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
2022-08-27 00:48:56 +00:00
parent 65cfbbabe5
commit 79bb9e69b7
163 changed files with 278 additions and 278 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
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 ... 3.276800 2.978909
0 256.0 2.978909 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 15.420235 15.420235
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 ... 40.140799 39.025776
6 1024.0 49.932191 ... 53.773130 52.428801
7 1152.0 44.566925 ... 47.396572 47.396572
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 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 68.147202 67.305878
10 1536.0 80.430545 ... 80.430545 78.643199
10 1536.0 80.430545 ... 81.355034 79.526831
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
13 1920.0 69.120002 ... 71.257735 71.257735
14 2048.0 73.908442 ... 78.398206 77.314362
15 2176.0 83.500614 ... 87.876193 86.367588
16 2304.0 68.251065 ... 78.064941 77.057651
17 2432.0 71.305746 ... 83.614477 83.366361
18 2560.0 77.833728 ... 82.747477 81.715711
19 2688.0 83.922689 ... 90.748936 89.044730
20 2816.0 82.759409 ... 84.197315 83.712490
21 2944.0 81.298583 ... 83.899046 80.771529
22 3072.0 81.825298 ... 89.310890 87.246694
23 3200.0 81.424937 ... 97.116842 95.096582
24 3328.0 84.003845 ... 85.908470 84.101981
25 3456.0 79.118323 ... 85.585527 88.400840
26 3584.0 87.127323 ... 99.518972 95.756542
27 3712.0 84.159518 ... 84.658765 87.937800
28 3840.0 84.615146 ... 89.042358 84.323810
29 3968.0 92.512459 ... 81.950257 84.915752
30 4096.0 87.381330 ... 85.489001 90.079009
15 2176.0 83.500614 ... 87.115360 85.632545
16 2304.0 68.446623 ... 78.064941 77.307030
17 2432.0 71.305746 ... 86.179335 75.320281
18 2560.0 77.833728 ... 82.539044 81.310171
19 2688.0 83.737433 ... 90.316801 89.254248
20 2816.0 79.806423 ... 84.116121 83.873477
21 2944.0 81.298583 ... 83.060049 83.337844
22 3072.0 78.643199 ... 88.335577 86.315709
23 3200.0 82.368085 ... 96.676741 95.665176
24 3328.0 83.130825 ... 84.695641 84.397770
25 3456.0 82.015834 ... 91.097818 90.892410
26 3584.0 84.865870 ... 95.451583 90.367227
27 3712.0 84.658765 ... 88.955779 87.018592
28 3840.0 84.485870 ... 89.802683 88.473602
29 3968.0 92.864488 ... 87.066671 89.493168
30 4096.0 88.417474 ... 86.258181 89.898012
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 21.317 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 34.417 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>