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
2022-08-23 00:54:28 +00:00
parent 9a6ec45a5b
commit 42588a2a5c
163 changed files with 274 additions and 274 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
master/_sources/getting-started/tutorials/01-vector-add.rst.txt
View File

@@ -234,7 +234,7 @@ 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
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
@@ -245,7 +245,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p
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
@@ -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 45.595 seconds)
**Total running time of the script:** ( 1 minutes 41.994 seconds)
.. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

20
master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt
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)
0 256.0 546.133347 546.133347 188.321838
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
3 640.0 706.206879 640.000002 158.759699
4 768.0 722.823517 664.216187 162.754967
2 512.0 655.360017 585.142849 154.566038
3 640.0 706.206879 640.000002 160.000000
4 768.0 722.823517 664.216187 163.839992
.. ... ... ... ...
93 12160.0 812.359066 406.179533 198.631953
94 12288.0 812.429770 415.661740 198.895304
95 12416.0 812.498981 412.149375 198.556711
96 12544.0 810.925276 412.546756 198.815254
97 12672.0 811.007961 412.097543 198.873965
93 12160.0 812.359066 405.755985 198.936606
94 12288.0 812.429770 415.661740 199.096718
95 12416.0 812.498981 412.149375 198.755369
96 12544.0 810.925276 412.971190 198.913776
97 12672.0 811.007961 412.097543 199.069228
[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 30.581 seconds)
**Total running time of the script:** ( 3 minutes 29.122 seconds)
.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

46
master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt
View File

@@ -459,37 +459,37 @@ 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 3.276800
0 256.0 2.730667 ... 3.276800 2.978909
1 384.0 7.372800 ... 8.507077 8.507077
2 512.0 14.563555 ... 16.384000 16.384000
2 512.0 14.563555 ... 16.384000 15.420235
3 640.0 22.260869 ... 24.380953 24.380953
4 768.0 32.768000 ... 35.389441 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 48.161033
7 1152.0 44.566925 ... 47.396572 47.396572
8 1280.0 51.200001 ... 57.690139 57.690139
9 1408.0 64.138541 ... 69.009825 68.147202
10 1536.0 80.430545 ... 81.355034 79.526831
9 1408.0 64.138541 ... 68.147202 67.305878
10 1536.0 80.430545 ... 81.355034 78.643199
11 1664.0 62.929456 ... 63.372618 62.492442
12 1792.0 72.512412 ... 73.460287 59.467852
13 1920.0 69.120002 ... 71.257735 71.257735
13 1920.0 69.120002 ... 71.626943 71.257735
14 2048.0 73.908442 ... 78.398206 77.314362
15 2176.0 83.500614 ... 87.876193 86.367588
16 2304.0 68.446623 ... 78.064941 77.307030
17 2432.0 71.305746 ... 86.179335 85.653855
18 2560.0 77.833728 ... 82.125311 81.715711
19 2688.0 83.552988 ... 90.748936 89.254248
20 2816.0 83.873477 ... 84.687779 83.873477
21 2944.0 81.967162 ... 81.431424 83.337844
22 3072.0 81.589488 ... 86.712254 88.197981
23 3200.0 84.099871 ... 96.749806 95.238096
24 3328.0 82.939284 ... 85.096096 84.695641
25 3456.0 80.300370 ... 91.615417 86.596744
26 3584.0 83.876297 ... 88.152348 93.857401
27 3712.0 85.528545 ... 83.526206 87.629253
28 3840.0 81.798814 ... 88.086021 90.058629
29 3968.0 87.976885 ... 91.989400 86.296981
30 4096.0 93.142072 ... 83.105343 84.626564
15 2176.0 83.500614 ... 87.494120 85.998493
16 2304.0 68.446623 ... 77.810656 77.307030
17 2432.0 71.305746 ... 86.047367 80.155391
18 2560.0 78.019048 ... 82.331658 81.108913
19 2688.0 83.369354 ... 90.102270 89.888756
20 2816.0 79.733474 ... 83.873477 83.712490
21 2944.0 81.832567 ... 82.921853 82.102191
22 3072.0 82.540970 ... 88.820552 85.922766
23 3200.0 79.601989 ... 89.761569 95.952022
24 3328.0 83.516586 ... 85.806075 85.703924
25 3456.0 78.463811 ... 90.738961 83.632331
26 3584.0 86.540320 ... 88.152348 93.955476
27 3712.0 85.748791 ... 85.345876 87.475786
28 3840.0 82.592983 ... 87.286505 90.500819
29 3968.0 86.788006 ... 91.609561 84.096442
30 4096.0 92.691803 ... 90.200084 86.480498
[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 29.672 seconds)
**Total running time of the script:** ( 6 minutes 19.422 seconds)
.. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

