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
2022-07-24 00:52:21 +00:00
parent 5f9c7bc693
commit 379acd8521
165 changed files with 266 additions and 266 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -567,42 +567,42 @@ 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 2.978909 ... 2.978909 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 15.420235 15.420235
0 256.0 2.730667 ... 2.978909 2.978909
1 384.0 7.372800 ... 7.899428 8.507077
2 512.0 14.563555 ... 16.384000 15.420235
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 34.028308 34.028308
4 768.0 32.768000 ... 35.389441 34.028308
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
7 1152.0 45.242181 ... 47.396572 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 ... 81.355034 79.526831
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 68.776119 ... 71.257735 70.892307
14 2048.0 73.584279 ... 78.033565 76.959706
13 1920.0 69.467336 ... 70.892307 71.257735
14 2048.0 73.584279 ... 78.033565 77.314362
15 2176.0 83.155572 ... 87.494120 85.998493
16 2304.0 68.446623 ... 78.320893 77.558029
17 2432.0 71.305746 ... 86.711310 75.320281
16 2304.0 68.251065 ... 78.064941 77.307030
17 2432.0 71.125224 ... 86.444504 85.653855
18 2560.0 77.833728 ... 82.747477 81.715711
19 2688.0 83.552988 ... 90.532356 89.676257
20 2816.0 83.552120 ... 84.035084 83.392363
21 2944.0 81.832567 ... 83.758038 81.967162
22 3072.0 82.540970 ... 89.877939 89.170242
23 3200.0 84.321474 ... 96.822991 95.380032
24 3328.0 83.034941 ... 85.806075 84.596116
25 3456.0 82.183044 ... 91.928814 87.632137
26 3584.0 87.381330 ... 92.696281 96.891584
27 3712.0 84.694652 ... 87.244203 88.092894
28 3840.0 85.136259 ... 88.900318 90.279183
29 3968.0 88.008611 ... 92.547541 84.268854
30 4096.0 93.368854 ... 87.781379 86.592080
19 2688.0 83.737433 ... 90.748936 89.044730
20 2816.0 79.587973 ... 84.852542 84.197315
21 2944.0 81.967162 ... 83.758038 82.102191
22 3072.0 81.825298 ... 89.877939 88.473602
23 3200.0 84.656085 ... 96.822991 95.522391
24 3328.0 83.034941 ... 86.320498 82.891535
25 3456.0 81.026701 ... 82.350937 87.442050
26 3584.0 87.296493 ... 99.574077 98.699661
27 3712.0 84.088676 ... 89.513749 87.860458
28 3840.0 81.019778 ... 89.766237 90.352941
29 3968.0 85.992909 ... 92.723355 84.300694
30 4096.0 93.990003 ... 88.127204 87.495257
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 21.318 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 39.020 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>