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
2022-08-17 00:49:36 +00:00
parent d1343b5511
commit f20cbb2743
167 changed files with 326 additions and 311 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
master/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
<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 2.978909 ... 2.978909 3.276800
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
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 39.025776 ... 40.140799 39.025776
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 48.161033
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 67.305878
10 1536.0 80.430545 ... 81.355034 79.526831
9 1408.0 64.138541 ... 69.009825 68.147202
10 1536.0 80.430545 ... 80.430545 78.643199
11 1664.0 62.929456 ... 63.372618 62.492442
12 1792.0 72.512412 ... 73.460287 59.467852
13 1920.0 68.776119 ... 71.257735 71.257735
12 1792.0 72.983276 ... 73.460287 59.467852
13 1920.0 69.120002 ... 71.626943 71.257735
14 2048.0 73.908442 ... 78.398206 77.314362
15 2176.0 83.500614 ... 87.876193 86.367588
16 2304.0 68.446623 ... 77.810656 77.307030
17 2432.0 71.305746 ... 86.711310 85.653855
18 2560.0 77.833728 ... 82.956960 81.108913
19 2688.0 83.369354 ... 90.316801 90.102270
20 2816.0 79.587973 ... 84.687779 83.153880
21 2944.0 81.967162 ... 83.617504 81.967162
22 3072.0 81.707223 ... 90.020831 88.060814
23 3200.0 83.879425 ... 95.238096 87.673110
24 3328.0 83.226931 ... 82.748617 84.895397
25 3456.0 81.353753 ... 88.207407 91.200871
26 3584.0 87.296493 ... 99.354022 97.628001
27 3712.0 82.421427 ... 89.353616 83.247783
28 3840.0 83.339866 ... 91.398346 86.840987
29 3968.0 86.849777 ... 92.302520 84.066569
30 4096.0 93.077479 ... 83.055527 82.340585
15 2176.0 83.155572 ... 87.876193 85.998493
16 2304.0 68.446623 ... 78.064941 77.307030
17 2432.0 71.305746 ... 86.179335 85.653855
18 2560.0 77.833728 ... 82.539044 81.310171
19 2688.0 83.737433 ... 90.532356 89.676257
20 2816.0 80.767055 ... 83.873477 81.674548
21 2944.0 82.237674 ... 83.477440 82.373605
22 3072.0 81.707223 ... 89.877939 88.197981
23 3200.0 84.544253 ... 96.822991 94.814812
24 3328.0 83.226931 ... 85.398926 84.895397
25 3456.0 81.766291 ... 91.511426 86.503829
26 3584.0 83.876297 ... 95.756542 95.350361
27 3712.0 84.159518 ... 88.837126 87.937800
28 3840.0 85.070769 ... 93.326587 85.663823
29 3968.0 91.198760 ... 87.097744 91.609561
30 4096.0 86.204508 ... 93.792965 89.240508
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 16.663 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 38.507 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>