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
2022-08-15 00:49:17 +00:00
parent 36804ec20e
commit 943e27aa53
165 changed files with 312 additions and 312 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
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
1 384.0 7.372800 ... 8.507077 7.899428
0 256.0 2.978909 ... 2.978909 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 49.932191 ... 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 ... 71.588687 71.588687
13 1920.0 68.776119 ... 70.172588 70.530615
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.155572 ... 86.367588 85.269692
5 896.0 39.025776 ... 39.025776 39.025776
6 1024.0 51.150050 ... 52.428801 52.428801
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 ... 79.526831 79.526831
11 1664.0 63.372618 ... 62.061463 62.061463
12 1792.0 72.512412 ... 72.047592 71.588687
13 1920.0 69.120002 ... 70.172588 70.172588
14 2048.0 73.908442 ... 76.959706 76.959706
15 2176.0 83.500614 ... 85.998493 85.269692
16 2304.0 68.446623 ... 76.809875 76.563695
17 2432.0 71.305746 ... 74.918570 84.877538
18 2560.0 77.833728 ... 81.310171 81.108913
19 2688.0 83.552988 ... 90.102270 88.732296
20 2816.0 82.602666 ... 83.712490 82.759409
21 2944.0 81.967162 ... 82.578347 82.646820
22 3072.0 82.062468 ... 87.651868 86.579673
23 3200.0 84.544253 ... 89.887639 94.674553
24 3328.0 83.226931 ... 81.346098 83.710812
25 3456.0 82.688790 ... 90.180725 91.097818
26 3584.0 85.430303 ... 92.505546 97.522120
27 3712.0 85.528545 ... 85.672957 87.552452
28 3840.0 84.292684 ... 87.148936 91.022218
29 3968.0 86.973584 ... 90.656713 84.856701
30 4096.0 93.531519 ... 83.416859 87.267706
18 2560.0 77.833728 ... 81.310171 80.313727
19 2688.0 83.922689 ... 89.676257 88.422041
20 2816.0 80.617762 ... 83.392363 83.233226
21 2944.0 82.373605 ... 82.373605 81.298583
22 3072.0 82.540970 ... 88.335577 88.060814
23 3200.0 83.769634 ... 95.096582 94.674553
24 3328.0 84.003845 ... 83.516586 84.003845
25 3456.0 82.015834 ... 89.183149 84.597660
26 3584.0 86.043434 ... 97.416461 96.579370
27 3712.0 81.548851 ... 88.797643 84.946722
28 3840.0 83.908951 ... 91.097196 85.930069
29 3968.0 91.301109 ... 86.175099 89.068569
30 4096.0 88.534120 ... 93.206754 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 27.557 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 21.527 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>