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
2022-05-03 00:45:18 +00:00
parent 567aa8d4fc
commit af77440e1b
156 changed files with 280 additions and 280 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
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 ... 3.276800 2.978909
0 256.0 2.730667 ... 2.978909 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
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 ... 53.773130 52.428801
5 896.0 37.971025 ... 39.025776 37.971025
6 1024.0 49.932191 ... 52.428801 52.428801
7 1152.0 45.242181 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.109587
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 80.430545 ... 79.526831 78.643199
10 1536.0 79.526831 ... 79.526831 78.643199
11 1664.0 63.372618 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.512412 71.588687
13 1920.0 68.776119 ... 70.172588 70.172588
13 1920.0 69.120002 ... 70.172588 70.172588
14 2048.0 73.908442 ... 76.959706 76.608294
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.251065 ... 77.057651 76.563695
17 2432.0 71.305746 ... 85.653855 84.877538
18 2560.0 77.833728 ... 81.310171 80.709358
19 2688.0 83.552988 ... 89.888756 89.254248
20 2816.0 83.873477 ... 83.873477 83.392363
21 2944.0 82.509987 ... 82.373605 82.237674
22 3072.0 82.301023 ... 88.473602 88.335577
23 3200.0 83.989503 ... 95.522391 94.955488
24 3328.0 83.130825 ... 84.496824 84.496824
25 3456.0 82.604067 ... 88.014813 88.790274
26 3584.0 87.551500 ... 93.661869 97.628001
27 3712.0 85.748791 ... 91.230455 87.475786
28 3840.0 83.402717 ... 90.798032 91.247522
29 3968.0 89.921841 ... 86.480463 89.723483
30 4096.0 87.609482 ... 87.495257 93.206754
16 2304.0 68.446623 ... 77.057651 76.563695
17 2432.0 71.305746 ... 85.393507 84.877538
18 2560.0 77.833728 ... 81.715711 80.511054
19 2688.0 84.108772 ... 90.316801 89.254248
20 2816.0 83.074685 ... 84.035084 83.552120
21 2944.0 82.237674 ... 82.373605 82.237674
22 3072.0 82.360879 ... 88.473602 88.820552
23 3200.0 84.656085 ... 95.380032 94.814812
24 3328.0 83.034941 ... 85.096096 84.596116
25 3456.0 81.849303 ... 91.097818 90.994998
26 3584.0 85.715344 ... 91.099693 95.350361
27 3712.0 83.247783 ... 83.317214 85.896254
28 3840.0 84.809814 ... 89.912191 91.549669
29 3968.0 88.938731 ... 91.335278 88.423140
30 4096.0 93.629390 ... 92.436452 88.243079
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 29.048 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 18.180 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>