[GH-PAGES] Updated website

This commit is contained in:
Philippe Tillet
2022-06-24 00:46:49 +00:00
parent 77f3a2cf96
commit 08c4b2c3be
175 changed files with 1240 additions and 306 deletions

View File

@@ -238,10 +238,10 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
3 32768.0 76.800002 76.800002
4 65536.0 127.999995 127.999995
5 131072.0 219.428568 219.428568
6 262144.0 341.333321 384.000001
6 262144.0 341.333321 341.333321
7 524288.0 472.615390 472.615390
8 1048576.0 614.400016 614.400016
9 2097152.0 722.823517 702.171410
9 2097152.0 702.171410 702.171410
10 4194304.0 780.190482 780.190482
11 8388608.0 812.429770 812.429770
12 16777216.0 833.084721 833.084721
@@ -255,7 +255,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 1 minutes 40.793 seconds)
**Total running time of the script:** ( 1 minutes 44.788 seconds)
.. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

View File

@@ -278,17 +278,17 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
softmax-performance:
N Triton Torch (native) Torch (jit)
0 256.0 512.000001 546.133347 188.321838
1 384.0 585.142862 585.142862 151.703707
0 256.0 512.000001 512.000001 186.181817
1 384.0 614.400016 585.142862 153.600004
2 512.0 655.360017 585.142849 154.566038
3 640.0 706.206879 640.000002 160.000000
3 640.0 682.666684 640.000002 158.759699
4 768.0 722.823517 664.216187 162.754967
.. ... ... ... ...
93 12160.0 812.359066 405.333344 198.530610
94 12288.0 812.429770 415.661740 198.794749
95 12416.0 812.498981 411.296057 198.457532
96 12544.0 810.925276 412.971190 198.618504
97 12672.0 811.007961 412.097543 198.776477
93 12160.0 812.359066 406.179533 198.631953
94 12288.0 812.429770 415.661740 198.995960
95 12416.0 810.840807 412.149375 198.556711
96 12544.0 810.925276 412.971190 198.815254
97 12672.0 811.007961 412.097543 198.873965
[98 rows x 4 columns]
@@ -306,7 +306,7 @@ In the above plot, we can see that:
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 3 minutes 23.140 seconds)
**Total running time of the script:** ( 3 minutes 23.445 seconds)
.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

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 2.978909
1 384.0 7.372800 ... 8.507077 7.899428
1 384.0 7.372800 ... 7.899428 7.899428
2 512.0 14.563555 ... 15.420235 15.420235
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 31.597714 ... 34.028308 34.028308
5 896.0 37.971025 ... 40.140799 39.025776
4 768.0 32.768000 ... 34.028308 34.028308
5 896.0 39.025776 ... 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 66.485074
9 1408.0 64.138541 ... 68.147202 65.684049
10 1536.0 79.526831 ... 81.355034 78.643199
11 1664.0 62.929456 ... 63.372618 62.492442
12 1792.0 72.983276 ... 73.460287 59.467852
13 1920.0 69.467336 ... 71.257735 70.892307
14 2048.0 73.262953 ... 78.033565 77.314362
15 2176.0 83.500614 ... 87.876193 85.998493
16 2304.0 68.446623 ... 77.810656 77.057651
13 1920.0 69.120002 ... 71.257735 71.257735
14 2048.0 73.584279 ... 78.398206 77.314362
15 2176.0 83.500614 ... 87.494120 85.998493
16 2304.0 68.446623 ... 78.064941 77.057651
17 2432.0 71.305746 ... 86.711310 85.393507
18 2560.0 77.833728 ... 82.539044 81.715711
19 2688.0 83.552988 ... 90.966561 88.422041
20 2816.0 84.035084 ... 84.687779 83.712490
21 2944.0 79.104810 ... 84.040530 82.646820
22 3072.0 78.972252 ... 89.593522 87.924073
23 3200.0 83.116885 ... 96.240602 94.674553
24 3328.0 82.369902 ... 85.398926 84.795401
25 3456.0 81.108217 ... 92.562076 85.767626
26 3584.0 87.296493 ... 97.628001 97.416461
27 3712.0 84.230479 ... 88.718781 87.552452
28 3840.0 80.313725 ... 90.835321 86.875096
29 3968.0 89.525997 ... 85.479929 89.855624
30 4096.0 91.616198 ... 92.214171 89.359338
18 2560.0 77.833728 ... 82.956960 81.512437
19 2688.0 83.369354 ... 90.316801 89.254248
20 2816.0 83.873477 ... 84.035084 82.916747
21 2944.0 82.646820 ... 82.237674 81.034195
22 3072.0 82.301023 ... 89.735509 86.579673
23 3200.0 84.880639 ... 96.096095 94.674553
24 3328.0 83.905938 ... 85.602017 84.995628
25 3456.0 82.015834 ... 91.928814 88.595129
26 3584.0 86.540320 ... 96.579370 87.042978
27 3712.0 85.675250 ... 89.835744 87.552452
28 3840.0 83.528704 ... 87.841141 89.548180
29 3968.0 86.053553 ... 92.442373 87.035620
30 4096.0 93.792965 ... 85.055593 85.271746
[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 6.178 seconds)
**Total running time of the script:** ( 6 minutes 5.069 seconds)
.. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

