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
2022-06-11 00:48:41 +00:00
parent 8168c311b3
commit 410d612f77
156 changed files with 274 additions and 274 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt
View File

@@ -460,36 +460,36 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
matmul-performance:
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 256.0 2.730667 ... 2.978909 3.276800
1 384.0 7.372800 ... 8.507077 8.507077
1 384.0 7.372800 ... 8.507077 7.899428
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 ... 41.321411 39.025776
4 768.0 32.768000 ... 34.028308 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
6 1024.0 49.932191 ... 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
11 1664.0 62.929456 ... 63.372618 62.492442
10 1536.0 79.526831 ... 80.430545 78.643199
11 1664.0 62.929456 ... 63.372618 62.061463
12 1792.0 72.983276 ... 63.499573 63.142831
13 1920.0 69.120002 ... 71.257735 70.892307
14 2048.0 73.262953 ... 78.033565 76.959706
15 2176.0 83.155572 ... 87.115360 85.632545
14 2048.0 73.584279 ... 78.398206 77.672296
15 2176.0 83.155572 ... 87.115360 85.269692
16 2304.0 68.251065 ... 78.064941 76.809875
17 2432.0 71.305746 ... 75.522751 74.521127
18 2560.0 77.833728 ... 82.125311 81.512437
19 2688.0 84.108772 ... 90.316801 90.102270
20 2816.0 79.154642 ... 84.197315 82.602666
21 2944.0 82.237674 ... 83.477440 83.060049
22 3072.0 82.301023 ... 90.020831 88.060814
23 3200.0 83.934428 ... 96.385543 94.534716
24 3328.0 83.226931 ... 86.424125 85.398926
25 3456.0 81.026701 ... 87.632137 90.687926
26 3584.0 87.296493 ... 99.905993 98.160909
27 3712.0 83.178475 ... 89.194055 85.675250
28 3840.0 83.781816 ... 92.236860 85.103501
29 3968.0 91.850912 ... 87.945181 90.321193
30 4096.0 87.495257 ... 90.412750 92.755862
17 2432.0 71.125224 ... 75.522751 74.521127
18 2560.0 77.833728 ... 82.539044 80.908642
19 2688.0 83.737433 ... 90.532356 90.102270
20 2816.0 83.873477 ... 84.360174 83.233226
21 2944.0 81.166173 ... 83.337844 83.060049
22 3072.0 82.420822 ... 89.451983 87.924073
23 3200.0 85.333333 ... 96.385543 94.674553
24 3328.0 84.101981 ... 83.226931 85.908470
25 3456.0 82.604067 ... 92.350019 91.824110
26 3584.0 86.540320 ... 88.412386 87.214470
27 3712.0 85.896254 ... 85.785610 88.404730
28 3840.0 84.809814 ... 93.012618 84.162386
29 3968.0 93.684402 ... 87.850207 89.657558
30 4096.0 88.563330 ... 85.327649 91.180520
[31 rows x 5 columns]
@@ -499,7 +499,7 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 6 minutes 7.264 seconds)
**Total running time of the script:** ( 6 minutes 9.675 seconds)
.. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py: