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
2022-07-28 00:52:17 +00:00
parent 2663713aec
commit 6cffd02787
167 changed files with 298 additions and 298 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
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 2.978909 ... 3.276800 3.276800
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 15.420235 15.420235
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 ... 39.025776 39.025776
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 56.109587
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 46.656000
8 1280.0 51.200001 ... 56.888887 56.888887
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 63.372618 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.047592 71.588687
13 1920.0 68.776119 ... 70.172588 70.172588
14 2048.0 73.584279 ... 76.959706 76.608294
15 2176.0 83.155572 ... 86.367588 85.269692
16 2304.0 68.056616 ... 76.809875 76.563695
17 2432.0 71.125224 ... 83.864074 84.877538
18 2560.0 77.833728 ... 81.108913 80.908642
19 2688.0 83.552988 ... 89.888756 89.464755
20 2816.0 83.712490 ... 83.074685 82.446516
21 2944.0 81.967162 ... 82.237674 82.237674
22 3072.0 82.540970 ... 89.030036 89.451983
23 3200.0 84.432717 ... 96.240602 95.665176
24 3328.0 82.939284 ... 83.130825 84.795401
25 3456.0 81.932484 ... 91.615417 91.200871
26 3584.0 83.954614 ... 95.858629 98.483450
27 3712.0 82.491612 ... 87.937800 88.170647
28 3840.0 85.070769 ... 86.875096 91.473945
29 3968.0 87.066671 ... 91.472214 87.723894
30 4096.0 93.924229 ... 92.436452 89.299883
11 1664.0 62.929456 ... 62.061463 62.061463
12 1792.0 72.512412 ... 62.441243 62.441243
13 1920.0 69.120002 ... 70.530615 70.530615
14 2048.0 73.908442 ... 77.314362 76.959706
15 2176.0 83.155572 ... 86.367588 85.632545
16 2304.0 68.251065 ... 76.809875 76.563695
17 2432.0 71.305746 ... 74.918570 84.877538
18 2560.0 78.019048 ... 81.512437 80.511054
19 2688.0 83.737433 ... 90.316801 88.422041
20 2816.0 79.443003 ... 82.916747 83.392363
21 2944.0 82.237674 ... 82.373605 83.060049
22 3072.0 82.661468 ... 87.924073 87.584078
23 3200.0 84.432717 ... 95.238096 94.955488
24 3328.0 82.843841 ... 85.196803 85.602017
25 3456.0 78.502012 ... 85.133652 89.779026
26 3584.0 87.211821 ... 90.364394 97.522120
27 3712.0 86.192706 ... 86.754095 87.246590
28 3840.0 83.245767 ... 92.236860 84.036474
29 3968.0 92.512459 ... 83.866153 90.859224
30 4096.0 87.438257 ... 84.679957 90.169784
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 20.621 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 52.358 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>