View File

@@ -39,35 +39,35 @@ Layer Normalization
layer-norm:
N Triton Torch Apex
0 1024.0 585.142849 277.694907 468.114273
1 1536.0 614.400016 323.368435 511.999982
2 2048.0 682.666643 337.814445 520.126988
1 1536.0 630.153868 323.368435 511.999982
2 2048.0 682.666643 334.367358 520.126988
3 2560.0 694.237267 362.477870 512.000013
4 3072.0 712.347810 375.206126 496.484863
5 3584.0 725.873439 384.859062 455.111115
4 3072.0 712.347810 375.206126 501.551037
5 3584.0 725.873439 384.859062 458.751978
6 4096.0 728.177767 381.023256 458.293714
7 4608.0 670.254540 396.387087 421.302872
8 5120.0 694.237267 397.669909 420.102563
9 5632.0 704.000002 396.969169 413.357796
10 6144.0 702.171410 402.885254 409.600010
11 6656.0 705.271522 400.360920 400.360920
12 7168.0 690.891575 394.116833 387.459443
7 4608.0 670.254540 394.267384 426.173427
8 5120.0 688.403381 397.669909 424.455959
9 5632.0 704.000002 395.228063 413.357796
10 6144.0 702.171410 402.885254 411.313806
11 6656.0 705.271522 398.861429 400.360920
12 7168.0 690.891575 396.844306 387.459443
13 7680.0 682.666656 392.587863 387.634072
14 8192.0 636.271854 391.259714 371.308771
15 8704.0 633.018177 390.095225 380.502740
16 9216.0 611.850618 403.989025 381.023249
17 9728.0 591.817503 408.524944 382.427505
18 10240.0 566.920437 409.600010 382.803739
19 10752.0 551.384634 410.577576 380.601764
20 11264.0 536.380957 403.185684 370.831272
21 11776.0 523.377770 408.711507 377.587162
22 12288.0 517.389457 413.042029 382.505826
23 12800.0 505.679014 410.420828 377.163903
24 13312.0 494.754948 404.927765 376.976995
25 13824.0 482.934503 409.600016 378.092325
26 14336.0 471.967074 403.121247 373.576536
27 14848.0 461.297068 406.099164 375.304904
14 8192.0 636.271854 393.609605 371.308771
15 8704.0 630.153861 389.005597 380.502740
16 9216.0 606.814809 407.337026 383.002605
17 9728.0 589.575753 409.599987 382.427505
18 10240.0 566.920437 408.578556 382.803739
19 10752.0 549.623009 411.559798 380.601764
20 11264.0 536.380957 406.826188 373.134567
21 11776.0 523.377770 409.599991 377.587162
22 12288.0 516.031509 413.911572 383.251457
23 12800.0 505.679014 410.420828 376.470582
24 13312.0 494.180982 405.699062 376.310952
25 13824.0 482.934503 411.888257 379.389355
26 14336.0 471.967074 406.695045 374.185964
27 14848.0 461.297068 408.192434 375.304904
28 15360.0 454.269882 406.214870 378.092307
29 15872.0 447.098578 408.282944 376.783377
29 15872.0 447.098578 406.974373 376.225175
@@ -389,7 +389,7 @@ Layer Normalization
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 5 minutes 24.882 seconds)
**Total running time of the script:** ( 5 minutes 24.552 seconds)
.. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

View File

@@ -5,16 +5,16 @@
Computation times
=================
**16:35.469** total execution time for **getting-started_tutorials** files:
**16:38.329** total execution time for **getting-started_tutorials** files:
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:06.178 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:05.069 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:24.882 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:24.552 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:23.140 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:23.445 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:40.793 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:44.788 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.476 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+