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
2022-02-28 00:41:59 +00:00
parent a64f41ab97
commit 11bcbd3d04
156 changed files with 276 additions and 276 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
v1.1.2/_sources/getting-started/tutorials/01-vector-add.rst.txt
View File

@@ -233,18 +233,18 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
size Triton Torch
0 4096.0 9.600000 9.600000
1 8192.0 19.200000 19.200000
2 16384.0 38.400001 38.400001
3 32768.0 63.999998 63.999998
2 16384.0 31.999999 38.400001
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 722.823517
10 4194304.0 780.190482 780.190482
11 8388608.0 812.429770 812.429770
12 16777216.0 833.084721 833.084721
13 33554432.0 842.004273 843.811163
13 33554432.0 842.004273 842.004273
14 67108864.0 847.448255 848.362445
15 134217728.0 849.737435 850.656574
@@ -254,7 +254,7 @@ 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 42.564 seconds)
**Total running time of the script:** ( 1 minutes 40.495 seconds)
.. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

10
v1.1.2/_sources/getting-started/tutorials/02-fused-softmax.rst.txt
View File

@@ -286,16 +286,16 @@ 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
0 256.0 512.000001 546.133347 190.511628
1 384.0 585.142862 585.142862 153.600004
2 512.0 655.360017 606.814814 154.566038
3 640.0 682.666684 640.000002 160.000000
4 768.0 722.823517 664.216187 162.754967
.. ... ... ... ...
93 12160.0 814.058574 406.179533 198.834951
93 12160.0 814.058574 406.179533 198.936606
94 12288.0 814.111783 415.661740 199.197579
95 12416.0 812.498981 412.149375 198.755369
96 12544.0 812.566838 412.971190 198.913776
95 12416.0 812.498981 412.577363 198.755369
96 12544.0 812.566838 412.971190 199.012395
97 12672.0 812.633240 412.097543 199.069228
[98 rows x 4 columns]
@@ -314,7 +314,7 @@ In the above plot, we can see that:
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 3 minutes 23.367 seconds)
**Total running time of the script:** ( 3 minutes 23.196 seconds)
.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

38
v1.1.2/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt
View File

@@ -462,7 +462,7 @@ 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 2.978909 ... 3.276800 2.978909
0 256.0 2.978909 ... 3.276800 3.276800
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 16.384000 16.384000
3 640.0 22.260869 ... 24.380953 24.380953
@@ -476,23 +476,23 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
11 1664.0 62.929456 ... 62.492442 62.061463
12 1792.0 72.512412 ... 72.047592 71.588687
13 1920.0 68.776119 ... 70.172588 70.172588
14 2048.0 73.584279 ... 76.608294 76.959706
15 2176.0 83.500614 ... 85.632545 84.909907
16 2304.0 68.446623 ... 76.809875 76.076024
17 2432.0 71.125224 ... 85.134737 84.115159
18 2560.0 78.019048 ... 80.709358 80.313727
19 2688.0 83.552988 ... 89.464755 88.836198
20 2816.0 82.290955 ... 83.233226 82.602666
21 2944.0 82.102191 ... 82.646820 82.646820
22 3072.0 81.825298 ... 88.197981 88.060814
23 3200.0 84.656085 ... 95.238096 94.674553
24 3328.0 83.034941 ... 82.275764 81.162679
25 3456.0 81.683457 ... 89.579522 91.200871
26 3584.0 87.127323 ... 90.458141 94.548254
27 3712.0 85.455380 ... 88.092894 91.481080
28 3840.0 82.041542 ... 87.148936 91.097196
29 3968.0 85.869991 ... 90.522206 87.913500
30 4096.0 92.755862 ... 81.991628 90.018600
14 2048.0 73.584279 ... 76.959706 76.608294
15 2176.0 83.500614 ... 85.998493 85.269692
16 2304.0 68.544825 ... 77.057651 76.076024
17 2432.0 71.305746 ... 84.877538 84.877538
18 2560.0 78.019048 ... 80.709358 80.908642
19 2688.0 83.004501 ... 89.676257 89.044730
20 2816.0 83.074685 ... 82.995641 83.233226
21 2944.0 82.509987 ... 81.564701 82.237674
22 3072.0 82.003045 ... 88.335577 86.845249
23 3200.0 82.262212 ... 91.954023 92.086332
24 3328.0 80.527177 ... 84.895397 84.995628
25 3456.0 82.773682 ... 91.200871 90.892410
26 3584.0 84.825838 ... 91.656871 94.947616
27 3712.0 85.601834 ... 88.955788 86.791782
28 3840.0 80.255442 ... 86.265212 91.549669
29 3968.0 88.040360 ... 91.130650 84.797731
30 4096.0 93.531519 ... 88.243079 86.258181
[31 rows x 5 columns]
@@ -502,7 +502,7 @@ 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:** ( 5 minutes 27.871 seconds)
**Total running time of the script:** ( 5 minutes 29.403 seconds)
.. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

