diff --git a/master/.buildinfo b/master/.buildinfo index dcc24689c..857b2d32f 100644 --- a/master/.buildinfo +++ b/master/.buildinfo @@ -1,4 +1,4 @@ # Sphinx build info version 1 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done. -config: 8854530bca5900a6d2403fdb7d46c23c +config: 3b66780e257fdfca48695fc8f9205443 tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/master/.doctrees/environment.pickle b/master/.doctrees/environment.pickle index aea72a91d..787e6a11f 100644 Binary files a/master/.doctrees/environment.pickle and b/master/.doctrees/environment.pickle differ diff --git a/master/.doctrees/getting-started/installation.doctree b/master/.doctrees/getting-started/installation.doctree index 852b51477..d0de267b5 100644 Binary files a/master/.doctrees/getting-started/installation.doctree and b/master/.doctrees/getting-started/installation.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/01-vector-add.doctree b/master/.doctrees/getting-started/tutorials/01-vector-add.doctree index 9d3295cd4..c312a05d7 100644 Binary files a/master/.doctrees/getting-started/tutorials/01-vector-add.doctree and b/master/.doctrees/getting-started/tutorials/01-vector-add.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/02-fused-softmax.doctree b/master/.doctrees/getting-started/tutorials/02-fused-softmax.doctree index 6ed43cac0..7d36d0845 100644 Binary files a/master/.doctrees/getting-started/tutorials/02-fused-softmax.doctree and b/master/.doctrees/getting-started/tutorials/02-fused-softmax.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree b/master/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree index 736fca78d..305858350 100644 Binary files a/master/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree and b/master/.doctrees/getting-started/tutorials/03-matrix-multiplication.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree b/master/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree index 35cfe877d..a7b2be38d 100644 Binary files a/master/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree and b/master/.doctrees/getting-started/tutorials/04-low-memory-dropout.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/05-layer-norm.doctree b/master/.doctrees/getting-started/tutorials/05-layer-norm.doctree index 7c35cca34..6f341d86f 100644 Binary files a/master/.doctrees/getting-started/tutorials/05-layer-norm.doctree and b/master/.doctrees/getting-started/tutorials/05-layer-norm.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/index.doctree b/master/.doctrees/getting-started/tutorials/index.doctree index afb80799f..1cad1243c 100644 Binary files a/master/.doctrees/getting-started/tutorials/index.doctree and b/master/.doctrees/getting-started/tutorials/index.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/sg_execution_times.doctree b/master/.doctrees/getting-started/tutorials/sg_execution_times.doctree index 9b3fe3055..3913c559d 100644 Binary files a/master/.doctrees/getting-started/tutorials/sg_execution_times.doctree and b/master/.doctrees/getting-started/tutorials/sg_execution_times.doctree differ diff --git a/master/.doctrees/index.doctree b/master/.doctrees/index.doctree index 4a66d1bbb..b54573da3 100644 Binary files a/master/.doctrees/index.doctree and b/master/.doctrees/index.doctree differ diff --git a/master/.doctrees/programming-guide/chapter-1/introduction.doctree b/master/.doctrees/programming-guide/chapter-1/introduction.doctree index ba71edc13..9a3e1de88 100644 Binary files a/master/.doctrees/programming-guide/chapter-1/introduction.doctree and b/master/.doctrees/programming-guide/chapter-1/introduction.doctree differ diff --git a/master/.doctrees/programming-guide/chapter-2/related-work.doctree b/master/.doctrees/programming-guide/chapter-2/related-work.doctree index c59e9fe55..e93a472b0 100644 Binary files a/master/.doctrees/programming-guide/chapter-2/related-work.doctree and b/master/.doctrees/programming-guide/chapter-2/related-work.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.Config.doctree b/master/.doctrees/python-api/generated/triton.Config.doctree index cbed8b686..5531e10f0 100644 Binary files a/master/.doctrees/python-api/generated/triton.Config.doctree and b/master/.doctrees/python-api/generated/triton.Config.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.autotune.doctree b/master/.doctrees/python-api/generated/triton.autotune.doctree index 5eb2f91f3..e09b08a13 100644 Binary files a/master/.doctrees/python-api/generated/triton.autotune.doctree and b/master/.doctrees/python-api/generated/triton.autotune.