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

46
v1.1.2/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -569,41 +569,41 @@ 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
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 37.971025 ... 40.140799 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
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 56.888887
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 80.430545 ... 79.526831 79.526831
11 1664.0 62.929456 ... 62.492442 62.061463
12 1792.0 72.983276 ... 71.588687 71.588687
13 1920.0 69.120002 ... 70.172588 70.172588
14 2048.0 73.584279 ... 76.608294 76.260072
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 73.908442 ... 76.959706 76.608294
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.446623 ... 76.809875 76.563695
17 2432.0 71.305746 ... 82.874527 84.877538
18 2560.0 78.019048 ... 80.709358 80.511054
19 2688.0 83.369354 ... 89.044730 89.676257
20 2816.0 83.233226 ... 82.916747 82.602666
21 2944.0 81.832567 ... 80.640830 82.169877
22 3072.0 82.181572 ... 88.473602 88.473602
23 3200.0 84.768213 ... 95.096582 94.395283
24 3328.0 82.939284 ... 81.346098 84.695641
25 3456.0 81.932484 ... 90.180725 91.097818
26 3584.0 87.085130 ... 98.268190 93.564405
27 3712.0 83.317214 ... 88.443865 83.947349
28 3840.0 84.874902 ... 91.322872 84.421376
29 3968.0 90.388098 ... 84.210698 88.615785
30 4096.0 86.480498 ... 92.948562 88.243079
16 2304.0 68.446623 ... 76.563695 76.319081
17 2432.0 71.125224 ... 85.134737 84.621881
18 2560.0 77.833728 ... 81.108913 80.908642
19 2688.0 83.737433 ... 89.888756 89.464755
20 2816.0 83.074685 ... 82.759409 81.218262
21 2944.0 81.698415 ... 80.510553 79.737653
22 3072.0 82.181572 ... 88.612060 88.335577
23 3200.0 82.156612 ... 93.841640 93.979441
24 3328.0 81.530349 ... 84.795401 84.596116
25 3456.0 82.141178 ... 88.595129 89.281913
26 3584.0 87.296493 ... 91.563533 96.683219
27 3712.0 85.675250 ... 86.191546 88.561477
28 3840.0 79.448276 ... 84.548438 91.322872
29 3968.0 86.973584 ... 90.791620 85.871877
30 4096.0 93.142072 ... 82.040176 89.062862
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 51.135 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 44.408 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>