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
2022-06-25 00:46:57 +00:00
parent 08c4b2c3be
commit 37abd97851
159 changed files with 264 additions and 264 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -565,42 +565,42 @@ 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
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 15.420235 15.420235
0 256.0 2.730667 ... 3.276800 2.978909
1 384.0 7.372800 ... 7.899428 8.507077
2 512.0 14.563555 ... 15.420235 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
4 768.0 32.768000 ... 35.389441 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 45.242181 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 68.147202 65.684049
10 1536.0 79.526831 ... 81.355034 78.643199
11 1664.0 62.929456 ... 63.372618 62.492442
9 1408.0 64.138541 ... 68.147202 66.485074
10 1536.0 79.526831 ... 80.430545 78.643199
11 1664.0 63.372618 ... 63.372618 62.492442
12 1792.0 72.983276 ... 73.460287 59.467852
13 1920.0 69.120002 ... 71.257735 71.257735
14 2048.0 73.584279 ... 78.398206 77.314362
15 2176.0 83.500614 ... 87.494120 85.998493
16 2304.0 68.446623 ... 78.064941 77.057651
17 2432.0 71.305746 ... 86.711310 85.393507
18 2560.0 77.833728 ... 82.956960 81.512437
19 2688.0 83.369354 ... 90.316801 89.254248
20 2816.0 83.873477 ... 84.035084 82.916747
21 2944.0 82.646820 ... 82.237674 81.034195
22 3072.0 82.301023 ... 89.735509 86.579673
23 3200.0 84.880639 ... 96.096095 94.674553
24 3328.0 83.905938 ... 85.602017 84.995628
25 3456.0 82.015834 ... 91.928814 88.595129
26 3584.0 86.540320 ... 96.579370 87.042978
27 3712.0 85.675250 ... 89.835744 87.552452
28 3840.0 83.528704 ... 87.841141 89.548180
29 3968.0 86.053553 ... 92.442373 87.035620
30 4096.0 93.792965 ... 85.055593 85.271746
13 1920.0 69.467336 ... 71.257735 70.892307
14 2048.0 73.262953 ... 78.398206 77.314362
15 2176.0 83.500614 ... 87.494120 86.367588
16 2304.0 68.446623 ... 78.064941 77.307030
17 2432.0 71.305746 ... 86.711310 75.118889
18 2560.0 77.833728 ... 82.125311 81.512437
19 2688.0 83.737433 ... 91.185232 89.254248
20 2816.0 80.617762 ... 84.523664 83.074685
21 2944.0 80.767437 ... 83.060049 82.509987
22 3072.0 81.121923 ... 89.310890 87.381335
23 3200.0 84.656085 ... 96.969694 95.380032
24 3328.0 83.226931 ... 85.908470 84.101981
25 3456.0 81.766291 ... 87.158452 81.026701
26 3584.0 87.000867 ... 98.808123 97.153313
27 3712.0 82.355598 ... 89.114488 82.593917
28 3840.0 84.615146 ... 92.934455 84.552479
29 3968.0 91.816356 ... 87.097744 91.540836
30 4096.0 86.482237 ... 89.777746 91.491294
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 5.069 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 4.553 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>