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
2022-04-29 00:42:56 +00:00
parent e7903f3c77
commit ea296daf2a
156 changed files with 268 additions and 268 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -564,42 +564,42 @@ 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 ... 3.276800 3.276800
1 384.0 7.372800 ... 7.899428 8.507077
2 512.0 14.563555 ... 15.420235 15.420235
2 512.0 14.563555 ... 16.384000 16.384000
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 31.597714 ... 35.389441 34.028308
5 896.0 37.971025 ... 40.140799 40.140799
4 768.0 32.768000 ... 35.389441 34.028308
5 896.0 37.971025 ... 41.321411 40.140799
6 1024.0 49.932191 ... 53.773130 53.773130
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 68.147202
10 1536.0 80.430545 ... 80.430545 80.430545
11 1664.0 62.929456 ... 63.372618 62.929456
10 1536.0 79.526831 ... 79.526831 80.430545
11 1664.0 62.929456 ... 63.372618 63.372618
12 1792.0 72.983276 ... 63.499573 63.142831
13 1920.0 69.120002 ... 71.626943 71.257735
14 2048.0 73.584279 ... 78.033565 77.672296
15 2176.0 83.155572 ... 87.115360 86.739860
16 2304.0 68.251065 ... 77.810656 77.558029
17 2432.0 71.305746 ... 75.320281 75.320281
18 2560.0 77.833728 ... 82.539044 82.125311
19 2688.0 83.922689 ... 90.966561 90.532356
20 2816.0 83.233226 ... 84.035084 83.552120
21 2944.0 82.102191 ... 83.337844 84.182483
22 3072.0 81.005868 ... 90.020831 89.451983
23 3200.0 84.880639 ... 96.385543 95.238096
24 3328.0 83.905938 ... 84.995628 85.297742
25 3456.0 81.108217 ... 86.689860 89.380896
26 3584.0 86.540320 ... 99.244365 99.684470
27 3712.0 82.287760 ... 85.163978 86.942857
28 3840.0 84.842346 ... 87.355452 92.468225
29 3968.0 87.097744 ... 92.163097 84.504108
30 4096.0 93.271527 ... 93.077479 87.324485
13 1920.0 68.776119 ... 71.257735 70.892307
14 2048.0 73.262953 ... 78.033565 77.672296
15 2176.0 83.155572 ... 87.494120 86.739860
16 2304.0 68.446623 ... 78.064941 77.558029
17 2432.0 71.305746 ... 75.522751 75.320281
18 2560.0 77.833728 ... 82.331658 82.125311
19 2688.0 84.108772 ... 90.748936 90.532356
20 2816.0 83.233226 ... 83.873477 83.873477
21 2944.0 81.967162 ... 83.899046 84.182483
22 3072.0 81.707223 ... 88.890270 89.877939
23 3200.0 84.656085 ... 96.385543 96.240602
24 3328.0 83.226931 ... 84.995628 84.795401
25 3456.0 82.773682 ... 92.033756 89.779026
26 3584.0 86.540320 ... 95.148565 96.372338
27 3712.0 84.301560 ... 87.629253 88.248537
28 3840.0 81.079177 ... 88.050954 91.777595
29 3968.0 87.913500 ... 91.575185 84.915752
30 4096.0 92.500158 ... 88.011627 88.011627
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 49.071 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 14.105 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>