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
2022-04-27 00:47:37 +00:00
parent b0a569b724
commit 9bf9b2f3d8
158 changed files with 302 additions and 302 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

@@ -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 ... 2.978909 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 16.384000 16.384000
1 384.0 7.372800 ... 8.507077 7.899428
2 512.0 14.563555 ... 15.420235 15.420235
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
4 768.0 32.768000 ... 34.028308 32.768000
5 896.0 37.971025 ... 39.025776 37.971025
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 ... 66.485074 66.485074
10 1536.0 80.430545 ... 79.526831 79.526831
9 1408.0 64.138541 ... 67.305878 65.684049
10 1536.0 79.526831 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.512412 71.588687
13 1920.0 68.776119 ... 70.172588 70.172588
14 2048.0 73.584279 ... 76.959706 76.608294
13 1920.0 69.120002 ... 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 ... 76.809875 76.563695
17 2432.0 71.305746 ... 84.621881 84.877538
18 2560.0 77.833728 ... 81.310171 80.908642
19 2688.0 83.922689 ... 90.316801 89.888756
20 2816.0 83.233226 ... 83.074685 83.074685
21 2944.0 81.967162 ... 81.564701 82.373605
22 3072.0 82.420822 ... 88.335577 88.473602
23 3200.0 85.447263 ... 95.451158 94.955488
24 3328.0 83.226931 ... 84.795401 84.795401
25 3456.0 81.849303 ... 89.480098 91.304157
26 3584.0 87.381330 ... 90.549237 94.548254
27 3712.0 85.896254 ... 89.035062 90.650947
28 3840.0 80.901241 ... 86.130841 91.777595
29 3968.0 86.942599 ... 91.747320 86.849777
30 4096.0 93.924236 ... 88.446606 91.867031
16 2304.0 68.446623 ... 77.057651 76.563695
17 2432.0 71.305746 ... 85.393507 84.877538
18 2560.0 77.833728 ... 81.310171 80.511054
19 2688.0 84.295681 ... 89.888756 89.254248
20 2816.0 84.360174 ... 84.035084 82.602666
21 2944.0 82.646820 ... 82.784108 82.784108
22 3072.0 82.661468 ... 88.750943 88.335577
23 3200.0 83.333330 ... 95.665176 94.955488
24 3328.0 83.613586 ... 84.895397 84.695641
25 3456.0 82.350937 ... 91.304157 85.676480
26 3584.0 83.876297 ... 94.152243 86.958797
27 3712.0 85.675250 ... 88.483034 87.744698
28 3840.0 83.402717 ... 87.286505 90.947372
29 3968.0 87.660873 ... 90.859224 85.781326
30 4096.0 93.401342 ... 91.428970 91.304576
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 19.590 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 1.111 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>