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
2022-04-10 00:41:56 +00:00
parent 226c24346e
commit be39c1e8bc
156 changed files with 292 additions and 292 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
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 2.730667 ... 2.978909 2.978909
0 256.0 2.730667 ... 3.276800 2.978909
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 16.384000 16.384000
3 640.0 22.260869 ... 24.380953 24.380953
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
6 1024.0 49.932191 ... 52.428801 52.428801
7 1152.0 45.242181 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.888887
9 1408.0 64.138541 ... 67.305878 67.305878
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 80.430545 ... 79.526831 79.526831
11 1664.0 63.372618 ... 62.492442 62.061463
12 1792.0 72.512412 ... 72.047592 71.588687
12 1792.0 72.983276 ... 59.154861 71.588687
13 1920.0 69.120002 ... 70.172588 70.172588
14 2048.0 73.908442 ... 76.959706 76.608294
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.251065 ... 76.563695 76.563695
17 2432.0 71.125224 ... 82.874527 84.115159
18 2560.0 77.833728 ... 81.310171 80.511054
19 2688.0 83.737433 ... 89.676257 89.044730
20 2816.0 83.552120 ... 83.074685 82.602666
21 2944.0 82.237674 ... 82.784108 82.784108
22 3072.0 81.825298 ... 87.651868 86.845249
23 3200.0 82.156612 ... 89.761569 88.275863
24 3328.0 79.548391 ... 80.527177 83.710812
25 3456.0 81.683457 ... 91.511426 91.097818
26 3584.0 85.552231 ... 90.549237 96.683219
27 3712.0 85.455380 ... 88.248537 88.640059
28 3840.0 82.778440 ... 87.252072 88.971840
29 3968.0 93.076994 ... 84.094627 91.335278
30 4096.0 86.590337 ... 86.480498 92.182504
16 2304.0 68.251065 ... 76.563695 76.319081
17 2432.0 71.305746 ... 84.877538 84.621881
18 2560.0 77.833728 ... 81.310171 80.709358
19 2688.0 83.737433 ... 89.464755 89.888756
20 2816.0 83.552120 ... 83.712490 82.916747
21 2944.0 81.967162 ... 80.902653 82.102191
22 3072.0 82.062468 ... 88.197981 87.924073
23 3200.0 84.544253 ... 95.380032 94.955488
24 3328.0 82.939284 ... 84.695641 81.162679
25 3456.0 80.061141 ... 82.183044 87.632137
26 3584.0 87.254137 ... 90.460980 94.349836
27 3712.0 85.601834 ... 89.194055 91.313847
28 3840.0 84.100380 ... 84.972723 88.686451
29 3968.0 93.148045 ... 79.236324 80.971427
30 4096.0 91.647477 ... 83.390136 89.181212
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 23.977 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 18.978 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>