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
2022-04-13 00:45:31 +00:00
parent d19191fa7e
commit 9d65bf62fb
158 changed files with 314 additions and 314 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 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 ... 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 ... 58.514284 57.690139
9 1408.0 64.138541 ... 69.009825 68.147202
10 1536.0 79.526831 ... 80.430545 80.430545
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 71.257735
14 2048.0 73.584279 ... 78.033565 77.672296
15 2176.0 83.155572 ... 87.115360 86.739860
16 2304.0 68.446623 ... 77.810656 77.558029
17 2432.0 71.125224 ... 75.522751 75.118889
18 2560.0 77.833728 ... 82.125311 81.715711
19 2688.0 83.552988 ... 90.316801 89.888756
20 2816.0 80.173175 ... 83.873477 83.392363
21 2944.0 81.034195 ... 84.040530 82.237674
22 3072.0 82.301023 ... 89.310890 89.030036
23 3200.0 82.156612 ... 96.385543 96.822991
24 3328.0 83.516586 ... 85.500351 85.703924
25 3456.0 81.683457 ... 86.226274 86.783176
26 3584.0 87.211821 ... 98.808123 99.408944
27 3712.0 84.159518 ... 86.641231 88.248537
28 3840.0 79.391241 ... 85.136259 91.247522
29 3968.0 87.097744 ... 91.472214 84.797731
30 4096.0 93.401342 ... 84.096318 86.092193
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 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 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
9 1408.0 64.138541 ... 69.009825 67.305878
10 1536.0 79.526831 ... 79.526831 79.526831
11 1664.0 62.929456 ... 63.372618 62.929456
12 1792.0 72.983276 ... 63.142831 63.142831
13 1920.0 68.776119 ... 71.257735 70.892307
14 2048.0 73.262953 ... 78.398206 77.672296
15 2176.0 83.155572 ... 87.494120 86.367588
16 2304.0 68.251065 ... 77.810656 77.558029
17 2432.0 71.125224 ... 75.726318 75.320281
18 2560.0 77.833728 ... 82.331658 82.125311
19 2688.0 83.737433 ... 90.966561 89.888756
20 2816.0 80.767055 ... 83.712490 83.712490
21 2944.0 81.765436 ... 83.477440 83.899046
22 3072.0 81.943708 ... 89.030036 88.820552
23 3200.0 82.901554 ... 92.753621 88.213121
24 3328.0 80.798314 ... 82.369902 86.320498
25 3456.0 80.945348 ... 88.790274 91.200871
26 3584.0 87.127323 ... 100.017124 99.463928
27 3712.0 81.615477 ... 86.641231 88.248537
28 3840.0 82.778440 ... 87.148936 91.322872
29 3968.0 86.051653 ... 85.391135 84.270676
30 4096.0 91.366730 ... 84.149044 90.748973
[31 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 4.871 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 6 minutes 49.578 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>