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
2022-08-16 01:02:32 +00:00
parent 943e27aa53
commit d1343b5511
165 changed files with 306 additions and 306 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
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 2.730667 ... 2.978909 3.276800
1 384.0 7.372800 ... 8.507077 7.899428
0 256.0 2.978909 ... 2.978909 3.276800
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 ... 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 ... 48.161033 48.161033
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 79.526831
9 1408.0 64.138541 ... 69.009825 67.305878
10 1536.0 80.430545 ... 81.355034 79.526831
11 1664.0 62.929456 ... 63.372618 62.492442
12 1792.0 72.512412 ... 73.460287 59.467852
13 1920.0 69.120002 ... 71.626943 71.257735
13 1920.0 68.776119 ... 71.257735 71.257735
14 2048.0 73.908442 ... 78.398206 77.314362
15 2176.0 83.500614 ... 87.876193 86.367588
16 2304.0 68.251065 ... 77.810656 77.307030
17 2432.0 71.305746 ... 84.367759 75.320281
18 2560.0 78.019048 ... 82.539044 81.310171
19 2688.0 83.552988 ... 90.316801 89.254248
20 2816.0 79.154642 ... 83.873477 83.712490
21 2944.0 82.784108 ... 83.617504 83.337844
22 3072.0 81.707223 ... 86.978653 88.750943
23 3200.0 82.262212 ... 92.086332 87.611228
24 3328.0 81.622783 ... 83.808259 82.181847
25 3456.0 81.849303 ... 88.207407 90.281712
26 3584.0 86.874778 ... 98.483450 98.483450
27 3712.0 81.615477 ... 89.114488 87.629253
28 3840.0 81.919998 ... 88.121115 90.389865
29 3968.0 86.973584 ... 91.954739 86.053553
30 4096.0 93.401342 ... 83.106955 88.709668
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
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 37.352 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 16.663 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>