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
2022-04-20 00:43:07 +00:00
parent 245e5ab128
commit 8d0e47d73e
156 changed files with 282 additions and 282 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -565,41 +565,41 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
<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 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 16.384000 15.420235
1 384.0 7.372800 ... 7.899428 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 37.971025 ... 41.321411 40.140799
5 896.0 37.971025 ... 40.140799 40.140799
6 1024.0 49.932191 ... 53.773130 53.773130
7 1152.0 44.566925 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
7 1152.0 45.242181 ... 48.161033 47.396572
8 1280.0 51.200001 ... 58.514284 57.690139
9 1408.0 64.138541 ... 69.009825 69.009825
10 1536.0 80.430545 ... 80.430545 80.430545
11 1664.0 63.372618 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.142831 63.142831
13 1920.0 69.120002 ... 71.626943 70.892307
10 1536.0 79.526831 ... 80.430545 80.430545
11 1664.0 62.929456 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.142831 62.790080
13 1920.0 68.776119 ... 71.626943 71.257735
14 2048.0 73.584279 ... 78.398206 78.033565
15 2176.0 83.155572 ... 87.115360 86.739860
16 2304.0 68.251065 ... 77.810656 77.558029
16 2304.0 68.446623 ... 77.810656 77.558029
17 2432.0 71.125224 ... 75.726318 75.320281
18 2560.0 77.833728 ... 81.920002 81.512437
19 2688.0 83.369354 ... 91.404957 90.748936
20 2816.0 83.392363 ... 83.712490 83.873477
21 2944.0 81.967162 ... 83.477440 82.373605
22 3072.0 78.752578 ... 88.612060 87.246694
23 3200.0 79.601989 ... 96.096095 95.952022
24 3328.0 84.003845 ... 85.196803 85.703924
25 3456.0 81.683457 ... 92.350019 92.508971
26 3584.0 84.745889 ... 88.412386 94.250936
27 3712.0 85.675250 ... 87.706180 87.399253
28 3840.0 83.465663 ... 88.332269 91.777595
29 3968.0 88.040360 ... 91.678389 86.788006
30 4096.0 93.531519 ... 83.156833 86.593830
18 2560.0 77.833728 ... 82.125311 81.715711
19 2688.0 83.369354 ... 90.532356 90.748936
20 2816.0 80.916902 ... 83.552120 83.552120
21 2944.0 82.373605 ... 83.617504 83.617504
22 3072.0 81.707223 ... 87.651868 89.593522
23 3200.0 85.219705 ... 96.385543 96.385543
24 3328.0 82.275764 ... 86.011103 85.703924
25 3456.0 81.890873 ... 92.455926 92.138932
26 3584.0 86.623693 ... 89.290361 94.250936
27 3712.0 85.675250 ... 88.092894 84.874549
28 3840.0 84.679936 ... 92.468225 85.136259
29 3968.0 90.724116 ... 84.974886 90.522206
30 4096.0 90.996029 ... 87.438257 92.309303
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 8.669 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 10.290 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>