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.heuristics.doctree b/master/.doctrees/python-api/generated/triton.heuristics.doctree index 421c72b07..85f549497 100644 Binary files a/master/.doctrees/python-api/generated/triton.heuristics.doctree and b/master/.doctrees/python-api/generated/triton.heuristics.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.jit.doctree b/master/.doctrees/python-api/generated/triton.jit.doctree index 48b58ff7a..6ff2656d1 100644 Binary files a/master/.doctrees/python-api/generated/triton.jit.doctree and b/master/.doctrees/python-api/generated/triton.jit.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.arange.doctree b/master/.doctrees/python-api/generated/triton.language.arange.doctree index a5b6a44da..dcf128b63 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.arange.doctree and b/master/.doctrees/python-api/generated/triton.language.arange.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_add.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_add.doctree index 8823cb533..cdc24c578 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_add.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_add.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_cas.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_cas.doctree index 32838c5d7..bceb984ea 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_cas.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_cas.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_max.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_max.doctree index 56c878fd6..ffc3c735d 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_max.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_max.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_min.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_min.doctree index 903a589cf..1dcb7f9b5 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_min.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_min.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.atomic_xchg.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_xchg.doctree index 59cda0453..14c19a3b5 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_xchg.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_xchg.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.broadcast_to.doctree b/master/.doctrees/python-api/generated/triton.language.broadcast_to.doctree index 7e7f45e40..64fa5dae2 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.broadcast_to.doctree and b/master/.doctrees/python-api/generated/triton.language.broadcast_to.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.cos.doctree b/master/.doctrees/python-api/generated/triton.language.cos.doctree index 8b50e56cd..d9639b741 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.cos.doctree and b/master/.doctrees/python-api/generated/triton.language.cos.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.dot.doctree b/master/.doctrees/python-api/generated/triton.language.dot.doctree index 5fc3a7da1..793cb11e1 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.dot.doctree and b/master/.doctrees/python-api/generated/triton.language.dot.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.exp.doctree b/master/.doctrees/python-api/generated/triton.language.exp.doctree index 74e859cd9..146a6160e 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.exp.doctree and b/master/.doctrees/python-api/generated/triton.language.exp.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.load.doctree b/master/.doctrees/python-api/generated/triton.language.load.doctree index 4c1e57ab5..4ff295e8f 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.load.doctree and b/master/.doctrees/python-api/generated/triton.language.load.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.log.doctree b/master/.doctrees/python-api/generated/triton.language.log.doctree index f1ab35f3b..057de6026 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.log.doctree and b/master/.doctrees/python-api/generated/triton.language.log.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.max.doctree b/master/.doctrees/python-api/generated/triton.language.max.doctree index 911181df7..1e5719100 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.max.doctree and b/master/.doctrees/python-api/generated/triton.language.max.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.maximum.doctree b/master/.doctrees/python-api/generated/triton.language.maximum.doctree index 6dee585f6..dd23e0d8a 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.maximum.doctree and b/master/.doctrees/python-api/generated/triton.language.maximum.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.min.doctree b/master/.doctrees/python-api/generated/triton.language.min.doctree index f91e5a6f4..3a66ebee3 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.min.doctree and b/master/.doctrees/python-api/generated/triton.language.min.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.minimum.doctree b/master/.doctrees/python-api/generated/triton.language.minimum.doctree index 02f7d172a..6ab14f112 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.minimum.doctree and b/master/.doctrees/python-api/generated/triton.language.minimum.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.multiple_of.doctree b/master/.doctrees/python-api/generated/triton.language.multiple_of.doctree index d87635730..7e8da0f96 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.multiple_of.doctree and b/master/.doctrees/python-api/generated/triton.language.multiple_of.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.num_programs.doctree b/master/.doctrees/python-api/generated/triton.language.num_programs.doctree index a61e041e7..6adbd025b 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.num_programs.doctree and b/master/.doctrees/python-api/generated/triton.language.num_programs.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.program_id.doctree b/master/.doctrees/python-api/generated/triton.language.program_id.doctree index 50b77c176..204ab7af3 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.program_id.doctree and b/master/.doctrees/python-api/generated/triton.language.program_id.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.rand.doctree b/master/.doctrees/python-api/generated/triton.language.rand.doctree index 153a36679..576d47cea 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.rand.doctree and b/master/.doctrees/python-api/generated/triton.language.rand.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.randint.doctree b/master/.doctrees/python-api/generated/triton.language.randint.doctree index 3472c8854..e0db33731 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.randint.doctree and b/master/.doctrees/python-api/generated/triton.language.randint.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.randint4x.doctree b/master/.doctrees/python-api/generated/triton.language.randint4x.doctree index ad3166c64..868f4c202 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.randint4x.doctree and b/master/.doctrees/python-api/generated/triton.language.randint4x.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.randn.doctree b/master/.doctrees/python-api/generated/triton.language.randn.doctree index fe705cce7..13a8ec746 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.randn.doctree and b/master/.doctrees/python-api/generated/triton.language.randn.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.ravel.doctree b/master/.doctrees/python-api/generated/triton.language.ravel.doctree index c3660165d..68cc6b576 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.ravel.doctree and b/master/.doctrees/python-api/generated/triton.language.ravel.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.reshape.doctree b/master/.doctrees/python-api/generated/triton.language.reshape.doctree index e342a5c49..78f206ff4 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.reshape.doctree and b/master/.doctrees/python-api/generated/triton.language.reshape.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.sigmoid.doctree b/master/.doctrees/python-api/generated/triton.language.sigmoid.doctree index a807c20dc..ce21c7fd1 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.sigmoid.doctree and b/master/.doctrees/python-api/generated/triton.language.sigmoid.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.sin.doctree b/master/.doctrees/python-api/generated/triton.language.sin.doctree index 7a1dc0326..7b456a941 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.sin.doctree and b/master/.doctrees/python-api/generated/triton.language.sin.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.softmax.doctree b/master/.doctrees/python-api/generated/triton.language.softmax.doctree index 60d28434f..ba9b84ab4 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.softmax.doctree and b/master/.doctrees/python-api/generated/triton.language.softmax.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.sqrt.doctree b/master/.doctrees/python-api/generated/triton.language.sqrt.doctree index d2b931076..7c5642e6e 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.sqrt.doctree and b/master/.doctrees/python-api/generated/triton.language.sqrt.