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
2022-08-01 00:51:04 +00:00
parent 57b5951fdb
commit 54ca5217e0
163 changed files with 298 additions and 298 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
v1.1.2/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -568,42 +568,42 @@ 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 ... 3.276800 3.276800
0 256.0 2.978909 ... 3.276800 2.978909
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 39.025776 ... 39.025776 39.025776
4 768.0 32.768000 ... 34.028308 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
7 1152.0 45.242181 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.109587
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.061463 62.061463
12 1792.0 72.512412 ... 72.047592 71.588687
13 1920.0 69.120002 ... 70.530615 70.172588
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.500614 ... 85.632545 85.269692
16 2304.0 68.251065 ... 76.319081 76.809875
17 2432.0 71.305746 ... 74.918570 83.366361
18 2560.0 78.019048 ... 81.310171 81.108913
19 2688.0 83.369354 ... 90.316801 89.464755
20 2816.0 79.733474 ... 82.135981 83.392363
21 2944.0 82.784108 ... 81.967162 81.832567
22 3072.0 81.648313 ... 85.662786 88.750943
23 3200.0 79.701121 ... 91.822093 91.298148
24 3328.0 80.798314 ... 84.101981 85.602017
25 3456.0 81.766291 ... 90.994998 90.994998
26 3584.0 84.825838 ... 87.124679 94.947616
27 3712.0 85.309435 ... 87.475786 88.640059
28 3840.0 84.744825 ... 91.968402 86.197974
29 3968.0 92.864488 ... 83.866153 90.859224
30 4096.0 86.202781 ... 86.844210 91.741443
7 1152.0 45.242181 ... 47.396572 46.656000
8 1280.0 51.200001 ... 56.888887 56.888887
9 1408.0 64.138541 ... 67.305878 67.305878
10 1536.0 80.430545 ... 80.430545 79.526831
11 1664.0 62.929456 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.512412 72.047592
13 1920.0 69.120002 ... 70.530615 70.530615
14 2048.0 73.908442 ... 76.959706 76.959706
15 2176.0 83.500614 ... 85.998493 85.269692
16 2304.0 68.251065 ... 76.809875 76.563695
17 2432.0 71.305746 ... 74.719317 84.877538
18 2560.0 77.833728 ... 81.310171 81.108913
19 2688.0 83.369354 ... 89.044730 88.422041
20 2816.0 78.868366 ... 83.074685 83.074685
21 2944.0 80.380696 ... 82.646820 82.921853
22 3072.0 81.943708 ... 83.146995 88.335577
23 3200.0 84.099871 ... 95.808380 94.814812
24 3328.0 83.710812 ... 84.995628 84.546440
25 3456.0 81.683457 ... 90.079964 89.183149
26 3584.0 84.229877 ... 90.367227 97.100854
27 3712.0 85.528545 ... 88.404730 87.094458
28 3840.0 82.716526 ... 86.332554 91.322872
29 3968.0 85.750244 ... 91.130650 85.751184
30 4096.0 93.466385 ... 92.309303 87.267706
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 14.452 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.435 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>