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
2022-04-30 00:47:08 +00:00
parent ea296daf2a
commit e15e7e5ae2
156 changed files with 274 additions and 274 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
v1.1.2/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -569,41 +569,41 @@ 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 2.978909 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 7.899428
2 512.0 14.563555 ... 16.384000 15.420235
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 37.971025 ... 39.025776 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
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 56.109587
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.929456 62.061463
11 1664.0 63.372618 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.512412 71.588687
13 1920.0 69.120002 ... 69.818184 70.172588
14 2048.0 73.584279 ... 76.959706 76.608294
13 1920.0 68.776119 ... 70.172588 70.172588
14 2048.0 73.908442 ... 76.959706 76.608294
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.251065 ... 77.057651 76.563695
17 2432.0 71.305746 ... 85.134737 85.134737
18 2560.0 78.019048 ... 81.310171 80.908642
19 2688.0 83.922689 ... 89.888756 88.628636
20 2816.0 84.035084 ... 83.873477 83.392363
21 2944.0 81.967162 ... 79.865439 82.646820
22 3072.0 82.420822 ... 88.335577 86.184329
23 3200.0 81.476768 ... 94.814812 94.117647
24 3328.0 83.130825 ... 84.995628 84.995628
25 3456.0 82.099354 ... 85.858966 88.304015
26 3584.0 87.254137 ... 97.840469 91.007486
27 3712.0 83.247783 ... 87.783251 86.716441
28 3840.0 85.070769 ... 92.236860 84.421376
29 3968.0 93.720380 ... 84.154440 91.335278
30 4096.0 86.536250 ... 87.239345 93.142072
17 2432.0 71.305746 ... 85.393507 84.877538
18 2560.0 77.833728 ... 81.310171 80.511054
19 2688.0 84.295681 ... 89.149366 89.676257
20 2816.0 84.523664 ... 83.792906 82.602666
21 2944.0 82.646820 ... 82.921853 82.921853
22 3072.0 81.707223 ... 85.147525 88.197981
23 3200.0 84.880639 ... 93.023256 93.023256
24 3328.0 83.130825 ... 84.895397 85.602017
25 3456.0 80.061141 ... 89.779026 91.304157
26 3584.0 87.211821 ... 92.696281 94.647779
27 3712.0 85.748791 ... 89.035062 87.475786
28 3840.0 81.798814 ... 91.097196 89.151148
29 3968.0 89.855624 ... 87.347124 89.723483
30 4096.0 87.552332 ... 89.478485 92.182504
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 22.838 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 19.631 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>