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
2022-06-06 00:46:47 +00:00
parent fd3a9985ea
commit 9927d8c291
158 changed files with 264 additions and 264 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -565,42 +565,42 @@ 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 8.507077
0 256.0 2.730667 ... 3.276800 2.978909
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 15.420235 15.420235
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 35.389441 34.028308
5 896.0 39.025776 ... 41.321411 39.025776
4 768.0 32.768000 ... 34.028308 34.028308
5 896.0 37.971025 ... 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
9 1408.0 64.138541 ... 68.147202 67.305878
10 1536.0 80.430545 ... 80.430545 78.643199
11 1664.0 63.372618 ... 63.372618 62.492442
12 1792.0 72.983276 ... 63.499573 63.142831
13 1920.0 69.120002 ... 71.626943 71.257735
14 2048.0 73.908442 ... 78.033565 76.959706
15 2176.0 83.155572 ... 87.115360 85.632545
16 2304.0 68.251065 ... 78.064941 76.809875
17 2432.0 71.125224 ... 75.522751 74.521127
18 2560.0 77.833728 ... 82.331658 80.908642
19 2688.0 84.108772 ... 90.966561 89.254248
20 2816.0 83.552120 ... 83.712490 83.552120
21 2944.0 82.237674 ... 84.324925 83.899046
22 3072.0 81.825298 ... 89.735509 89.170242
23 3200.0 84.432717 ... 96.240602 94.674553
24 3328.0 82.939284 ... 86.736504 86.113988
25 3456.0 82.688790 ... 88.014813 81.269178
26 3584.0 86.457107 ... 99.684470 99.025764
27 3712.0 83.247783 ... 89.594031 85.675250
28 3840.0 85.070769 ... 93.090912 87.980905
29 3968.0 93.648452 ... 86.114283 87.284643
30 4096.0 89.627865 ... 89.240508 93.792965
10 1536.0 79.526831 ... 80.430545 78.643199
11 1664.0 62.929456 ... 63.372618 62.061463
12 1792.0 72.983276 ... 63.142831 62.790080
13 1920.0 69.120002 ... 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 68.643310 ... 78.064941 76.809875
17 2432.0 71.125224 ... 75.320281 74.521127
18 2560.0 77.833728 ... 82.539044 81.715711
19 2688.0 84.295681 ... 90.966561 89.254248
20 2816.0 82.838003 ... 83.873477 83.392363
21 2944.0 82.784108 ... 83.477440 83.758038
22 3072.0 81.589488 ... 88.473602 88.197981
23 3200.0 84.099871 ... 96.096095 95.238096
24 3328.0 83.905938 ... 82.088138 85.297742
25 3456.0 82.519518 ... 92.244355 92.244355
26 3584.0 86.457107 ... 91.377427 97.311031
27 3712.0 85.675250 ... 84.053300 87.246590
28 3840.0 83.465663 ... 88.971840 89.403396
29 3968.0 89.855624 ... 92.512459 87.723894
30 4096.0 93.891376 ... 94.187878 91.553703
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 16.582 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 0.141 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>