58
master/_sources/getting-started/tutorials/05-layer-norm.rst.txt
View File

@@ -38,36 +38,36 @@ Layer Normalization
layer-norm:
N Triton Torch Apex
0 1024.0 585.142849 277.694907 468.114273
0 1024.0 585.142849 277.694907 481.882344
1 1536.0 630.153868 323.368435 511.999982
2 2048.0 668.734716 334.367358 520.126988
3 2560.0 694.237267 365.714281 518.481028
4 3072.0 712.347810 378.092307 496.484863
5 3584.0 725.873439 384.859062 451.527536
2 2048.0 682.666643 334.367358 520.126988
3 2560.0 694.237267 362.477870 518.481028
4 3072.0 712.347810 378.092307 501.551037
5 3584.0 725.873439 384.859062 458.751978
6 4096.0 728.177767 381.023256 455.111095
7 4608.0 670.254540 394.267384 421.302872
8 5120.0 688.403381 397.669909 424.455959
9 5632.0 698.542675 395.228063 411.470331
10 6144.0 702.171410 402.885254 411.313806
11 6656.0 700.631610 398.861429 400.360920
12 7168.0 690.891575 396.844306 387.459443
13 7680.0 678.895043 393.846167 386.415087
14 8192.0 636.271854 393.609605 372.363633
15 8704.0 627.315309 389.005597 380.502740
16 9216.0 606.814809 407.337026 383.999986
17 9728.0 587.350922 409.599987 382.427505
18 10240.0 564.965524 408.578556 382.803739
19 10752.0 547.872604 411.559798 381.445676
20 11264.0 533.207081 406.826188 373.134567
21 11776.0 520.486200 409.599991 377.587162
22 12288.0 514.680630 413.911572 383.251457
23 12800.0 504.433489 410.420828 376.470582
24 13312.0 494.180982 405.699062 376.976995
25 13824.0 482.934503 411.122660 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 406.974373 376.783377
7 4608.0 670.254540 396.387087 426.173427
8 5120.0 688.403381 395.748783 424.455959
9 5632.0 704.000002 396.969169 413.357796
10 6144.0 697.191505 402.885254 411.313806
11 6656.0 700.631610 400.360920 398.861429
12 7168.0 686.754468 383.571898 381.023265
13 7680.0 678.895043 391.337574 386.415087
14 8192.0 642.509816 390.095241 377.729113
15 8704.0 621.714277 390.095225 379.465939
16 9216.0 601.861217 403.989025 383.002605
17 9728.0 585.142883 409.599987 382.427505
18 10240.0 563.024047 409.600010 382.803739
19 10752.0 546.133312 410.577576 380.601764
20 11264.0 531.634232 397.845487 371.595879
21 11776.0 519.052343 409.599991 377.587162
22 12288.0 516.031509 413.911572 382.505826
23 12800.0 503.194086 409.599981 376.470582
24 13312.0 494.180982 407.250459 376.976995
25 13824.0 481.882350 411.888257 379.389355
26 14336.0 471.967074 399.609753 371.760140
27 14848.0 461.297068 405.406157 374.712936
28 15360.0 454.269882 407.562194 378.092307
29 15872.0 447.887117 406.974373 376.225175
@@ -393,7 +393,7 @@ Layer Normalization
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 5 minutes 36.337 seconds)
**Total running time of the script:** ( 5 minutes 29.220 seconds)
.. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py:

2
master/_sources/getting-started/tutorials/06-fused-attention.rst.txt
View File

@@ -390,7 +390,7 @@ This is a Triton implementation of the Flash Attention algorithm
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 0 minutes 0.072 seconds)
**Total running time of the script:** ( 0 minutes 0.076 seconds)
.. _sphx_glr_download_getting-started_tutorials_06-fused-attention.py:

2
master/_sources/getting-started/tutorials/07-libdevice-function.rst.txt
View File

@@ -152,7 +152,7 @@ We can also customize the libdevice library path by passing the path to the `lib
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 0 minutes 0.010 seconds)
**Total running time of the script:** ( 0 minutes 0.012 seconds)
.. _sphx_glr_download_getting-started_tutorials_07-libdevice-function.py:

14
master/_sources/getting-started/tutorials/sg_execution_times.rst.txt
View File

@@ -5,20 +5,20 @@
Computation times
=================
**17:22.279** total execution time for **getting-started_tutorials** files:
**16:59.858** total execution time for **getting-started_tutorials** files:
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:29.672 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:19.422 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:36.337 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:29.220 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:30.581 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:29.122 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:45.595 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:41.994 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``) | 00:00.072 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``) | 00:00.076 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.012 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.010 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.012 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+