[GH-PAGES] Updated website
This commit is contained in:
@@ -234,13 +234,13 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
|
||||
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
|
||||
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
|
||||
7 524288.0 472.615390 472.615390
|
||||
8 1048576.0 614.400016 614.400016
|
||||
9 2097152.0 722.823517 722.823517
|
||||
9 2097152.0 722.823517 702.171410
|
||||
10 4194304.0 780.190482 780.190482
|
||||
11 8388608.0 812.429770 812.429770
|
||||
12 16777216.0 833.084721 833.084721
|
||||
@@ -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 45.148 seconds)
|
||||
**Total running time of the script:** ( 1 minutes 37.395 seconds)
|
||||
|
||||
|
||||
.. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:
|
||||
|
@@ -286,17 +286,17 @@ 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
|
||||
1 384.0 614.400016 585.142862 153.600004
|
||||
2 512.0 655.360017 606.814814 154.566038
|
||||
0 256.0 512.000001 512.000001 190.511628
|
||||
1 384.0 585.142862 585.142862 153.600004
|
||||
2 512.0 655.360017 585.142849 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
|
||||
94 12288.0 814.111783 416.101597 199.197579
|
||||
95 12416.0 812.498981 412.149375 198.854847
|
||||
96 12544.0 812.566838 412.971190 199.111113
|
||||
97 12672.0 812.633240 412.097543 199.167004
|
||||
93 12160.0 812.359066 406.179533 198.834951
|
||||
94 12288.0 814.111783 415.661740 199.096718
|
||||
95 12416.0 812.498981 412.149375 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 21.863 seconds)
|
||||
**Total running time of the script:** ( 3 minutes 18.756 seconds)
|
||||
|
||||
|
||||
.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:
|
||||
|
@@ -462,37 +462,37 @@ 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 ... 2.978909 2.978909
|
||||
1 384.0 7.372800 ... 8.507077 7.899428
|
||||
0 256.0 2.730667 ... 2.978909 2.978909
|
||||
1 384.0 7.372800 ... 8.507077 8.507077
|
||||
2 512.0 14.563555 ... 16.384000 15.420235
|
||||
3 640.0 22.260869 ... 24.380953 24.380953
|
||||
4 768.0 32.768000 ... 34.028308 34.028308
|
||||
5 896.0 39.025776 ... 40.140799 39.025776
|
||||
6 1024.0 51.150050 ... 52.428801 52.428801
|
||||
7 1152.0 45.242181 ... 47.396572 46.656000
|
||||
8 1280.0 51.200001 ... 56.888887 56.888887
|
||||
9 1408.0 64.138541 ... 67.305878 67.305878
|
||||
10 1536.0 80.430545 ... 79.526831 79.526831
|
||||
11 1664.0 63.372618 ... 62.492442 62.061463
|
||||
12 1792.0 72.983276 ... 72.512412 72.047592
|
||||
13 1920.0 69.120002 ... 70.530615 70.172588
|
||||
14 2048.0 73.908442 ... 77.314362 76.959706
|
||||
15 2176.0 83.500614 ... 86.367588 85.632545
|
||||
16 2304.0 68.251065 ... 77.057651 76.076024
|
||||
5 896.0 39.025776 ... 39.025776 37.971025
|
||||
6 1024.0 49.932191 ... 53.773130 52.428801
|
||||
7 1152.0 45.242181 ... 46.656000 46.656000
|
||||
8 1280.0 51.200001 ... 56.888887 56.109587
|
||||
9 1408.0 64.138541 ... 67.305878 66.485074
|
||||
10 1536.0 80.430545 ... 79.526831 78.643199
|
||||
11 1664.0 62.929456 ... 62.061463 62.061463
|
||||
12 1792.0 72.512412 ... 72.047592 71.588687
|
||||
13 1920.0 69.120002 ... 70.530615 70.530615
|
||||
14 2048.0 73.908442 ... 76.959706 76.959706
|
||||
15 2176.0 83.500614 ... 85.998493 85.632545
|
||||
16 2304.0 68.251065 ... 76.319081 76.563695
|
||||
17 2432.0 71.305746 ... 74.719317 84.877538
|
||||
18 2560.0 77.833728 ... 80.908642 80.511054
|
||||
19 2688.0 83.737433 ... 89.254248 89.888756
|
||||
20 2816.0 81.369790 ... 82.290955 83.233226
|
||||
21 2944.0 81.832567 ... 81.564701 82.509987
|
||||
22 3072.0 82.661468 ... 88.335577 88.060814
|
||||
23 3200.0 83.009080 ... 95.522391 95.238096
|
||||
24 3328.0 82.843841 ... 84.052885 84.200347
|
||||
25 3456.0 80.140726 ... 91.200871 90.892410
|
||||
26 3584.0 86.540320 ... 94.647779 94.997774
|
||||
27 3712.0 85.019017 ... 87.475786 87.706180
|
||||
28 3840.0 84.036474 ... 91.247522 89.295115
|
||||
29 3968.0 91.540836 ... 83.921126 91.198760
|
||||
30 4096.0 86.202781 ... 86.480498 91.118618
|
||||
18 2560.0 77.833728 ... 81.310171 80.908642
|
||||
19 2688.0 83.004501 ... 88.732296 89.044730
|
||||
20 2816.0 79.443003 ... 82.290955 83.074685
|
||||
21 2944.0 82.102191 ... 83.198715 82.373605
|
||||
22 3072.0 82.181572 ... 87.651868 82.661468
|
||||
23 3200.0 80.808083 ... 95.808380 94.955488
|
||||
24 3328.0 83.323259 ... 80.347427 84.596116
|
||||
25 3456.0 81.477080 ... 86.689860 90.281712
|
||||
26 3584.0 87.296493 ... 98.483450 93.564405
|
||||
27 3712.0 84.088676 ... 88.404730 86.791782
|
||||
28 3840.0 84.615146 ... 92.083268 84.102376
|
||||
29 3968.0 92.372393 ... 80.278903 84.299785
|
||||
30 4096.0 90.443212 ... 86.369197 89.538177
|
||||
|
||||
[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 25.100 seconds)
|
||||
**Total running time of the script:** ( 5 minutes 18.032 seconds)
|
||||
|
||||
|
||||
.. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:
|
||||
|
@@ -38,36 +38,36 @@ Layer Normalization
|
||||
|
||||
layer-norm-backward:
|
||||
N Triton Torch Apex
|
||||
0 1024.0 311.088617 99.096776 311.088617
|
||||
1 1536.0 351.085717 133.083026 341.333333
|
||||
2 2048.0 423.724127 162.217818 338.979315
|
||||
3 2560.0 461.954908 182.857144 330.322572
|
||||
4 3072.0 511.999982 191.501303 315.076914
|
||||
5 3584.0 554.941930 208.271186 310.527060
|
||||
0 1024.0 311.088617 99.096776 307.200008
|
||||
1 1536.0 351.085717 133.083026 338.201833
|
||||
2 2048.0 423.724127 162.217818 336.657521
|
||||
3 2560.0 461.954908 182.857144 328.556154
|
||||
4 3072.0 511.999982 191.501303 320.556515
|
||||
5 3584.0 554.941930 208.271186 308.301075
|
||||
6 4096.0 568.231237 220.412561 297.890900
|
||||
7 4608.0 498.162157 231.849059 290.267724
|
||||
8 5120.0 525.128191 242.845844 286.433562
|
||||
9 5632.0 538.517949 243.107920 290.683877
|
||||
10 6144.0 544.118087 248.661056 286.322318
|
||||
7 4608.0 498.162157 231.849059 287.251954
|
||||
8 5120.0 525.128191 242.845844 283.787523
|
||||
9 5632.0 538.517949 243.545956 290.683877
|
||||
10 6144.0 542.117638 248.661056 285.767458
|
||||
11 6656.0 527.207907 256.000009 286.279570
|
||||
12 7168.0 505.976473 262.243907 288.160801
|
||||
13 7680.0 482.513091 260.707203 277.172933
|
||||
14 8192.0 460.440290 268.957600 286.600589
|
||||
12 7168.0 505.976473 261.844750 288.160801
|
||||
13 7680.0 482.513091 260.707203 277.590365
|
||||
14 8192.0 460.440290 268.957600 286.183409
|
||||
15 8704.0 416.958106 267.815384 285.377055
|
||||
16 9216.0 428.651187 272.729961 289.507855
|
||||
17 9728.0 439.683593 280.615388 288.950501
|
||||
18 10240.0 446.836366 286.767793 290.153487
|
||||
19 10752.0 430.079980 246.464170 289.941565
|
||||
20 11264.0 429.786952 245.091565 285.767446
|
||||
21 11776.0 421.198220 249.227509 288.686414
|
||||
17 9728.0 439.683593 280.278512 288.950501
|
||||
18 10240.0 447.650282 286.767793 290.496460
|
||||
19 10752.0 430.079980 246.464170 290.267711
|
||||
20 11264.0 429.104745 245.091565 285.767446
|
||||
21 11776.0 421.198220 249.447482 288.686414
|
||||
22 12288.0 420.102570 254.453844 295.207195
|
||||
23 12800.0 415.696898 253.465340 288.180121
|
||||
23 12800.0 415.696898 253.465340 288.721817
|
||||
24 13312.0 412.242569 252.559690 290.179836
|
||||
25 13824.0 405.098897 257.190689 292.571423
|
||||
25 13824.0 405.098897 257.590056 292.571423
|
||||
26 14336.0 397.761846 254.673567 286.481278
|
||||
27 14848.0 384.414233 257.108233 289.246765
|
||||
28 15360.0 374.443863 257.790220 287.775181
|
||||
29 15872.0 366.982663 262.890274 291.006885
|
||||
28 15360.0 374.253788 257.790220 287.550706
|
||||
29 15872.0 366.982663 262.890274 291.229369
|
||||
|
||||
|
||||
|
||||
@@ -329,7 +329,7 @@ Layer Normalization
|
||||
|
||||
.. rst-class:: sphx-glr-timing
|
||||
|
||||
**Total running time of the script:** ( 2 minutes 10.934 seconds)
|
||||
**Total running time of the script:** ( 2 minutes 12.525 seconds)
|
||||
|
||||
|
||||
.. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:
|
||||
|
@@ -5,16 +5,16 @@
|
||||
|
||||
Computation times
|
||||
=================
|
||||
**12:43.056** total execution time for **getting-started_tutorials** files:
|
||||
**12:26.718** total execution time for **getting-started_tutorials** files:
|
||||
|
||||
+---------------------------------------------------------------------------------------------------------+-----------+--------+
|
||||
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:25.100 | 0.0 MB |
|
||||
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:18.032 | 0.0 MB |
|
||||
+---------------------------------------------------------------------------------------------------------+-----------+--------+
|
||||
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:21.863 | 0.0 MB |
|
||||
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:18.756 | 0.0 MB |
|
||||
+---------------------------------------------------------------------------------------------------------+-----------+--------+
|
||||
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:10.934 | 0.0 MB |
|
||||
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:12.525 | 0.0 MB |
|
||||
+---------------------------------------------------------------------------------------------------------+-----------+--------+
|
||||
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:45.148 | 0.0 MB |
|
||||
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:37.395 | 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 |
|
||||
+---------------------------------------------------------------------------------------------------------+-----------+--------+
|
||||
|
Reference in New Issue
Block a user