diff --git a/master/.buildinfo b/master/.buildinfo index 9fe9f53bd..dcc24689c 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: 339ccb5e1779e5292300a49b5d2513b2 +config: 8854530bca5900a6d2403fdb7d46c23c tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/master/.doctrees/environment.pickle b/master/.doctrees/environment.pickle index cdd05ead1..aea72a91d 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 b8d3dd926..852b51477 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 68f1ecc50..9d3295cd4 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 2ab4fd831..6ed43cac0 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 6a91d7a39..736fca78d 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 a6264ce85..35cfe877d 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 edfc1720a..7c35cca34 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 de0c89663..afb80799f 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 7e45341cd..9b3fe3055 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 ee27e53e7..4a66d1bbb 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 e555c284b..ba71edc13 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 7acb7b502..c59e9fe55 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 95b96ec40..cbed8b686 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 5ad33641d..5eb2f91f3 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 f10ef0ba1..421c72b07 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 7425f5979..48b58ff7a 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 4cc9fb840..a5b6a44da 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 e3d792ddf..8823cb533 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 a1e11f586..32838c5d7 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 178f69459..56c878fd6 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 91474b8dd..903a589cf 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 4aa0e0fad..59cda0453 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 67c450ba8..7e7f45e40 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 c720de0ef..8b50e56cd 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 f966a07eb..5fc3a7da1 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 8f85e1b8f..74e859cd9 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 06f95baad..4c1e57ab5 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 44cdf8f1b..f1ab35f3b 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 aa1045879..911181df7 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 6eb191a2b..6dee585f6 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 dcdd7dd41..f91e5a6f4 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 32a3e2bf6..02f7d172a 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 5616b3288..d87635730 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 aa4f19853..a61e041e7 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 9c6e3bed7..50b77c176 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 4b9827471..153a36679 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 82fd2a4fa..3472c8854 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 979a92ffa..ad3166c64 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 60dc57214..fe705cce7 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 817c6867b..c3660165d 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 e76be52be..e342a5c49 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 ba6674316..a807c20dc 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 9682324ae..7a1dc0326 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 86faa5735..60d28434f 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 fea8cceb2..d2b931076 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 408d5b8c8..95d0fb565 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 a6f5058ae..f3780c04a 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 f11edc700..9e2d22f31 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 d38d504bb..8b20630e4 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 29f19937e..5b8e1ba04 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 92b0698c8..d4c1001f4 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 cf330a0d1..c0354b15f 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 2618bb142..05fa55071 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 66e5f586e..87dc9d842 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 7eeb51b3d..c4723486a 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 f0f143bf6..bf5ca5cba 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 08b23cd44..908d2c732 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 ac603e0df..a7d7e71a5 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 1b727f524..28de8dbf5 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 87dd5a8d2..492b772cb 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 8e4202cd7..a5deba40b 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 e9c55f6d3..18ababcfb 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 e92b2c10f..759364e24 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 06a8434d8..d29b48bae 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 b9b382252..21da8957e 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 1c58c0773..586be2644 100644 --- a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -237,21 +237,21 @@ 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 4.800000 9.600000 - 1 8192.0 10.666666 19.200000 + 0 4096.0 4.363636 9.600000 + 1 8192.0 9.600000 19.200000 2 16384.0 17.454545 38.400001 - 3 32768.0 38.400001 63.999998 + 3 32768.0 38.400001 76.800002 4 65536.0 69.818181 127.999995 5 131072.0 127.999995 219.428568 - 6 262144.0 219.428568 384.000001 + 6 262144.0 236.307695 341.333321 7 524288.0 341.333321 472.615390 8 1048576.0 472.615390 614.400016 - 9 2097152.0 599.414644 702.171410 + 9 2097152.0 614.400016 702.171410 10 4194304.0 712.347810 780.190482 11 8388608.0 774.047204 812.429770 - 12 16777216.0 809.086412 833.084721 - 13 33554432.0 831.323480 842.004273 - 14 67108864.0 841.103727 848.362445 + 12 16777216.0 812.429770 833.084721 + 13 33554432.0 829.569620 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 38.714 seconds) + **Total running time of the script:** ( 1 minutes 41.223 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 1eb644167..63f8cd1fe 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) - 0 256.0 546.133347 546.133347 192.752942 + 0 256.0 512.000001 546.133347 188.321838 1 384.0 585.142862 585.142862 151.703707 - 2 512.0 655.360017 606.814814 156.038096 + 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 .. ... ... ... ... - 93 12160.0 814.058574 405.755985 198.834951 - 94 12288.0 815.800825 415.661740 199.096718 - 95 12416.0 814.163950 412.149375 198.705656 - 96 12544.0 814.214963 412.971190 198.913776 - 97 12672.0 814.265046 412.097543 199.069228 + 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 [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 26.814 seconds) + **Total running time of the script:** ( 3 minutes 27.275 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 d01b78c47..1a80e831f 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 7.899428 - 2 512.0 14.563555 ... 