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
2022-09-01 00:49:59 +00:00
parent cb05587449
commit 41ab369e01
165 changed files with 280 additions and 280 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
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 ... 39.025776 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
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
5 896.0 37.971025 ... 40.140799 39.025776
6 1024.0 51.150050 ... 52.428801 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
13 1920.0 69.120002 ... 70.530615 70.530615
14 2048.0 73.908442 ... 76.959706 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 ... 84.621881 84.877538
18 2560.0 77.833728 ... 80.908642 80.908642
19 2688.0 83.369354 ... 88.836198 88.628636
20 2816.0 79.587973 ... 83.074685 82.602666
21 2944.0 81.431424 ... 82.784108 81.967162
22 3072.0 82.661468 ... 82.241254 88.197981
23 3200.0 84.432717 ... 95.167286 95.238096
24 3328.0 82.748617 ... 84.695641 84.496824
25 3456.0 81.518272 ... 85.767626 88.400840
26 3584.0 87.296493 ... 98.483450 91.470385
27 3712.0 84.159518 ... 88.483034 83.947349
28 3840.0 84.615146 ... 92.468225 84.228485
29 3968.0 92.442373 ... 85.093402 90.724116
30 4096.0 87.495257 ... 87.495257 92.182504
15 2176.0 83.155572 ... 86.367588 85.269692
16 2304.0 68.348707 ... 76.809875 76.563695
17 2432.0 71.305746 ... 74.719317 82.630777
18 2560.0 78.019048 ... 80.709358 81.108913
19 2688.0 83.186525 ... 89.464755 89.044730
20 2816.0 80.617762 ... 83.074685 82.446516
21 2944.0 82.102191 ... 83.060049 82.509987
22 3072.0 81.530748 ... 89.030036 89.310890
23 3200.0 84.544253 ... 95.096582 95.096582
24 3328.0 84.003845 ... 80.437202 83.808259
25 3456.0 81.849303 ... 90.892410 91.097818
26 3584.0 83.954614 ... 93.611591 98.591437
27 3712.0 85.382349 ... 83.526206 87.475786
28 3840.0 81.798814 ... 85.333335 91.549669
29 3968.0 88.938731 ... 91.198760 85.871877
30 4096.0 93.271527 ... 92.309303 85.217605
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 22.961 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 24.156 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>