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
2022-08-21 00:48:50 +00:00
parent b4367e5d30
commit 76917619fc
165 changed files with 286 additions and 286 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
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 ... 3.276800 2.978909
0 256.0 2.978909 ... 2.978909 2.978909
1 384.0 7.372800 ... 8.507077 7.899428
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
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 56.109587
9 1408.0 64.138541 ... 66.485074 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 ... 72.047592 71.588687
13 1920.0 69.120002 ... 70.530615 70.530615
14 2048.0 73.908442 ... 76.959706 76.959706
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 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.512412 72.047592
13 1920.0 69.120002 ... 70.530615 70.172588
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.500614 ... 86.367588 85.632545
16 2304.0 68.251065 ... 76.809875 76.563695
17 2432.0 71.305746 ... 85.393507 84.877538
18 2560.0 78.019048 ... 80.709358 80.709358
19 2688.0 83.369354 ... 90.102270 89.464755
20 2816.0 82.446516 ... 82.213395 82.135981
21 2944.0 82.102191 ... 83.198715 82.921853
22 3072.0 81.589488 ... 87.651868 82.721850
23 3200.0 80.402009 ... 95.025983 94.955488
24 3328.0 83.323259 ... 81.254285 83.710812
25 3456.0 81.849303 ... 90.281712 90.994998
26 3584.0 84.033077 ... 91.563533 97.416461
27 3712.0 85.601834 ... 89.114488 87.246590
28 3840.0 84.356981 ... 87.080314 91.398346
29 3968.0 87.035620 ... 91.403695 84.797731
30 4096.0 93.596744 ... 91.335643 87.267706
16 2304.0 68.251065 ... 77.057651 76.076024
17 2432.0 71.305746 ... 74.719317 84.877538
18 2560.0 77.833728 ... 80.908642 80.511054
19 2688.0 83.737433 ... 89.254248 89.888756
20 2816.0 81.369790 ... 82.290955 83.233226
21 2944.0 81.832567 ... 81.564701 82.509987
22 3072.0 82.661468 ... 88.335577 88.060814
23 3200.0 83.009080 ... 95.522391 95.238096
24 3328.0 82.843841 ... 84.052885 84.200347
25 3456.0 80.140726 ... 91.200871 90.892410
26 3584.0 86.540320 ... 94.647779 94.997774
27 3712.0 85.019017 ... 87.475786 87.706180
28 3840.0 84.036474 ... 91.247522 89.295115
29 3968.0 91.540836 ... 83.921126 91.198760
30 4096.0 86.202781 ... 86.480498 91.118618
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 26.004 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 25.100 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>