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
2022-08-31 00:55:11 +00:00
parent bbcfff8e7c
commit cb05587449
165 changed files with 292 additions and 292 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
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 ... 3.276800 3.276800
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 16.384000 16.384000
0 256.0 2.978909 ... 3.276800 3.276800
1 384.0 7.372800 ... 7.899428 8.507077
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 39.025776
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 45.242181 ... 48.161033 48.161033
5 896.0 39.025776 ... 40.140799 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
7 1152.0 45.242181 ... 47.396572 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 ... 68.147202 67.305878
10 1536.0 80.430545 ... 81.355034 78.643199
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 70.892307
14 2048.0 73.584279 ... 78.398206 77.314362
15 2176.0 83.500614 ... 87.876193 85.632545
16 2304.0 68.446623 ... 78.064941 77.307030
13 1920.0 69.120002 ... 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 68.446623 ... 78.064941 76.809875
17 2432.0 71.305746 ... 85.915795 84.621881
18 2560.0 78.019048 ... 82.331658 81.715711
19 2688.0 83.552988 ... 90.532356 89.044730
20 2816.0 81.521884 ... 84.197315 80.767055
21 2944.0 82.646820 ... 82.784108 82.784108
22 3072.0 81.589488 ... 89.240511 88.335577
23 3200.0 84.544253 ... 96.096095 93.841640
24 3328.0 81.530349 ... 84.695641 84.795401
25 3456.0 81.518272 ... 91.719645 90.892410
26 3584.0 84.825838 ... 92.126428 94.647779
27 3712.0 85.748791 ... 83.456425 84.159518
28 3840.0 84.679936 ... 93.960918 84.548438
29 3968.0 92.512459 ... 84.974886 91.643962
30 4096.0 88.534120 ... 85.380235 92.182504
18 2560.0 78.019048 ... 82.539044 81.310171
19 2688.0 83.369354 ... 90.748936 89.254248
20 2816.0 79.733474 ... 84.197315 83.712490
21 2944.0 79.610276 ... 83.060049 82.102191
22 3072.0 82.301023 ... 89.451983 88.197981
23 3200.0 85.447263 ... 97.116842 95.380032
24 3328.0 83.178850 ... 85.196803 84.695641
25 3456.0 82.688790 ... 84.909497 81.274299
26 3584.0 87.381330 ... 98.375705 98.591437
27 3712.0 82.423549 ... 89.035062 87.552452
28 3840.0 82.716526 ... 85.930069 90.058629
29 3968.0 87.913500 ... 91.678389 85.212248
30 4096.0 93.206754 ... 86.230472 89.958266
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 14.622 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 16.811 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>