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
2022-08-10 00:48:34 +00:00
parent 24ae9b82dd
commit 4b51054036
165 changed files with 288 additions and 288 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
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 2.978909
0 256.0 2.730667 ... 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 ... 34.028308 34.028308
5 896.0 39.025776 ... 40.140799 39.025776
5 896.0 39.025776 ... 39.025776 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
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 ... 79.526831 79.526831
11 1664.0 63.372618 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.512412 72.047592
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 68.776119 ... 70.172588 70.172588
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.500614 ... 85.998493 85.632545
14 2048.0 73.908442 ... 76.959706 76.959706
15 2176.0 83.500614 ... 86.367588 85.632545
16 2304.0 68.251065 ... 76.809875 76.563695
17 2432.0 71.305746 ... 74.719317 84.877538
18 2560.0 77.833728 ... 81.512437 81.108913
19 2688.0 83.369354 ... 89.044730 88.628636
20 2816.0 83.552120 ... 83.233226 83.233226
21 2944.0 82.237674 ... 83.198715 82.102191
22 3072.0 81.943708 ... 88.060814 89.030036
23 3200.0 84.210524 ... 94.955488 95.238096
24 3328.0 83.419811 ... 84.397770 84.200347
25 3456.0 81.353753 ... 91.407671 85.630979
26 3584.0 85.633710 ... 93.661869 95.553020
27 3712.0 83.386762 ... 87.246590 86.942857
28 3840.0 83.497171 ... 90.242349 88.156237
29 3968.0 91.266964 ... 86.175099 89.394823
30 4096.0 88.592559 ... 93.045216 89.240508
17 2432.0 71.305746 ... 85.393507 84.367759
18 2560.0 77.833728 ... 81.310171 80.908642
19 2688.0 83.369354 ... 88.836198 89.464755
20 2816.0 79.733474 ... 83.552120 82.602666
21 2944.0 82.237674 ... 83.060049 81.298583
22 3072.0 79.638683 ... 88.473602 87.924073
23 3200.0 84.656085 ... 95.665176 95.238096
24 3328.0 84.003845 ... 84.695641 83.516586
25 3456.0 81.849303 ... 84.508982 88.790274
26 3584.0 86.958797 ... 98.591437 94.548254
27 3712.0 85.019017 ... 85.748791 86.716441
28 3840.0 85.005380 ... 86.164395 88.615388
29 3968.0 92.793868 ... 85.093402 90.926929
30 4096.0 88.592559 ... 86.480498 93.045216
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 21.974 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 22.058 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>