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
2022-06-03 00:42:29 +00:00
parent ebf28cdc4b
commit 4d64e1b60e
353 changed files with 148 additions and 43136 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
v1.1.2/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -569,41 +569,41 @@ 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 ... 2.978909 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
1 384.0 7.372800 ... 8.507077 7.899428
2 512.0 14.563555 ... 16.384000 16.384000
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 34.028308 34.028308
5 896.0 37.971025 ... 39.025776 37.971025
6 1024.0 49.932191 ... 52.428801 52.428801
5 896.0 39.025776 ... 40.140799 39.025776
6 1024.0 51.150050 ... 53.773130 52.428801
7 1152.0 45.242181 ... 46.656000 46.656000
8 1280.0 51.200001 ... 56.888887 56.888887
9 1408.0 64.138541 ... 67.305878 66.485074
10 1536.0 80.430545 ... 79.526831 78.643199
11 1664.0 63.372618 ... 62.492442 62.061463
12 1792.0 72.983276 ... 72.047592 71.588687
13 1920.0 68.776119 ... 70.530615 70.530615
11 1664.0 62.929456 ... 62.492442 62.061463
12 1792.0 72.983276 ... 59.154861 71.588687
13 1920.0 69.120002 ... 70.172588 70.172588
14 2048.0 73.908442 ... 76.959706 76.608294
15 2176.0 83.155572 ... 85.998493 85.269692
16 2304.0 68.446623 ... 76.809875 76.563695
17 2432.0 71.305746 ... 83.366361 84.877538
18 2560.0 77.833728 ... 81.512437 81.310171
19 2688.0 84.295681 ... 90.102270 89.254248
20 2816.0 84.605647 ... 83.873477 82.602666
21 2944.0 81.431424 ... 82.646820 82.921853
22 3072.0 81.589488 ... 88.612060 88.612060
23 3200.0 84.044651 ... 94.814812 91.298148
24 3328.0 83.808259 ... 84.895397 85.500351
25 3456.0 81.932484 ... 86.876687 85.676480
26 3584.0 87.381330 ... 98.808123 92.983857
27 3712.0 81.415926 ... 87.937800 85.822459
28 3840.0 82.654712 ... 92.468225 85.201850
29 3968.0 92.652949 ... 80.147087 77.377257
30 4096.0 91.867031 ... 93.336389 89.181212
16 2304.0 68.251065 ... 77.057651 76.809875
17 2432.0 71.305746 ... 74.918570 84.877538
18 2560.0 77.833728 ... 81.310171 80.908642
19 2688.0 83.922689 ... 90.102270 89.464755
20 2816.0 83.074685 ... 83.074685 82.916747
21 2944.0 82.646820 ... 81.564701 82.921853
22 3072.0 81.589488 ... 88.473602 87.516392
23 3200.0 80.706181 ... 93.704243 95.665176
24 3328.0 82.796202 ... 83.857070 84.895397
25 3456.0 81.766291 ... 91.304157 91.719645
26 3584.0 87.551500 ... 96.891584 98.160909
27 3712.0 85.601834 ... 91.397382 87.399253
28 3840.0 84.874902 ... 90.798032 87.910967
29 3968.0 91.954739 ... 90.859224 85.871877
30 4096.0 93.401342 ... 92.372834 90.200084
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 57.968 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 12.411 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>