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
2022-04-25 00:41:43 +00:00
parent 1581cf9d79
commit 21613349ac
158 changed files with 316 additions and 316 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
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
1 384.0 7.372800 ... 8.507077 7.899428
2 512.0 14.563555 ... 15.420235 15.420235
0 256.0 2.978909 ... 2.978909 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
4 768.0 31.597714 ... 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
7 1152.0 44.566925 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.109587
9 1408.0 64.138541 ... 67.305878 65.684049
10 1536.0 79.526831 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.061463 62.061463
12 1792.0 72.983276 ... 72.047592 71.588687
13 1920.0 68.776119 ... 70.172588 70.172588
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 79.526831 ... 78.643199 78.643199
11 1664.0 62.929456 ... 62.061463 61.636381
12 1792.0 72.512412 ... 62.441243 62.096267
13 1920.0 69.120002 ... 70.172588 70.172588
14 2048.0 73.584279 ... 76.959706 76.608294
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.251065 ... 76.809875 76.563695
17 2432.0 71.305746 ... 83.366361 84.115159
18 2560.0 77.833728 ... 80.908642 80.511054
19 2688.0 83.922689 ... 89.676257 89.464755
20 2816.0 84.605647 ... 82.759409 82.759409
21 2944.0 82.509987 ... 82.509987 82.237674
22 3072.0 81.825298 ... 87.381335 87.651868
23 3200.0 84.993363 ... 92.888243 95.522391
24 3328.0 83.468170 ... 83.323259 83.419811
25 3456.0 82.519518 ... 90.994998 91.097818
26 3584.0 84.825838 ... 93.661869 97.205829
27 3712.0 85.785610 ... 89.957089 89.114488
28 3840.0 81.798814 ... 89.043476 91.625518
29 3968.0 86.023220 ... 91.747320 84.738843
30 4096.0 94.419788 ... 90.995066 88.185107
16 2304.0 68.056616 ... 76.809875 76.563695
17 2432.0 71.305746 ... 74.918570 84.621881
18 2560.0 77.833728 ... 81.310171 80.709358
19 2688.0 83.922689 ... 89.464755 89.888756
20 2816.0 83.392363 ... 83.074685 83.233226
21 2944.0 81.832567 ... 82.509987 82.921853
22 3072.0 82.062468 ... 88.612060 89.310890
23 3200.0 83.879425 ... 95.451158 95.096582
24 3328.0 83.905938 ... 81.346098 84.695641
25 3456.0 81.849303 ... 91.200871 88.497878
26 3584.0 86.540320 ... 98.808123 98.591437
27 3712.0 81.682211 ... 87.821837 88.170647
28 3840.0 84.292684 ... 91.360593 89.912191
29 3968.0 92.793868 ... 85.034103 91.403695
30 4096.0 87.495257 ... 85.816960 91.180520
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 59.967 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 32.577 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>