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
2022-04-08 00:44:05 +00:00
parent 80b92a0d2d
commit 0c570c178d
173 changed files with 401 additions and 386 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -565,41 +565,41 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
<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 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 7.899428
2 512.0 14.563555 ... 16.384000 16.384000
1 384.0 7.372800 ... 7.899428 8.507077
2 512.0 14.563555 ... 15.420235 15.420235
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
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 66.485074
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 62.929456 ... 62.492442 61.636381
12 1792.0 72.512412 ... 72.512412 72.047592
13 1920.0 69.467336 ... 70.172588 69.818184
14 2048.0 73.262953 ... 76.608294 76.608294
15 2176.0 83.500614 ... 85.998493 85.632545
16 2304.0 68.643310 ... 77.057651 76.319081
17 2432.0 71.305746 ... 85.393507 85.134737
18 2560.0 78.019048 ... 80.709358 81.108913
19 2688.0 83.004501 ... 89.464755 89.254248
20 2816.0 80.767055 ... 83.552120 82.602666
21 2944.0 81.298583 ... 82.237674 81.967162
22 3072.0 81.707223 ... 88.473602 87.516392
23 3200.0 84.377059 ... 94.955488 94.674553
24 3328.0 83.034941 ... 84.695641 83.905938
25 3456.0 81.108217 ... 85.133652 81.029251
26 3584.0 86.623693 ... 98.483450 98.160909
27 3712.0 81.682211 ... 88.404730 84.017953
28 3840.0 82.592983 ... 92.006659 85.169042
29 3968.0 90.791620 ... 86.236000 90.522206
30 4096.0 86.369197 ... 85.001726 91.304576
4 768.0 32.768000 ... 35.389441 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
6 1024.0 49.932191 ... 53.773130 53.773130
7 1152.0 45.242181 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 69.009825 67.305878
10 1536.0 79.526831 ... 80.430545 79.526831
11 1664.0 63.372618 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.142831 63.142831
13 1920.0 69.120002 ... 71.626943 70.892307
14 2048.0 73.584279 ... 78.033565 77.672296
15 2176.0 83.500614 ... 87.115360 86.739860
16 2304.0 68.446623 ... 77.810656 77.307030
17 2432.0 71.125224 ... 75.522751 75.320281
18 2560.0 77.833728 ... 81.715711 81.512437
19 2688.0 83.737433 ... 90.966561 90.532356
20 2816.0 79.443003 ... 82.916747 84.035084
21 2944.0 81.832567 ... 83.198715 82.102191
22 3072.0 81.121923 ... 88.197981 87.381335
23 3200.0 83.116885 ... 96.385543 96.096095
24 3328.0 82.939284 ... 84.895397 85.096096
25 3456.0 77.745004 ... 86.596744 84.332184
26 3584.0 86.540320 ... 91.380335 97.416461
27 3712.0 85.748791 ... 88.404730 86.341700
28 3840.0 84.874902 ... 93.247896 85.300426
29 3968.0 92.372393 ... 80.015697 78.220472
30 4096.0 93.990003 ... 93.206754 86.036145
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 0.645 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 48.521 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>