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
2022-02-18 00:43:01 +00:00
parent 0cd3b626c5
commit cee16caf2b
156 changed files with 240 additions and 240 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -565,41 +565,41 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
<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
2 512.0 14.563555 ... 16.384000 16.384000
1 384.0 7.372800 ... 8.507077 8.507077
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
5 896.0 37.971025 ... 40.140799 39.025776
6 1024.0 49.932191 ... 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 66.485074
10 1536.0 79.526831 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.061463 61.636381
9 1408.0 64.138541 ... 67.305878 65.684049
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.492442 62.061463
12 1792.0 72.512412 ... 72.047592 72.047592
13 1920.0 68.776119 ... 70.530615 70.530615
14 2048.0 73.584279 ... 76.959706 76.608294
15 2176.0 83.500614 ... 85.998493 85.632545
16 2304.0 68.446623 ... 76.319081 76.319081
17 2432.0 71.305746 ... 74.719317 85.134737
18 2560.0 78.019048 ... 80.709358 80.313727
19 2688.0 83.737433 ... 88.628636 89.254248
20 2816.0 79.879498 ... 83.233226 83.233226
21 2944.0 82.169877 ... 82.237674 82.102191
22 3072.0 81.121923 ... 88.612060 88.335577
23 3200.0 83.879425 ... 95.096582 95.380032
24 3328.0 82.843841 ... 84.200347 84.397770
25 3456.0 77.745004 ... 91.200871 84.686523
26 3584.0 86.540320 ... 97.840469 98.053863
27 3712.0 82.491612 ... 87.094458 86.867254
28 3840.0 81.859361 ... 90.058629 88.121115
29 3968.0 88.938731 ... 91.062642 86.880696
30 4096.0 93.012976 ... 91.242506 87.267706
13 1920.0 68.776119 ... 70.172588 69.818184
14 2048.0 73.262953 ... 76.959706 76.608294
15 2176.0 83.500614 ... 86.367588 85.269692
16 2304.0 68.643310 ... 77.057651 76.809875
17 2432.0 71.487187 ... 84.367759 84.877538
18 2560.0 78.019048 ... 80.709358 80.511054
19 2688.0 83.004501 ... 89.888756 89.254248
20 2816.0 80.767055 ... 82.916747 81.521884
21 2944.0 81.698415 ... 82.237674 82.921853
22 3072.0 82.661468 ... 88.612060 87.516392
23 3200.0 82.051282 ... 94.814812 94.534716
24 3328.0 83.226931 ... 84.895397 84.496824
25 3456.0 81.108217 ... 91.200871 85.722029
26 3584.0 82.189576 ... 93.370085 95.047985
27 3712.0 82.491612 ... 88.092894 89.114488
28 3840.0 82.716526 ... 89.620748 86.670843
29 3968.0 85.934238 ... 91.062642 86.114283
30 4096.0 93.012976 ... 92.691803 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 57.748 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 7.784 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>