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
2022-05-05 00:44:03 +00:00
parent d420763e0b
commit 19398e6d8a
158 changed files with 286 additions and 286 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -563,43 +563,43 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
<img alt="03 matrix multiplication" class="sphx-glr-single-img" src="../../_images/sphx_glr_03-matrix-multiplication_001.png" />
<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
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 15.420235 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
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 45.242181 ... 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 80.430545
11 1664.0 63.372618 ... 63.372618 63.372618
12 1792.0 72.983276 ... 63.499573 63.142831
13 1920.0 69.120002 ... 71.626943 70.892307
14 2048.0 73.262953 ... 78.033565 77.672296
15 2176.0 83.155572 ... 87.115360 86.739860
16 2304.0 68.251065 ... 78.064941 77.558029
17 2432.0 71.305746 ... 75.726318 75.522751
18 2560.0 77.833728 ... 82.125311 82.125311
19 2688.0 83.552988 ... 90.316801 90.966561
20 2816.0 83.233226 ... 83.233226 84.278666
21 2944.0 81.166173 ... 83.617504 84.182483
22 3072.0 81.825298 ... 89.451983 89.451983
23 3200.0 83.989503 ... 96.530922 94.256261
24 3328.0 83.905938 ... 86.946008 86.217120
25 3456.0 80.300370 ... 92.350019 88.497878
26 3584.0 87.381330 ... 98.053863 99.463928
27 3712.0 85.528545 ... 87.629253 88.326564
28 3840.0 82.716526 ... 88.971840 91.625518
29 3968.0 87.004591 ... 92.652949 85.841672
30 4096.0 93.727466 ... 89.092421 87.495257
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 256.0 2.730667 ... 2.978909 3.276800
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 ... 57.690139 57.690139
9 1408.0 64.138541 ... 69.009825 68.147202
10 1536.0 80.430545 ... 80.430545 80.430545
11 1664.0 62.929456 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.499573 63.142831
13 1920.0 68.776119 ... 71.257735 71.257735
14 2048.0 73.584279 ... 78.398206 78.033565
15 2176.0 83.500614 ... 87.115360 86.739860
16 2304.0 68.251065 ... 78.320893 77.810656
17 2432.0 71.305746 ... 75.726318 75.522751
18 2560.0 77.833728 ... 82.331658 81.715711
19 2688.0 83.552988 ... 90.966561 90.966561
20 2816.0 82.602666 ... 84.687779 84.523664
21 2944.0 82.921853 ... 83.758038 84.182483
22 3072.0 82.181572 ... 89.170242 88.197981
23 3200.0 81.321474 ... 95.238096 94.395283
24 3328.0 82.939284 ... 86.320498 85.908470
25 3456.0 80.140726 ... 87.727494 91.407671
26 3584.0 87.381330 ... 100.128496 99.684470
27 3712.0 83.247783 ... 87.629253 89.194055
28 3840.0 84.228485 ... 92.236860 85.533390
29 3968.0 91.885495 ... 85.093402 90.589410
30 4096.0 91.616198 ... 93.792965 91.242506
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 7.255 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 44.529 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>