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.store.doctree b/master/.doctrees/python-api/generated/triton.language.store.doctree index 95d0fb565..972d0b9ef 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.store.doctree and b/master/.doctrees/python-api/generated/triton.language.store.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.sum.doctree b/master/.doctrees/python-api/generated/triton.language.sum.doctree index f3780c04a..2817d488a 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.sum.doctree and b/master/.doctrees/python-api/generated/triton.language.sum.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.where.doctree b/master/.doctrees/python-api/generated/triton.language.where.doctree index 9e2d22f31..c97a0217c 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.where.doctree and b/master/.doctrees/python-api/generated/triton.language.where.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.language.zeros.doctree b/master/.doctrees/python-api/generated/triton.language.zeros.doctree index 8b20630e4..754a3907e 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.zeros.doctree and b/master/.doctrees/python-api/generated/triton.language.zeros.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.testing.Benchmark.doctree b/master/.doctrees/python-api/generated/triton.testing.Benchmark.doctree index 5b8e1ba04..6d80cb50e 100644 Binary files a/master/.doctrees/python-api/generated/triton.testing.Benchmark.doctree and b/master/.doctrees/python-api/generated/triton.testing.Benchmark.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.testing.do_bench.doctree b/master/.doctrees/python-api/generated/triton.testing.do_bench.doctree index d4c1001f4..57e0c029a 100644 Binary files a/master/.doctrees/python-api/generated/triton.testing.do_bench.doctree and b/master/.doctrees/python-api/generated/triton.testing.do_bench.doctree differ diff --git a/master/.doctrees/python-api/generated/triton.testing.perf_report.doctree b/master/.doctrees/python-api/generated/triton.testing.perf_report.doctree index c0354b15f..214d4d900 100644 Binary files a/master/.doctrees/python-api/generated/triton.testing.perf_report.doctree and b/master/.doctrees/python-api/generated/triton.testing.perf_report.doctree differ diff --git a/master/.doctrees/python-api/triton.doctree b/master/.doctrees/python-api/triton.doctree index 05fa55071..c4ad90c0e 100644 Binary files a/master/.doctrees/python-api/triton.doctree and b/master/.doctrees/python-api/triton.doctree differ diff --git a/master/.doctrees/python-api/triton.language.doctree b/master/.doctrees/python-api/triton.language.doctree index 87dc9d842..d4e3ca50a 100644 Binary files a/master/.doctrees/python-api/triton.language.doctree and b/master/.doctrees/python-api/triton.language.doctree differ diff --git a/master/.doctrees/python-api/triton.testing.doctree b/master/.doctrees/python-api/triton.testing.doctree index c4723486a..d88e8e28a 100644 Binary files a/master/.doctrees/python-api/triton.testing.doctree and b/master/.doctrees/python-api/triton.testing.doctree differ diff --git a/master/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip b/master/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip index bf5ca5cba..a7b455426 100644 Binary files a/master/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip and b/master/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip differ diff --git a/master/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip b/master/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip index 908d2c732..3046ca4da 100644 Binary files a/master/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip and b/master/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip differ diff --git a/master/_images/sphx_glr_01-vector-add_001.png b/master/_images/sphx_glr_01-vector-add_001.png index a7d7e71a5..d54d37bcc 100644 Binary files a/master/_images/sphx_glr_01-vector-add_001.png and b/master/_images/sphx_glr_01-vector-add_001.png differ diff --git a/master/_images/sphx_glr_01-vector-add_thumb.png b/master/_images/sphx_glr_01-vector-add_thumb.png index 28de8dbf5..8e49b7455 100644 Binary files a/master/_images/sphx_glr_01-vector-add_thumb.png and b/master/_images/sphx_glr_01-vector-add_thumb.png differ diff --git a/master/_images/sphx_glr_02-fused-softmax_001.png b/master/_images/sphx_glr_02-fused-softmax_001.png index 492b772cb..ac7dd0721 100644 Binary files a/master/_images/sphx_glr_02-fused-softmax_001.png and b/master/_images/sphx_glr_02-fused-softmax_001.png differ diff --git a/master/_images/sphx_glr_02-fused-softmax_thumb.png b/master/_images/sphx_glr_02-fused-softmax_thumb.png