393507 84.367759
18 2560.0 78.019048 ... 80.908642 81.108913
19 2688.0 83.369354 ... 89.888756 89.044730
20 2816.0 83.552120 ... 83.712490 82.759409
21 2944.0 81.564701 ... 81.698415 81.832567
22 3072.0 82.062468 ... 88.473602 88.335577
23 3200.0 84.544253 ... 95.238096 95.096582
24 3328.0 83.130825 ... 84.101981 84.003845
25 3456.0 79.430113 ... 88.595129 88.400840
26 3584.0 87.296493 ... 98.160909 98.160909
27 3712.0 82.423549 ... 88.561477 85.822459
28 3840.0 84.809814 ... 92.006659 87.286505
29 3968.0 93.148045 ... 82.953048 80.917732
30 4096.0 93.045216 ... 92.884244 88.243079
19 2688.0 83.737433 ... 89.044730 88.628636
20 2816.0 79.587973 ... 82.916747 83.233226
21 2944.0 81.564701 ... 82.373605 82.921853
22 3072.0 82.181572 ... 89.451983 87.313963
23 3200.0 83.116885 ... 92.753621 91.298148
24 3328.0 80.617354 ... 84.895397 84.596116
25 3456.0 82.099354 ... 91.097818 90.586029
26 3584.0 82.189576 ... 91.563533 95.047985
27 3712.0 85.309435 ... 90.981189 87.170458
28 3840.0 81.079177 ... 85.070769 91.097196
29 3968.0 85.752131 ... 91.266964 85.751184
30 4096.0 93.336389 ... 92.245860 88.243079
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 25.861 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 16.690 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>