diff --git a/master/.buildinfo b/master/.buildinfo index bb983f3e0..64dc426d9 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: 2733d834a878ced23a6c2f6f4c64be8c +config: 29a6392189b919d314768a8cb78a5eab tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/master/.doctrees/environment.pickle b/master/.doctrees/environment.pickle index dac8cf048..852a194e2 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 41aa54b74..274055c9b 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 5a6b8b456..0e773cc17 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 0af926751..2dd5f5ee3 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 a077a3001..e10b8ad9f 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 c94fd543d..9661ce0ff 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 c0d02075e..7c4d5ebef 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 8a6991250..60cfda12c 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 547b2d91e..d10eb4b35 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 2a0472082..09afbce0a 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 d249afb2d..80450577e 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 c68d75561..4b08a31e9 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 d896ae14d..d1a286e7f 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 fd3c3dd03..cea07328f 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 d97645da4..367ac0e35 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 85258c9de..36e55d4ed 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 daf87090b..630aa67a9 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 ab1f24e62..1c035d663 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 f314bae7e..5493d105a 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 d3d777caf..eb28751e5 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 117b8411a..89225099e 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 98608d9b4..cd4c0ad88 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 f8782ca06..76293ec5f 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 cd54322d1..5e1558eb2 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 d4da0d4ae..2da90a6dd 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 8fcae659c..3aaa48adf 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 b5f583eb7..1e6b05d7b 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 ae78fb921..bd29bd539 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 f5de0308a..a91558835 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 4e445da52..a9645824b 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 a432bb195..0f044e916 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 0de00cc66..3e0188f19 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 48f0ebdca..9ad9b44c4 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 b1da736f5..6644c7742 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 b1c66a18f..bf30ce67a 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 9e12cf4d9..946a0f177 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 564bfce99..0f7e5f95e 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 2620c6cd9..5fc876148 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 216e2d1e0..c208908ce 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 75635182a..465bb35ec 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 1aebe10e3..5579f869f 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 b54ff9e03..c59d3bcd6 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 f36303c6b..d4b885b8d 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 b3b5688b8..eb2b73ddd 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 0b1d371fb..a020205f3 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 9ba9760a6..a876c7651 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 4b49121a9..d63942976 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 a6cb7300b..5db4e9bf0 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 806fb749d..bc27112dd 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 8530039e9..3d7b9e58a 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 a9241ca1a..ca5c61d6b 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 020c09f68..d21e1ea19 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 1f1d74581..accc0082c 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 d4418bc13..3abd27b73 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 d89b874e7..9594bef18 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 e5a62c7fe..cfea68960 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 397d6dce4..9731194a9 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 94847c78d..1f6c3ce5e 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 