index a5deba40b..7d72b4f84 100644 Binary files a/master/_images/sphx_glr_02-fused-softmax_thumb.png and b/master/_images/sphx_glr_02-fused-softmax_thumb.png differ diff --git a/master/_images/sphx_glr_03-matrix-multiplication_001.png b/master/_images/sphx_glr_03-matrix-multiplication_001.png index 18ababcfb..b15a5d6cf 100644 Binary files a/master/_images/sphx_glr_03-matrix-multiplication_001.png and b/master/_images/sphx_glr_03-matrix-multiplication_001.png differ diff --git a/master/_images/sphx_glr_03-matrix-multiplication_thumb.png b/master/_images/sphx_glr_03-matrix-multiplication_thumb.png index 759364e24..4897252d9 100644 Binary files a/master/_images/sphx_glr_03-matrix-multiplication_thumb.png and b/master/_images/sphx_glr_03-matrix-multiplication_thumb.png differ diff --git a/master/_images/sphx_glr_05-layer-norm_001.png b/master/_images/sphx_glr_05-layer-norm_001.png index d29b48bae..32efbdd9a 100644 Binary files a/master/_images/sphx_glr_05-layer-norm_001.png and b/master/_images/sphx_glr_05-layer-norm_001.png differ diff --git a/master/_images/sphx_glr_05-layer-norm_thumb.png b/master/_images/sphx_glr_05-layer-norm_thumb.png index 21da8957e..c3c08213f 100644 Binary files a/master/_images/sphx_glr_05-layer-norm_thumb.png and b/master/_images/sphx_glr_05-layer-norm_thumb.png differ diff --git a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt index 586be2644..293c82c5f 100644 --- a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -238,19 +238,19 @@ We can now run the decorated function above. Pass `print_data=True` to see the p vector-add-performance: size Triton Torch 0 4096.0 4.363636 9.600000 - 1 8192.0 9.600000 19.200000 - 2 16384.0 17.454545 38.400001 + 1 8192.0 8.727273 19.200000 + 2 16384.0 19.200000 38.400001 3 32768.0 38.400001 76.800002 - 4 65536.0 69.818181 127.999995 - 5 131072.0 127.999995 219.428568 + 4 65536.0 76.800002 127.999995 + 5 131072.0 139.636363 219.428568 6 262144.0 236.307695 341.333321 7 524288.0 341.333321 472.615390 8 1048576.0 472.615390 614.400016 9 2097152.0 614.400016 702.171410 10 4194304.0 712.347810 780.190482 - 11 8388608.0 774.047204 812.429770 - 12 16777216.0 812.429770 833.084721 - 13 33554432.0 829.569620 842.004273 + 11 8388608.0 768.000002 812.429770 + 12 16777216.0 809.086412 833.084721 + 13 33554432.0 831.323480 842.004273 14 67108864.0 840.205105 848.362445 15 134217728.0 845.625825 850.656574 @@ -260,7 +260,7 @@ 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 41.223 seconds) + **Total running time of the script:** ( 1 minutes 38.363 seconds) .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py: diff --git a/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt b/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt index 63f8cd1fe..5df543cc7 100644 --- a/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt +++ b/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt @@ -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 - 2 512.0 655.360017 585.142849 156.038096 - 3 640.0 682.666684 640.000002 160.000000 - 4 768.0 722.823517 646.736871 163.839992 + 0 256.0 512.000001 546.133347 186.181817 + 1 384.0 585.142862 585.142862 149.853661 + 2 512.0 655.360017 585.142849 154.566038 + 3 640.0 682.666684 640.000002 158.759699 + 4 768.0 722.823517 646.736871 162.754967 .. ... ... ... ... - 93 12160.0 814.058574 405.755985 199.038365 - 94 12288.0 814.111783 415.222812 199.298541 - 95 12416.0 814.163950 412.149375 198.954424 - 96 12544.0 814.214963 412.971190 199.209928 - 97 12672.0 814.265046 412.097543 199.362843 + 93 12160.0 815.765209 406.179533 198.530610 + 94 12288.0 815.800825 416.101597 198.694297 + 95 12416.0 815.835709 412.577363 198.457532 + 96 12544.0 814.214963 412.971190 198.618504 + 97 12672.0 814.265046 412.097543 198.776477 [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 27.275 seconds) + **Total running time of the script:** ( 3 minutes 24.847 seconds) .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py: diff --git a/master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt b/master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt index 1a80e831f..ada697629 100644 --- a/master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt +++ b/master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt @@ -457,38 +457,38 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we .. code-block:: none matmul-performance: - M cuBLAS ... Triton Triton (+ LeakyReLU) - 0 256.0 2.730667 ... 3.276800 2.978909 - 1 384.0 7.372800 ... 7.899428 8.507077 - 2 512.0 14.563555 ... 15.420235 16.384000 - 3 640.0 22.260869 ... 