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
2022-06-22 00:49:37 +00:00
parent c168f03e0c
commit 6bf3700c9c
158 changed files with 262 additions and 262 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -565,12 +565,12 @@ 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 ... 3.276800 3.276800
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 15.420235 15.420235
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 ... 35.389441 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
5 896.0 39.025776 ... 40.140799 39.025776
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 45.242181 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
@@ -578,29 +578,29 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
10 1536.0 80.430545 ... 81.355034 78.643199
11 1664.0 63.372618 ... 63.372618 62.492442
12 1792.0 72.983276 ... 73.460287 59.467852
13 1920.0 69.467336 ... 71.257735 70.892307
14 2048.0 73.262953 ... 78.033565 76.959706
15 2176.0 83.155572 ... 87.494120 85.998493
16 2304.0 68.446623 ... 78.064941 77.057651
17 2432.0 71.125224 ... 86.444504 84.877538
18 2560.0 77.833728 ... 82.956960 81.108913
19 2688.0 83.552988 ... 90.966561 89.044730
20 2816.0 82.995641 ... 84.197315 83.712490
21 2944.0 82.646820 ... 83.758038 82.237674
22 3072.0 82.661468 ... 87.787755 88.612060
23 3200.0 81.424937 ... 93.704243 93.430660
24 3328.0 81.622783 ... 85.703924 84.795401
25 3456.0 82.604067 ... 92.033756 90.281712
26 3584.0 85.674507 ... 93.273228 95.960933
27 3712.0 85.748791 ... 86.118401 87.706180
28 3840.0 81.019778 ... 88.900318 89.475729
29 3968.0 88.008611 ... 87.315873 88.040360
30 4096.0 93.924229 ... 93.727466 87.552332
13 1920.0 68.776119 ... 71.626943 70.892307
14 2048.0 73.262953 ... 78.398206 76.959706
15 2176.0 83.155572 ... 87.876193 85.998493
16 2304.0 68.251065 ... 78.064941 77.057651
17 2432.0 71.305746 ... 86.711310 84.115159
18 2560.0 77.833728 ... 82.539044 81.512437
19 2688.0 83.737433 ... 90.966561 89.044730
20 2816.0 83.712490 ... 84.523664 83.712490
21 2944.0 82.784108 ... 83.060049 82.646820
22 3072.0 82.661468 ... 90.020831 87.787755
23 3200.0 85.219705 ... 96.822991 95.952022
24 3328.0 83.613586 ... 86.528001 84.200347
25 3456.0 81.849303 ... 91.928814 88.595129
26 3584.0 86.540320 ... 99.463928 91.563533
27 3712.0 82.355598 ... 89.154253 81.283434
28 3840.0 84.874902 ... 93.722032 85.399230
29 3968.0 93.469117 ... 89.198780 86.175099
30 4096.0 92.436452 ... 86.313653 82.241256
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 59.034 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 2.032 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>