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
2021-08-14 18:05:36 +00:00
parent 358fb209d7
commit 09be744d1d
31 changed files with 945 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -567,42 +567,42 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>matmul-performance:
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 128.0 0.455111 ... 0.512000 0.512000
1 256.0 2.978909 ... 2.978909 2.978909
1 256.0 2.730667 ... 3.276800 2.978909
2 384.0 7.372800 ... 8.507077 7.899428
3 512.0 14.563555 ... 16.384000 16.384000
4 640.0 22.260869 ... 24.380953 24.380953
5 768.0 32.768000 ... 34.028308 34.028308
6 896.0 39.025776 ... 40.140799 35.994954
6 896.0 39.025776 ... 39.025776 39.025776
7 1024.0 49.932191 ... 53.773130 52.428801
8 1152.0 44.566925 ... 46.656000 46.656000
9 1280.0 51.200001 ... 56.888887 56.888887
8 1152.0 45.242181 ... 46.656000 46.656000
9 1280.0 51.200001 ... 56.888887 56.109587
10 1408.0 64.138541 ... 64.902096 64.902096
11 1536.0 76.933564 ... 76.106321 76.106321
12 1664.0 63.372618 ... 61.217089 61.636381
13 1792.0 72.983276 ... 69.810085 69.379162
14 1920.0 67.434145 ... 70.172588 70.530615
15 2048.0 73.908442 ... 74.898285 74.898285
16 2176.0 83.500614 ... 80.173899 80.817862
17 2304.0 68.446623 ... 73.275679 73.275679
18 2432.0 71.125224 ... 81.908060 82.147552
19 2560.0 78.019048 ... 75.676673 76.027843
20 2688.0 83.369354 ... 83.369354 81.928846
21 2816.0 84.197315 ... 77.605356 79.733474
22 2944.0 80.122235 ... 77.385141 79.865439
23 3072.0 79.415291 ... 81.472093 82.782312
24 3200.0 83.879425 ... 89.136491 88.888888
25 3328.0 83.130825 ... 86.946008 84.298943
26 3456.0 81.849303 ... 81.932484 85.858966
27 3584.0 87.211821 ... 88.761490 91.563533
28 3712.0 85.896254 ... 82.152425 83.317214
29 3840.0 83.655065 ... 86.738820 87.493673
30 3968.0 93.219206 ... 87.535103 87.913500
31 4096.0 93.596744 ... 83.311685 90.810373
11 1536.0 80.430545 ... 76.106321 76.106321
12 1664.0 63.372618 ... 62.492442 62.492442
13 1792.0 72.983276 ... 69.810085 69.810085
14 1920.0 69.467336 ... 69.818184 69.818184
15 2048.0 73.584279 ... 75.234154 74.898285
16 2176.0 82.137338 ... 80.173899 80.494588
17 2304.0 68.251065 ... 73.275679 73.275679
18 2432.0 71.125224 ... 81.433227 81.908060
19 2560.0 77.833728 ... 76.560748 75.676673
20 2688.0 84.108772 ... 81.227100 83.186525
21 2816.0 83.712490 ... 79.298560 78.726003
22 2944.0 81.832567 ... 80.122235 78.979452
23 3072.0 80.890151 ... 80.890151 82.903517
24 3200.0 79.601989 ... 82.790959 88.765601
25 3328.0 84.101981 ... 82.843841 82.088138
26 3456.0 81.766291 ... 85.494768 83.806205
27 3584.0 85.879071 ... 95.553020 94.847460
28 3712.0 82.491612 ... 88.876645 83.386762
29 3840.0 81.138664 ... 82.285715 82.224536
30 3968.0 86.114283 ... 81.512316 88.167587
31 4096.0 93.662059 ... 90.079009 90.321484
[32 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 31.194 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 18.271 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>