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
2022-09-04 00:51:14 +00:00
parent 540e088822
commit ef6b89f4f1
165 changed files with 266 additions and 266 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
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
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 39.025776 ... 40.140799 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
7 1152.0 45.242181 ... 48.161033 48.161033
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 44.566925 ... 47.396572 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 69.009825 68.147202
10 1536.0 81.355034 ... 81.355034 79.526831
11 1664.0 63.372618 ... 63.822072 62.929456
12 1792.0 72.983276 ... 73.460287 59.467852
13 1920.0 68.776119 ... 71.257735 71.257735
9 1408.0 64.138541 ... 68.147202 67.305878
10 1536.0 80.430545 ... 81.355034 78.643199
11 1664.0 62.929456 ... 63.372618 62.492442
12 1792.0 72.512412 ... 73.460287 59.467852
13 1920.0 69.120002 ... 71.626943 71.257735
14 2048.0 73.908442 ... 78.398206 77.314362
15 2176.0 83.500614 ... 87.494120 85.998493
16 2304.0 68.446623 ... 78.064941 77.057651
17 2432.0 71.305746 ... 86.444504 75.320281
18 2560.0 77.833728 ... 82.747477 81.715711
19 2688.0 83.277839 ... 90.532356 90.102270
20 2816.0 80.320825 ... 83.873477 83.074685
21 2944.0 81.698415 ... 80.510553 83.337844
22 3072.0 81.472093 ... 89.735509 88.890270
23 3200.0 84.099871 ... 96.749806 95.665176
24 3328.0 83.130825 ... 85.297742 84.596116
25 3456.0 81.394821 ... 92.138932 90.790053
26 3584.0 86.623693 ... 93.370085 96.787292
27 3712.0 85.528545 ... 86.641231 87.937800
28 3840.0 83.402717 ... 92.429584 85.996889
29 3968.0 92.864488 ... 80.120775 84.915752
30 4096.0 86.204508 ... 89.062862 90.565269
15 2176.0 83.500614 ... 87.876193 86.367588
16 2304.0 68.446623 ... 78.064941 77.307030
17 2432.0 71.305746 ... 86.711310 85.653855
18 2560.0 78.019048 ... 82.747477 81.715711
19 2688.0 83.737433 ... 91.185232 89.464755
20 2816.0 83.074685 ... 84.687779 83.712490
21 2944.0 82.102191 ... 81.034195 82.784108
22 3072.0 82.540970 ... 89.170242 87.516392
23 3200.0 84.432717 ... 96.822991 95.808380
24 3328.0 83.130825 ... 85.500351 84.447271
25 3456.0 81.974138 ... 91.719645 90.079964
26 3584.0 83.876297 ... 90.549237 94.847460
27 3712.0 85.601834 ... 81.285505 86.044224
28 3840.0 82.840447 ... 92.236860 86.130841
29 3968.0 93.148045 ... 80.120775 84.856701
30 4096.0 86.258181 ... 85.762979 90.565269
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 24.066 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 45.893 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>