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
2021-09-07 00:13:40 +00:00
parent 44e1f5bfaa
commit 1bfcc182af
19 changed files with 85 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
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
0 256.0 2.978909 ... 3.276800 2.978909
1 384.0 7.372800 ... 7.899428 7.899428
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
5 896.0 37.971025 ... 40.140799 39.025776
5 896.0 37.971025 ... 39.025776 39.025776
6 1024.0 49.932191 ... 52.428801 52.428801
7 1152.0 44.566925 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.109587
8 1280.0 51.200001 ... 56.888887 56.888887
9 1408.0 64.138541 ... 63.392744 62.664092
10 1536.0 80.430545 ... 76.106321 75.296679
11 1664.0 63.372618 ... 62.061463 62.061463
10 1536.0 79.526831 ... 75.296679 76.106321
11 1664.0 62.929456 ... 62.061463 62.061463
12 1792.0 72.983276 ... 62.441243 62.441243
13 1920.0 68.098521 ... 70.172588 69.818184
14 2048.0 73.584279 ... 74.235468 67.932543
15 2176.0 82.813365 ... 79.855747 79.540109
16 2304.0 68.643310 ... 73.501144 73.275679
17 2432.0 71.305746 ... 72.037087 81.908060
18 2560.0 77.833728 ... 76.560748 76.560748
19 2688.0 80.880718 ... 81.752274 83.552988
20 2816.0 81.981598 ... 79.298560 78.442822
21 2944.0 81.564701 ... 77.505492 77.265163
22 3072.0 81.355034 ... 82.782312 82.903517
23 3200.0 81.321474 ... 85.906037 87.671229
24 3328.0 82.748617 ... 81.994643 82.275764
25 3456.0 81.683457 ... 81.932484 84.244062
26 3584.0 87.211821 ... 87.722333 91.284657
27 3712.0 85.675250 ... 82.017526 86.267139
28 3840.0 84.485870 ... 86.738820 86.602979
29 3968.0 92.864488 ... 87.284643 87.159957
30 4096.0 93.531519 ... 88.885914 88.827088
13 1920.0 69.120002 ... 68.776119 68.776119
14 2048.0 73.584279 ... 74.235468 74.565406
15 2176.0 83.155572 ... 80.173899 81.143743
16 2304.0 68.056616 ... 73.275679 73.275679
17 2432.0 71.125224 ... 72.037087 82.630777
18 2560.0 78.019048 ... 76.560748 76.027843
19 2688.0 84.108772 ... 81.752274 81.401408
20 2816.0 83.552120 ... 78.726003 79.298560
21 2944.0 80.510553 ... 78.112900 75.853930
22 3072.0 81.825298 ... 83.146995 81.589488
23 3200.0 84.768213 ... 86.253369 90.014065
24 3328.0 83.226931 ... 81.622783 86.632127
25 3456.0 81.600781 ... 83.980802 84.068369
26 3584.0 87.211821 ... 85.797134 85.308722
27 3712.0 85.822459 ... 79.472826 78.721311
28 3840.0 83.465663 ... 86.197974 86.265212
29 3968.0 93.219206 ... 86.849777 87.222259
30 4096.0 93.206754 ... 89.958266 89.777746
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 13.178 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 5.162 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>