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
2022-08-18 00:48:52 +00:00
parent f20cbb2743
commit db7b163cb5
163 changed files with 274 additions and 274 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

@@ -568,8 +568,8 @@ 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
1 384.0 7.372800 ... 8.507077 8.507077
0 256.0 2.978909 ... 2.978909 3.276800
1 384.0 7.372800 ... 7.899428 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
@@ -578,32 +578,32 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
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 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 69.467336 ... 70.530615 70.172588
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.061463 62.061463
12 1792.0 72.512412 ... 59.310944 71.588687
13 1920.0 69.120002 ... 70.530615 70.530615
14 2048.0 73.908442 ... 76.959706 76.959706
15 2176.0 83.500614 ... 85.998493 85.269692
16 2304.0 68.251065 ... 76.809875 76.076024
17 2432.0 71.305746 ... 75.118889 82.630777
18 2560.0 77.833728 ... 80.709358 80.908642
19 2688.0 83.004501 ... 89.464755 89.044730
20 2816.0 79.733474 ... 83.233226 82.602666
21 2944.0 82.237674 ... 82.646820 82.921853
22 3072.0 81.589488 ... 84.135370 88.473602
23 3200.0 84.099871 ... 94.955488 95.096582
24 3328.0 81.530349 ... 84.795401 84.596116
25 3456.0 81.974138 ... 91.407671 85.585527
26 3584.0 82.114517 ... 95.553020 90.458141
27 3712.0 80.627396 ... 86.044224 88.522238
28 3840.0 81.859361 ... 87.980905 91.398346
29 3968.0 85.841672 ... 91.885495 85.871877
30 4096.0 93.858555 ... 86.369197 84.254693
15 2176.0 83.155572 ... 86.367588 85.269692
16 2304.0 68.251065 ... 76.809875 76.319081
17 2432.0 71.305746 ... 82.388456 84.877538
18 2560.0 77.833728 ... 81.310171 81.108913
19 2688.0 83.552988 ... 89.044730 89.464755
20 2816.0 79.733474 ... 83.712490 82.446516
21 2944.0 81.698415 ... 81.832567 82.102191
22 3072.0 82.062468 ... 88.612060 89.170242
23 3200.0 82.262212 ... 93.704243 94.395283
24 3328.0 84.003845 ... 84.101981 83.905938
25 3456.0 79.508447 ... 84.775569 91.304157
26 3584.0 87.042978 ... 90.365811 97.522120
27 3712.0 85.601834 ... 87.208507 87.552452
28 3840.0 80.960466 ... 88.900318 90.095313
29 3968.0 88.873953 ... 85.271796 87.723894
30 4096.0 93.498941 ... 93.336389 86.258181
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 26.015 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.620 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>