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
2022-06-05 21:05:02 +00:00
parent a598db498f
commit fd3a9985ea
351 changed files with 43281 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
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 2.978909 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 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 32.768000 ... 34.028308 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
6 1024.0 49.932191 ... 52.428801 52.428801
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 45.242181 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.109587
8 1280.0 51.200001 ... 56.888887 56.888887
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 63.372618 ... 62.492442 62.061463
11 1664.0 63.372618 ... 62.929456 62.061463
12 1792.0 72.983276 ... 72.512412 71.588687
13 1920.0 69.120002 ... 70.530615 70.530615
13 1920.0 69.467336 ... 70.530615 70.530615
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.500614 ... 85.998493 85.269692
16 2304.0 68.056616 ... 77.307030 76.809875
15 2176.0 83.155572 ... 86.367588 84.909907
16 2304.0 68.446623 ... 77.307030 76.809875
17 2432.0 71.305746 ... 85.653855 84.877538
18 2560.0 77.833728 ... 81.310171 80.511054
19 2688.0 83.552988 ... 89.464755 89.044730
20 2816.0 82.759409 ... 83.873477 82.446516
21 2944.0 81.298583 ... 82.784108 83.060049
22 3072.0 82.661468 ... 89.451983 88.473602
23 3200.0 82.156612 ... 95.522391 94.814812
24 3328.0 84.003845 ... 81.254285 83.710812
25 3456.0 81.849303 ... 91.097818 91.097818
26 3584.0 87.893835 ... 92.696281 95.047985
27 3712.0 86.192706 ... 88.326564 90.445760
28 3840.0 81.859361 ... 90.798032 87.910967
29 3968.0 91.816356 ... 89.133631 91.403695
30 4096.0 86.563285 ... 89.418872 92.691803
18 2560.0 77.833728 ... 81.310171 80.709358
19 2688.0 83.737433 ... 89.888756 89.254248
20 2816.0 83.233226 ... 83.074685 83.392363
21 2944.0 82.715407 ... 83.198715 81.298583
22 3072.0 82.420822 ... 89.593522 89.170242
23 3200.0 84.544253 ... 96.096095 94.814812
24 3328.0 83.808259 ... 81.994643 84.496824
25 3456.0 82.604067 ... 91.511426 90.994998
26 3584.0 85.552231 ... 95.858629 98.483450
27 3712.0 83.317214 ... 90.939777 88.170647
28 3840.0 82.654712 ... 90.798032 87.011801
29 3968.0 89.855624 ... 87.158986 91.335278
30 4096.0 91.743400 ... 90.504200 93.206754
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 22.344 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 25.038 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>