24.380953 24.380953 - 4 768.0 32.768000 ... 35.389441 34.028308 - 5 896.0 37.971025 ... 40.140799 40.140799 - 6 1024.0 49.932191 ... 53.773130 53.773130 - 7 1152.0 44.566925 ... 48.161033 47.396572 - 8 1280.0 51.200001 ... 57.690139 57.690139 - 9 1408.0 64.138541 ... 69.009825 67.305878 - 10 1536.0 79.526831 ... 79.526831 79.526831 - 11 1664.0 62.929456 ... 63.372618 62.929456 - 12 1792.0 72.983276 ... 63.142831 63.142831 - 13 1920.0 68.776119 ... 71.257735 70.892307 - 14 2048.0 73.262953 ... 78.398206 77.672296 - 15 2176.0 83.155572 ... 87.494120 86.367588 - 16 2304.0 68.251065 ... 77.810656 77.558029 - 17 2432.0 71.125224 ... 75.726318 75.320281 - 18 2560.0 77.833728 ... 82.331658 82.125311 - 19 2688.0 83.737433 ... 90.966561 89.888756 - 20 2816.0 80.767055 ... 83.712490 83.712490 - 21 2944.0 81.765436 ... 83.477440 83.899046 - 22 3072.0 81.943708 ... 89.030036 88.820552 - 23 3200.0 82.901554 ... 92.753621 88.213121 - 24 3328.0 80.798314 ... 82.369902 86.320498 - 25 3456.0 80.945348 ... 88.790274 91.200871 - 26 3584.0 87.127323 ... 100.017124 99.463928 - 27 3712.0 81.615477 ... 86.641231 88.248537 - 28 3840.0 82.778440 ... 87.148936 91.322872 - 29 3968.0 86.051653 ... 85.391135 84.270676 - 30 4096.0 91.366730 ... 84.149044 90.748973 + M cuBLAS ... Triton Triton (+ LeakyReLU) + 0 256.0 2.730667 ... 2.978909 2.978909 + 1 384.0 7.372800 ... 8.507077 8.507077 + 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 + 6 1024.0 49.932191 ... 52.428801 52.428801 + 7 1152.0 43.911529 ... 46.656000 46.656000 + 8 1280.0 49.951220 ... 56.888887 56.109587 + 9 1408.0 62.664092 ... 67.305878 67.305878 + 10 1536.0 78.643199 ... 78.643199 78.643199 + 11 1664.0 62.061463 ... 62.492442 62.061463 + 12 1792.0 71.588687 ... 62.441243 62.096267 + 13 1920.0 68.098521 ... 70.172588 69.467336 + 14 2048.0 72.005219 ... 76.608294 76.260072 + 15 2176.0 81.472263 ... 85.269692 84.909907 + 16 2304.0 67.289781 ... 76.319081 76.076024 + 17 2432.0 69.713308 ... 73.932798 73.738752 + 18 2560.0 76.204654 ... 80.709358 80.313727 + 19 2688.0 82.284288 ... 89.044730 89.464755 + 20 2816.0 80.916902 ... 82.916747 82.602666 + 21 2944.0 80.902653 ... 82.373605 82.373605 + 22 3072.0 81.005868 ... 88.060814 88.197981 + 23 3200.0 83.660130 ... 95.522391 94.814812 + 24 3328.0 82.369902 ... 84.695641 84.795401 + 25 3456.0 80.783132 ... 91.046379 91.200871 + 26 3584.0 86.291162 ... 98.591437 98.591437 + 27 3712.0 84.874549 ... 88.876645 88.876645 + 28 3840.0 83.845335 ... 92.083268 92.083268 + 29 3968.0 92.442373 ... 91.678389 91.472214 + 30 4096.0 93.206754 ... 92.627833 92.980765 [31 rows x 5 columns] @@ -498,7 +498,7 @@ 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 49.578 seconds) + **Total running time of the script:** ( 6 minutes 43.515 seconds) .. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py: diff --git a/master/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt b/master/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt index a0c991db4..4dd4cf9de 100644 --- a/master/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt +++ b/master/_sources/getting-started/tutorials/04-low-memory-dropout.rst.txt @@ -240,7 +240,7 @@ References .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 0 minutes 0.328 seconds) + **Total running time of the script:** ( 0 minutes 0.327 seconds) .. _sphx_glr_download_getting-started_tutorials_04-low-memory-dropout.py: diff --git a/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt b/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt index 95f8e2f92..c6962a519 100644 --- a/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt +++ b/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt @@ -38,36 +38,36 @@ Layer Normalization layer-norm-backward: N Triton Torch Apex - 0 1024.0 356.173905 99.497980 315.076934 - 1 1536.0 405.098894 134.050910 344.523365 - 2 2048.0 491.520012 159.584422 321.254900 - 3 2560.0 458.507457 182.857144 326.808501 - 4 3072.0 519.211251 191.501303 319.168834 - 5 3584.0 551.384634 207.768111 307.199992 - 6 4096.0 564.965515 220.907859 293.444785 - 7 4608.0 502.690905 232.336141 290.267724 - 8 5120.0 527.381977 243.809526 287.102804 - 9 5632.0 540.671974 244.426754 291.310338 - 10 6144.0 548.163546 251.202731 288.000001 - 11 6656.0 532.479975 255.590406 286.279570 - 12 7168.0 510.480705 253.734520 277.919225 - 13 7680.0 487.619051 266.743841 284.884090 - 14 8192.0 468.114289 258.694729 278.481578 - 15 8704.0 415.300208 267.472468 284.987724 - 16 9216.0 429.483477 272.394084 290.267724 - 17 9728.0 438.033784 279.942444 288.950501 - 18 10240.0 444.412281 287.102804 289.811322 - 19 10752.0 426.525614 