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
2022-09-14 00:53:02 +00:00
parent 9fd9c56321
commit affd3325b2
163 changed files with 288 additions and 288 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
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 2.730667 ... 2.978909 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 16.384000 16.384000
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
5 896.0 39.025776 ... 39.025776 39.025776
6 1024.0 49.932191 ... 53.773130 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 70.530615
14 2048.0 73.908442 ... 76.959706 76.959706
15 2176.0 83.500614 ... 85.632545 85.632545
16 2304.0 68.446623 ... 76.563695 76.563695
17 2432.0 71.305746 ... 74.918570 84.877538
18 2560.0 77.833728 ... 81.108913 81.108913
19 2688.0 83.552988 ... 89.254248 89.464755
20 2816.0 79.587973 ... 82.916747 82.916747
21 2944.0 81.832567 ... 82.509987 82.509987
22 3072.0 82.062468 ... 87.651868 88.197981
23 3200.0 81.424937 ... 93.704243 92.352095
24 3328.0 84.003845 ... 84.895397 84.298943
25 3456.0 81.230800 ... 90.790053 87.489490
26 3584.0 85.633710 ... 96.166193 96.683219
27 3712.0 82.423549 ... 87.094458 87.706180
28 3840.0 83.402717 ... 91.134731 87.011801
29 3968.0 91.301109 ... 86.144680 89.394823
30 4096.0 86.592080 ... 93.206754 86.313653
12 1792.0 72.983276 ... 71.588687 71.588687
13 1920.0 68.776119 ... 70.530615 70.530615
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.500614 ... 85.998493 85.269692
16 2304.0 68.251065 ... 76.809875 76.563695
17 2432.0 71.305746 ... 74.719317 84.877538
18 2560.0 78.019048 ... 81.310171 81.108913
19 2688.0 83.552988 ... 89.995386 89.464755
20 2816.0 79.587973 ... 82.916747 82.602666
21 2944.0 82.102191 ... 82.646820 83.060049
22 3072.0 81.707223 ... 87.516392 88.060814
23 3200.0 80.402009 ... 87.551302 87.189747
24 3328.0 80.798314 ... 83.905938 84.596116
25 3456.0 82.688790 ... 91.252485 90.994998
26 3584.0 86.540320 ... 91.563533 95.350361
27 3712.0 82.491612 ... 86.867254 86.791782
28 3840.0 82.592983 ... 92.390975 86.400002
29 3968.0 93.254827 ... 85.093402 91.130650
30 4096.0 86.202781 ... 87.982773 89.210850
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 23.466 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 26.818 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>