16.384000 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 45.242181 ... 48.161033 47.396572 - 8 1280.0 51.200001 ... 58.514284 57.690139 - 9 1408.0 64.138541 ... 69.009825 68.147202 - 10 1536.0 79.526831 ... 80.430545 80.430545 - 11 1664.0 63.372618 ... 63.372618 62.929456 - 12 1792.0 72.983276 ... 63.142831 62.790080 - 13 1920.0 68.776119 ... 71.257735 71.257735 - 14 2048.0 73.584279 ... 78.033565 77.672296 - 15 2176.0 83.155572 ... 87.115360 86.739860 - 16 2304.0 68.446623 ... 77.810656 77.558029 - 17 2432.0 71.125224 ... 75.522751 75.118889 - 18 2560.0 77.833728 ... 82.125311 81.715711 - 19 2688.0 83.552988 ... 90.316801 89.888756 - 20 2816.0 80.173175 ... 83.873477 83.392363 - 21 2944.0 81.034195 ... 84.040530 82.237674 - 22 3072.0 82.301023 ... 89.310890 89.030036 - 23 3200.0 82.156612 ... 96.385543 96.822991 - 24 3328.0 83.516586 ... 85.500351 85.703924 - 25 3456.0 81.683457 ... 86.226274 86.783176 - 26 3584.0 87.211821 ... 98.808123 99.408944 - 27 3712.0 84.159518 ... 86.641231 88.248537 - 28 3840.0 79.391241 ... 85.136259 91.247522 - 29 3968.0 87.097744 ... 91.472214 84.797731 - 30 4096.0 93.401342 ... 84.096318 86.092193 + 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 [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 4.871 seconds) + **Total running time of the script:** ( 6 minutes 49.578 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 ecccf6a53..a0c991db4 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 0.016 seconds) + **Total running time of the script:** ( 0 minutes 0.328 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 8a6d50f27..95f8e2f92 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 1024.0 361.411758 99.902435 315.076934 - 1 1536.0 405.098894 134.540150 344.523365 - 2 2048.0 491.520012 159.584422 323.368435 - 3 2560.0 458.507457 182.857144 325.079368 - 4 3072.0 519.211251 191.999993 320.556515 - 5 3584.0 554.941930 208.271186 310.527060 - 6 4096.0 568.231237 221.405403 301.546004 - 7 4608.0 502.690905 232.336141 287.251954 - 8 5120.0 527.381977 243.809526 286.433562 - 9 5632.0 542.843364 244.647957 291.939522 - 10 6144.0 550.208948 251.202731 287.438593 - 11 6656.0 532.479975 255.590406 286.793541 - 12 7168.0 510.480705 253.734520 277.470965 - 13 7680.0 487.619051 266.358392 284.884090 - 14 8192.0 468.114289 258.354805 278.481578 - 15 8704.0 415.300208 267.815384 285.377055 - 16 9216.0 431.157889 272.394084 289.887291 - 17 9728.0 438.033784 280.278512 289.308559 - 18 10240.0 442.810829 287.438599 290.496460 - 19 10752.0 426.525614 246.935876 289.941565 - 20 11264.0 427.071098 245.536784 286.069848 - 21 11776.0 419.323436 249.447482 288.686414 - 22 12288.0 415.954875 254.893699 294.617366 - 23 12800.0 411.244989 254.094291 289.538159 - 24 13312.0 410.652963 252.559690 289.391298 - 25 13824.0 404.604870 257.190689 292.056329 - 26 14336.0 396.387109 256.190622 289.129416 - 27 14848.0 386.080180 257.665934 288.777966 - 28 15360.0 379.649845 258.513318 286.656296 - 29 15872.0 372.000001 261.806182 290.341468 + 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 @@ -339,7 +339,7 @@ Layer Normalization .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 2 minutes 12.229 seconds) + **Total running time of the script:** ( 2 minutes 14.213 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 2ce31744f..23a00e696 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 ================= -**13:22.644** total execution time for **getting-started_tutorials** files: +**14:12.617** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:04.871 | 0.0 MB | +| :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_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:26.814 | 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_05-layer-norm.py` (``05-layer-norm.py``) | 02:12.229 | 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_01-vector-add.py` (``01-vector-add.py``) | 01:38.714 | 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_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.016 | 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 | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/master/getting-started/tutorials/01-vector-add.html b/master/getting-started/tutorials/01-vector-add.html index 3fa7cdd1d..bab4892e6 100644 --- a/master/getting-started/tutorials/01-vector-add.html +++ b/master/getting-started/tutorials/01-vector-add.html @@ -327,25 +327,25 @@ for different problem sizes.

Out:

vector-add-performance:
            size      Triton       Torch
-0        4096.0    4.800000    9.600000
-1        8192.0   10.666666   19.200000
+0        4096.0    4.363636    9.600000
+1        8192.0    9.600000   19.200000
 2       16384.0   17.454545   38.400001
-3       32768.0   38.400001   63.999998
+3       32768.0   38.400001   76.800002
 4       65536.0   69.818181  127.999995
 5      131072.0  127.999995  219.428568
-6      262144.0  219.428568  384.000001
+6      262144.0  236.307695  341.333321
 7      524288.0  341.333321  472.615390
 8     1048576.0  472.615390  614.400016
-9     2097152.0  599.414644  702.171410
+9     2097152.0  614.400016  702.171410
 10    4194304.0  712.347810  780.190482
 11    8388608.0  774.047204  812.429770
-12   16777216.0  809.086412  833.084721
-13   33554432.0  831.323480  842.004273
-14   67108864.0  841.103727  848.362445
+12   16777216.0  812.429770  833.084721
+13   33554432.0  829.569620  842.004273
+14   67108864.0  840.205105  848.362445
 15  134217728.0  845.625825  850.656574
-

Total running time of the script: ( 1 minutes 38.714 seconds)

+

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