246.699797 290.267711 - 20 11264.0 426.397479 245.536784 286.372873 - 21 11776.0 419.323436 249.447482 288.981596 - 22 12288.0 414.784810 254.673582 294.323369 - 23 12800.0 410.146863 254.094291 288.180121 - 24 13312.0 410.125805 252.161013 289.391298 - 25 13824.0 404.112047 257.190689 291.799461 - 26 14336.0 395.475867 256.000002 288.644296 - 27 14848.0 386.080180 257.665934 288.544136 - 28 15360.0 380.433442 258.513318 286.433562 - 29 15872.0 372.363640 261.806182 290.562936 + 0 1024.0 351.085705 98.698793 311.088617 + 1 1536.0 396.387087 132.604320 341.333333 + 2 2048.0 481.882362 158.045011 321.254900 + 3 2560.0 451.764698 181.238943 325.079368 + 4 3072.0 508.468972 190.511624 317.793096 + 5 3584.0 547.872604 206.769233 308.301075 + 6 4096.0 564.965515 219.919464 300.623865 + 7 4608.0 493.714279 231.364016 285.767436 + 8 5120.0 518.481012 242.366855 285.767451 + 9 5632.0 532.157453 243.545956 291.310338 + 10 6144.0 544.118087 249.925419 286.322318 + 11 6656.0 530.710976 254.775119 286.279570 + 12 7168.0 510.480705 252.616738 277.024148 + 13 7680.0 486.332448 265.590783 284.006166 + 14 8192.0 467.002371 257.677592 277.303250 + 15 8704.0 405.623284 266.789264 284.212242 + 16 9216.0 420.501910 271.391419 289.129410 + 17 9728.0 428.388977 279.272720 287.881626 + 18 10240.0 434.973455 286.100109 289.129408 + 19 10752.0 421.647056 245.760009 289.291486 + 20 11264.0 423.724120 244.647957 285.465683 + 21 11776.0 416.849568 248.788725 288.097854 + 22 12288.0 413.042003 253.578674 293.444785 + 23 12800.0 408.510626 253.256381 287.371378 + 24 13312.0 408.552421 251.565353 288.607034 + 25 13824.0 403.130022 256.197690 291.031592 + 26 14336.0 395.930964 255.051144 287.919661 + 27 14848.0 385.245405 256.737757 287.844912 + 28 15360.0 380.041240 257.610071 285.546077 + 29 15872.0 372.545726 260.731015 289.679087 @@ -339,7 +339,7 @@ Layer Normalization .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 2 minutes 14.213 seconds) + **Total running time of the script:** ( 2 minutes 15.333 seconds) .. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py: diff --git a/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt b/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt index 23a00e696..0b07ec9de 100644 --- a/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt +++ b/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt @@ -5,16 +5,16 @@ Computation times ================= -**14:12.617** total execution time for **getting-started_tutorials** files: +**14:02.386** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:49.578 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:43.515 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:27.275 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:24.847 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:14.213 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:15.333 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:41.223 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:38.363 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.328 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.327 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/master/getting-started/tutorials/01-vector-add.html b/master/getting-started/tutorials/01-vector-add.html index bab4892e6..dad802210 100644 --- a/master/getting-started/tutorials/01-vector-add.html +++ b/master/getting-started/tutorials/01-vector-add.html @@ -328,24 +328,24 @@ for different problem sizes.

vector-add-performance:
            size      Triton       Torch
 0        4096.0    4.363636    9.600000
-1        8192.0    9.600000   19.200000
-2       16384.0   17.454545   38.400001
+1        8192.0    8.727273   19.200000
+2       16384.0   19.200000   38.400001
 3       32768.0   38.400001   76.800002
-4       65536.0   69.818181  127.999995
-5      131072.0  127.999995  219.428568
+4       65536.0   76.800002  127.999995
+5      131072.0  139.636363  219.428568
 6      262144.0  236.307695  341.333321
 7      524288.0  341.333321  472.615390
 8     1048576.0  472.615390  614.400016
 9     2097152.0  614.400016  702.171410
 10    4194304.0  712.347810  780.190482
-11    8388608.0  774.047204  812.429770
-12   16777216.0  812.429770  833.084721
-13   33554432.0  829.569620  842.004273
+11    8388608.0  768.000002  812.429770
+12   16777216.0  809.086412  833.084721
+13   33554432.0  831.323480  842.004273
 14   67108864.0  840.205105  848.362445
 15  134217728.0  845.625825  850.656574
-

Total running time of the script: ( 1 minutes 41.223 seconds)

+

Total running time of the script: ( 1 minutes 38.363 seconds)