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
2022-04-21 00:45:25 +00:00
parent 8d0e47d73e
commit ab04e47bf2
158 changed files with 312 additions and 312 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
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
1 384.0 7.372800 ... 7.899428 8.507077
2 512.0 14.563555 ... 16.384000 16.384000
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 16.384000
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 35.389441 34.028308
5 896.0 37.971025 ... 40.140799 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 ... 58.514284 57.690139
9 1408.0 64.138541 ... 69.009825 69.009825
10 1536.0 79.526831 ... 80.430545 80.430545
4 768.0 32.768000 ... 34.028308 34.028308
5 896.0 37.971025 ... 41.321411 40.140799
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 44.566925 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 69.009825 68.147202
10 1536.0 80.430545 ... 80.430545 79.526831
11 1664.0 62.929456 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.142831 62.790080
13 1920.0 68.776119 ... 71.626943 71.257735
14 2048.0 73.584279 ... 78.398206 78.033565
12 1792.0 72.983276 ... 63.499573 62.790080
13 1920.0 69.120002 ... 71.626943 70.892307
14 2048.0 73.262953 ... 78.033565 78.033565
15 2176.0 83.155572 ... 87.115360 86.739860
16 2304.0 68.446623 ... 77.810656 77.558029
17 2432.0 71.125224 ... 75.726318 75.320281
18 2560.0 77.833728 ... 82.125311 81.715711
19 2688.0 83.369354 ... 90.532356 90.748936
20 2816.0 80.916902 ... 83.552120 83.552120
21 2944.0 82.373605 ... 83.617504 83.617504
22 3072.0 81.707223 ... 87.651868 89.593522
23 3200.0 85.219705 ... 96.385543 96.385543
24 3328.0 82.275764 ... 86.011103 85.703924
25 3456.0 81.890873 ... 92.455926 92.138932
26 3584.0 86.623693 ... 89.290361 94.250936
27 3712.0 85.675250 ... 88.092894 84.874549
28 3840.0 84.679936 ... 92.468225 85.136259
29 3968.0 90.724116 ... 84.974886 90.522206
30 4096.0 90.996029 ... 87.438257 92.309303
16 2304.0 68.446623 ... 77.558029 77.307030
17 2432.0 71.125224 ... 75.726318 74.918570
18 2560.0 77.833728 ... 82.331658 81.715711
19 2688.0 83.369354 ... 91.404957 91.185232
20 2816.0 79.733474 ... 83.873477 83.392363
21 2944.0 82.102191 ... 83.758038 84.182483
22 3072.0 81.296638 ... 88.473602 87.516392
23 3200.0 79.750779 ... 96.168294 95.952022
24 3328.0 82.939284 ... 86.528001 85.602017
25 3456.0 82.688790 ... 92.455926 86.689860
26 3584.0 86.291162 ... 88.152348 94.250936
27 3712.0 85.675250 ... 87.706180 87.246590
28 3840.0 81.079177 ... 86.875096 91.398346
29 3968.0 87.035620 ... 89.525997 84.917596
30 4096.0 88.243079 ... 85.161847 91.616198
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 10.290 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 2.101 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>