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
2022-07-19 00:52:52 +00:00
parent 30db1c142b
commit 9f8b4adf8e
169 changed files with 291 additions and 291 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
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 2.730667 ... 2.978909 2.978909
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 15.420235 15.420235
0 256.0 2.730667 ... 2.978909 3.276800
1 384.0 7.372800 ... 7.899428 8.507077
2 512.0 14.563555 ... 15.420235 16.384000
3 640.0 22.260869 ... 24.380953 24.380953
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
6 1024.0 51.150050 ... 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 ... 81.355034 79.526831
11 1664.0 62.929456 ... 63.372618 62.492442
12 1792.0 72.983276 ... 72.983276 59.467852
13 1920.0 69.120002 ... 71.626943 71.626943
11 1664.0 63.372618 ... 63.372618 62.492442
12 1792.0 72.983276 ... 73.460287 59.467852
13 1920.0 69.120002 ... 71.257735 70.892307
14 2048.0 73.908442 ... 78.398206 77.314362
15 2176.0 83.500614 ... 87.494120 85.998493
16 2304.0 68.251065 ... 77.810656 77.307030
17 2432.0 71.305746 ... 86.711310 85.653855
18 2560.0 77.833728 ... 82.539044 81.310171
19 2688.0 83.737433 ... 90.532356 89.464755
20 2816.0 83.873477 ... 84.687779 84.035084
21 2944.0 82.509987 ... 83.899046 82.646820
22 3072.0 81.825298 ... 89.877939 88.473602
23 3200.0 84.432717 ... 96.896287 95.593730
24 3328.0 83.130825 ... 85.857242 83.130825
25 3456.0 82.519518 ... 89.084603 90.281712
26 3584.0 84.111686 ... 92.315595 95.756542
27 3712.0 85.970176 ... 89.755028 87.937800
28 3840.0 81.138664 ... 89.839159 90.205545
29 3968.0 86.051653 ... 92.442373 85.932350
30 4096.0 94.453011 ... 87.267706 86.536250
15 2176.0 83.155572 ... 88.261612 86.367588
16 2304.0 68.446623 ... 78.064941 77.558029
17 2432.0 71.305746 ... 86.711310 85.915795
18 2560.0 78.019048 ... 82.539044 81.310171
19 2688.0 83.552988 ... 90.102270 89.888756
20 2816.0 83.712490 ... 84.852542 83.873477
21 2944.0 82.373605 ... 83.758038 82.921853
22 3072.0 82.540970 ... 85.922766 88.335577
23 3200.0 84.993363 ... 96.676741 96.385543
24 3328.0 84.003845 ... 86.217120 81.162679
25 3456.0 81.026701 ... 85.767626 89.183149
26 3584.0 87.211821 ... 99.463928 97.840469
27 3712.0 83.247783 ... 89.273764 84.088676
28 3840.0 85.070769 ... 90.723546 88.686451
29 3968.0 93.219206 ... 88.103928 87.441013
30 4096.0 90.565269 ... 86.037005 82.597115
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 27.642 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 17.371 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>