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
2022-09-13 00:54:01 +00:00
parent a81d78b680
commit 9fd9c56321
165 changed files with 270 additions and 270 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 ... 2.978909 2.978909
0 256.0 2.730667 ... 3.276800 2.978909
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 39.025776 ... 40.140799 39.025776
6 1024.0 51.150050 ... 53.092457 52.428801
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 ... 67.305878 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 ... 62.441243 62.441243
13 1920.0 69.120002 ... 70.172588 70.172588
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.500614 ... 86.367588 85.632545
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 ... 74.719317 83.614477
18 2560.0 78.019048 ... 80.709358 80.313727
19 2688.0 83.922689 ... 88.628636 88.628636
20 2816.0 79.298560 ... 83.552120 83.233226
21 2944.0 80.510553 ... 81.967162 82.102191
22 3072.0 81.825298 ... 88.335577 88.197981
23 3200.0 84.321474 ... 87.549434 95.238096
24 3328.0 82.748617 ... 80.437202 83.808259
25 3456.0 81.766291 ... 91.304157 90.687926
26 3584.0 83.177979 ... 94.647779 97.628001
27 3712.0 85.455380 ... 86.192706 88.640059
28 3840.0 80.110103 ... 90.649182 85.996889
29 3968.0 91.747320 ... 78.421554 83.578035
30 4096.0 91.491294 ... 82.190894 84.334104
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
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 26.600 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 23.466 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>