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
2022-07-14 07:22:19 +00:00
parent 3e815114fd
commit d1c6625bfd
179 changed files with 2617 additions and 369 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -115,6 +115,8 @@
</li>
<li class="toctree-l2"><a class="reference internal" href="04-low-memory-dropout.html">Low-Memory Dropout</a></li>
<li class="toctree-l2"><a class="reference internal" href="05-layer-norm.html">Layer Normalization</a></li>
<li class="toctree-l2"><a class="reference internal" href="06-fused-attention.html">Fused Attention</a></li>
<li class="toctree-l2"><a class="reference internal" href="07-libdevice-function.html">Libdevice function</a></li>
</ul>
</li>
</ul>
@@ -565,42 +567,42 @@ 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 2.730667 ... 3.276800 2.978909
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 15.420235 15.420235
2 512.0 14.563555 ... 16.384000 15.420235
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 39.025776
5 896.0 39.025776 ... 40.140799 39.025776
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 45.242181 ... 48.161033 47.396572
7 1152.0 45.242181 ... 47.396572 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 68.147202 65.684049
10 1536.0 79.526831 ... 81.355034 78.643199
11 1664.0 63.372618 ... 63.372618 62.492442
9 1408.0 64.138541 ... 68.147202 66.485074
10 1536.0 80.430545 ... 80.430545 78.643199
11 1664.0 62.929456 ... 63.372618 62.492442
12 1792.0 72.983276 ... 72.983276 59.154861
13 1920.0 68.776119 ... 71.626943 70.892307
14 2048.0 73.584279 ... 78.033565 76.959706
15 2176.0 83.155572 ... 87.494120 86.367588
16 2304.0 68.446623 ... 78.064941 77.057651
17 2432.0 71.305746 ... 86.179335 85.393507
18 2560.0 77.833728 ... 82.956960 81.715711
19 2688.0 83.737433 ... 91.185232 89.464755
20 2816.0 82.446516 ... 84.523664 83.712490
21 2944.0 81.967162 ... 83.758038 82.373605
22 3072.0 82.420822 ... 88.750943 86.579673
23 3200.0 81.528664 ... 91.233074 95.665176
24 3328.0 83.516586 ... 85.908470 83.323259
25 3456.0 81.435930 ... 92.138932 90.180725
26 3584.0 83.954614 ... 91.189190 95.858629
27 3712.0 85.822459 ... 83.806497 87.783251
28 3840.0 80.901241 ... 89.259080 89.548180
29 3968.0 87.913500 ... 92.829164 84.096442
30 4096.0 93.825748 ... 89.299883 90.139506
13 1920.0 69.120002 ... 71.257735 71.257735
14 2048.0 73.584279 ... 78.398206 77.314362
15 2176.0 83.155572 ... 87.494120 85.998493
16 2304.0 68.446623 ... 78.320893 77.558029
17 2432.0 71.305746 ... 86.711310 75.421383
18 2560.0 77.833728 ... 82.747477 81.715711
19 2688.0 83.552988 ... 90.532356 89.464755
20 2816.0 84.197315 ... 84.035084 84.035084
21 2944.0 82.784108 ... 83.969728 83.060049
22 3072.0 81.825298 ... 89.593522 88.473602
23 3200.0 84.768213 ... 96.096095 95.808380
24 3328.0 83.226931 ... 85.908470 84.596116
25 3456.0 81.766291 ... 91.824110 91.097818
26 3584.0 87.466332 ... 91.194972 94.847460
27 3712.0 85.822459 ... 87.246590 87.860458
28 3840.0 81.859361 ... 87.011801 90.168771
29 3968.0 89.921841 ... 91.954739 85.271796
30 4096.0 93.596744 ... 88.243079 90.382307
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 52.578 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 13.827 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>