52
v1.1.2/_sources/getting-started/tutorials/05-layer-norm.rst.txt
View File

@@ -38,36 +38,36 @@ Layer Normalization
layer-norm-backward:
N Triton Torch Apex
0 1024.0 307.200008 98.303995 303.407414
1 1536.0 351.085717 134.050910 341.333333
2 2048.0 423.724127 161.684218 334.367350
3 2560.0 465.454542 181.238943 328.556154
4 3072.0 511.999982 191.999993 320.556515
5 3584.0 551.384634 207.768111 310.527060
6 4096.0 568.231237 220.412561 298.796351
0 1024.0 311.088617 98.303995 307.200008
1 1536.0 351.085717 134.540150 341.333333
2 2048.0 423.724127 161.684218 325.509933
3 2560.0 465.454542 181.775141 326.808501
4 3072.0 515.580429 192.501302 320.556515
5 3584.0 554.941930 208.271186 310.527060
6 4096.0 571.534884 220.412561 299.707322
7 4608.0 498.162157 232.825259 287.251954
8 5120.0 527.381977 242.845844 285.104413
9 5632.0 540.671974 243.107920 290.683877
10 6144.0 544.118087 248.242431 286.322318
8 5120.0 527.381977 242.845844 287.775181
9 5632.0 540.671974 243.545956 289.438969
10 6144.0 544.118087 248.661056 286.879370
11 6656.0 532.479975 256.000009 285.767438
12 7168.0 507.469040 260.654538 286.242939
13 7680.0 479.999983 262.190612 274.694491
14 8192.0 463.698115 266.767970 284.939124
15 8704.0 416.958106 267.472468 284.212242
16 9216.0 429.483477 272.059034 288.751954
17 9728.0 437.213490 280.615388 289.667485
18 10240.0 449.287041 286.433562 287.438599
19 10752.0 428.651173 247.172406 290.922209
20 11264.0 429.104745 245.536784 286.980888
21 11776.0 423.724129 249.667843 288.981596
13 7680.0 479.999983 262.564106 278.850215
14 8192.0 463.698115 267.130429 284.939124
15 8704.0 416.958106 267.472468 284.599455
16 9216.0 429.483477 272.729961 288.751954
17 9728.0 437.213490 280.278512 290.027323
18 10240.0 449.287041 286.433562 290.153487
19 10752.0 428.651173 246.935876 290.922209
20 11264.0 429.104745 245.536784 286.676558
21 11776.0 423.724129 249.888595 288.981596
22 12288.0 420.102570 254.673582 294.323369
23 12800.0 414.574901 253.256381 289.538159
24 13312.0 411.711355 252.559690 289.916513
23 12800.0 414.574901 253.674644 288.180121
24 13312.0 411.711355 252.959629 290.179836
25 13824.0 405.098897 257.390218 292.056329
26 14336.0 395.021816 254.297107 286.719986
27 14848.0 385.662341 257.665934 289.246765
28 15360.0 373.874218 257.790220 287.102804
29 15872.0 369.832994 261.806182 289.899545
26 14336.0 395.021816 254.297107 286.839504
27 14848.0 386.080180 257.665934 289.246765
28 15360.0 373.495460 257.970599 286.322325
29 15872.0 370.192407 261.626369 289.899545
@@ -329,7 +329,7 @@ Layer Normalization
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 2 minutes 13.380 seconds)
**Total running time of the script:** ( 2 minutes 12.617 seconds)
.. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

12
v1.1.2/_sources/getting-started/tutorials/sg_execution_times.rst.txt
View File

@@ -5,16 +5,16 @@
Computation times
=================
**12:47.192** total execution time for **getting-started_tutorials** files:
**12:45.723** total execution time for **getting-started_tutorials** files:
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:27.871 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:29.403 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:23.367 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:23.196 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:13.380 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:12.617 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:42.564 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:40.495 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.010 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.011 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+