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
2022-05-01 00:49:06 +00:00
parent e15e7e5ae2
commit 0bce260523
156 changed files with 280 additions and 280 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
master/getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -563,43 +563,43 @@ torch_output=tensor([[ 1.1045, -36.9688, 31.4688, ..., -11.3906, 24.4531, -3
<img alt="03 matrix multiplication" class="sphx-glr-single-img" src="../../_images/sphx_glr_03-matrix-multiplication_001.png" />
<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 ... 3.276800 2.978909
1 384.0 7.372800 ... 7.899428 8.507077
2 512.0 14.563555 ... 15.420235 15.420235
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 35.389441 34.028308
5 896.0 37.971025 ... 40.140799 40.140799
6 1024.0 49.932191 ... 53.773130 53.773130
7 1152.0 45.242181 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 69.009825 67.305878
10 1536.0 79.526831 ... 80.430545 79.526831
11 1664.0 63.372618 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.142831 62.790080
13 1920.0 68.776119 ... 71.257735 70.892307
14 2048.0 73.908442 ... 78.398206 78.033565
15 2176.0 83.155572 ... 87.115360 86.739860
16 2304.0 68.251065 ... 78.064941 77.558029
17 2432.0 71.305746 ... 75.726318 75.320281
18 2560.0 77.833728 ... 82.539044 82.125311
19 2688.0 83.552988 ... 91.625737 90.748936
20 2816.0 79.587973 ... 82.290955 84.197315
21 2944.0 81.232324 ... 83.477440 83.899046
22 3072.0 81.121923 ... 89.451983 89.735509
23 3200.0 84.656085 ... 96.240602 96.096095
24 3328.0 83.905938 ... 83.323259 82.939284
25 3456.0 82.519518 ... 86.876687 92.033756
26 3584.0 87.808000 ... 100.017124 99.354022
27 3712.0 84.874549 ... 88.561477 88.797643
28 3840.0 84.292684 ... 92.159996 85.597527
29 3968.0 91.816356 ... 87.976885 90.589410
30 4096.0 87.552332 ... 94.519528 88.011627
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 256.0 2.978909 ... 3.276800 2.978909
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 37.971025 ... 41.321411 39.025776
6 1024.0 49.932191 ... 53.773130 53.773130
7 1152.0 45.242181 ... 48.161033 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 69.009825 68.147202
10 1536.0 80.430545 ... 80.430545 80.430545
11 1664.0 63.372618 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.499573 63.142831
13 1920.0 68.776119 ... 71.257735 70.892307
14 2048.0 73.584279 ... 78.398206 78.033565
15 2176.0 83.155572 ... 87.115360 86.739860
16 2304.0 68.251065 ... 78.064941 77.558029
17 2432.0 71.305746 ... 75.726318 75.522751
18 2560.0 77.833728 ... 82.539044 82.331658
19 2688.0 84.108772 ... 91.185232 90.966561
20 2816.0 80.469019 ... 83.552120 84.523664
21 2944.0 81.832567 ... 84.324925 83.758038
22 3072.0 81.589488 ... 87.246694 89.451983
23 3200.0 85.106381 ... 96.385543 95.952022
24 3328.0 83.905938 ... 85.908470 86.113988
25 3456.0 82.604067 ... 85.043848 89.480098
26 3584.0 84.111686 ... 92.410473 94.747514
27 3712.0 85.675250 ... 85.896254 88.404730
28 3840.0 81.138664 ... 88.261772 91.701494
29 3968.0 87.976885 ... 92.477403 85.811488
30 4096.0 93.401342 ... 84.733417 86.872315
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 48.929 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 55.944 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>