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
2022-03-03 00:42:21 +00:00
parent 014137b675
commit 80b92a0d2d
158 changed files with 272 additions and 272 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
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 ... 2.978909 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
0 256.0 2.730667 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 7.899428
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
5 896.0 37.971025 ... 40.140799 39.025776
6 1024.0 51.150050 ... 53.773130 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 79.526831
10 1536.0 80.430545 ... 79.526831 79.526831
11 1664.0 62.929456 ... 62.492442 62.061463
12 1792.0 72.512412 ... 72.512412 71.588687
13 1920.0 69.120002 ... 70.530615 69.818184
12 1792.0 72.983276 ... 71.588687 71.588687
13 1920.0 69.120002 ... 70.172588 70.172588
14 2048.0 73.584279 ... 76.608294 76.260072
15 2176.0 83.155572 ... 86.367588 85.632545
16 2304.0 68.446623 ... 77.057651 76.563695
17 2432.0 71.305746 ... 85.653855 84.877538
18 2560.0 78.019048 ... 81.108913 80.908642
19 2688.0 83.186525 ... 88.836198 89.254248
20 2816.0 82.916747 ... 83.392363 82.290955
21 2944.0 81.166173 ... 82.784108 82.921853
22 3072.0 81.707223 ... 88.335577 88.060814
23 3200.0 84.432717 ... 95.096582 94.674553
24 3328.0 83.034941 ... 84.845369 84.695641
25 3456.0 82.773682 ... 87.632137 90.994998
26 3584.0 87.679562 ... 93.661869 97.416461
27 3712.0 85.601834 ... 87.246581 88.797643
28 3840.0 79.562590 ... 87.424508 91.549669
29 3968.0 87.976885 ... 91.130650 83.750126
30 4096.0 92.755862 ... 88.301134 90.079009
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.446623 ... 76.809875 76.563695
17 2432.0 71.305746 ... 82.874527 84.877538
18 2560.0 78.019048 ... 80.709358 80.511054
19 2688.0 83.369354 ... 89.044730 89.676257
20 2816.0 83.233226 ... 82.916747 82.602666
21 2944.0 81.832567 ... 80.640830 82.169877
22 3072.0 82.181572 ... 88.473602 88.473602
23 3200.0 84.768213 ... 95.096582 94.395283
24 3328.0 82.939284 ... 81.346098 84.695641
25 3456.0 81.932484 ... 90.180725 91.097818
26 3584.0 87.085130 ... 98.268190 93.564405
27 3712.0 83.317214 ... 88.443865 83.947349
28 3840.0 84.874902 ... 91.322872 84.421376
29 3968.0 90.388098 ... 84.210698 88.615785
30 4096.0 86.480498 ... 92.948562 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 43.135 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 51.135 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>