97d8e9200..184787c44 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 760d48fa0..7148128ff 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 4aa3b4efc..22ccdb470 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 8f05cf014..e732f4dc4 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 b2f5e438c..3233744b7 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 1e5edfc65..8f14dd7b1 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 cb32e9e97..a5a1b0d2c 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 9f99813c4..680089380 100644 --- a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -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 31.999999 31.999999 + 2 16384.0 38.400001 38.400001 3 32768.0 76.800002 76.800002 4 65536.0 127.999995 127.999995 5 131072.0 219.428568 219.428568 @@ -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 40.152 seconds) + **Total running time of the script:** ( 1 minutes 40.796 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 2de565e14..01a38a639 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 186.181817 - 1 384.0 585.142862 558.545450 151.703707 + 0 256.0 512.000001 512.000001 186.181817 + 1 384.0 585.142862 585.142862 151.703707 2 512.0 655.360017 606.814814 154.566038 - 3 640.0 682.666684 640.000002 158.759699 - 4 768.0 722.823517 664.216187 163.839992 + 3 640.0 682.666684 640.000002 160.000000 + 4 768.0 722.823517 664.216187 162.754967 .. ... ... ... ... - 93 12160.0 814.058574 405.755985 198.631953 - 94 12288.0 814.111783 415.661740 198.895304 - 95 12416.0 814.163950 412.149375 198.556711 - 96 12544.0 814.214963 412.971190 198.716830 - 97 12672.0 814.265046 411.679167 198.873965 + 93 12160.0 814.058574 405.755985 198.834951 + 94 12288.0 814.111783 415.222812 199.096718 + 95 12416.0 814.163950 411.722274 198.854847 + 96 12544.0 814.214963 412.546756 198.913776 + 97 12672.0 814.265046 411.679167 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 27.921 seconds) + **Total running time of the script:** ( 3 minutes 19.085 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 746c93ddb..7af0fab56 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 2.978909 ... 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 ... 41.321411 39.025776 - 6 1024.0 49.932191 ... 53.773130 53.773130 - 7 1152.0 45.242181 ... 48.161033 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 ... 80.430545 80.430545 - 11 1664.0 63.372618 ... 63.372618 62.929456 - 12 1792.0 72.983276 ... 63.499573 63.142831 - 13 1920.0 68.776119 ... 71.257735 70.892307 - 14 2048.0 73.584279 ... 78.398206 78.033565 - 15 2176.0 83.155572 ... 87.115360 86.739860 - 16 2304.0 68.251065 ... 78.064941 77.558029 - 17 2432.0 71.305746 ... 75.726318 75.522751 - 18 2560.0 77.833728 ... 82.539044 82.331658 - 19 2688.0 84.108772 ... 91.185232 90.966561 - 20 2816.0 80.469019 ... 83.552120 84.523664 - 21 2944.0 81.832567 ... 84.324925 83.758038 - 22 3072.0 81.589488 ... 87.246694 89.451983 - 23 3200.0 85.106381 ... 96.385543 95.952022 - 24 3328.0 83.905938 ... 85.908470 86.113988 - 25 3456.0 82.604067 ... 85.043848 89.480098 - 26 3584.0 84.111686 ... 92.410473 94.747514 - 27 3712.0 85.675250 ... 85.896254 88.404730 - 28 3840.0 81.138664 ... 88.261772 91.701494 - 29 3968.0 87.976885 ... 92.477403 85.811488 - 30 4096.0 93.401342 ... 84.733417 86.872315 + M cuBLAS ... Triton Triton (+ LeakyReLU) + 0 256.0 2.730667 ... 3.276800 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 32.768000 ... 34.028308 34.028308 + 5 896.0 37.971025 ... 41.321411 40.140799 + 6 1024.0 49.932191 ... 53.773130 52.428801 + 7 1152.0 45.242181 ... 48.161033 47.396572 + 8 1280.0 51.200001 ... 57.690139 57.690139 + 9 1408.0 64.138541 ... 68.147202 68.147202 + 10 1536.0 80.430545 ... 80.430545 80.430545 + 11 1664.0 62.929456 ... 63.372618 62.929456 + 12 1792.0 72.983276 ... 63.499573 63.142831 + 13 1920.0 68.776119 ... 70.892307 70.892307 + 14 2048.0 73.584279 ... 78.398206 78.033565 + 15 2176.0 83.155572 ... 87.115360 86.739860 + 16 2304.0 68.251065 ... 77.810656 77.558029 + 17 2432.0 71.305746 ... 75.726318 75.522751 + 18 2560.0 77.833728 ... 81.715711 81.920002 + 19 2688.0 83.737433 ... 90.966561 90.316801 + 20 2816.0 84.035084 ... 83.552120 83.873477 + 21 2944.0 82.509987 ... 83.899046 84.040530 + 22 3072.0 81.589488 ... 86.184329 89.735509 + 23 3200.0 84.993363 ... 96.240602 96.240602 + 24 3328.0 83.226931 ... 85.806075 84.895397 + 25 3456.0 82.604067 ... 84.068369 88.692595 + 26 3584.0 87.211821 ... 100.017124 100.351999 + 27 3712.0 85.091436 ... 89.513749 87.094458 + 28 3840.0 84.228485 ... 92.390975 85.531326 + 29 3968.0 91.954739 ... 85.034103 91.540836 + 30 4096.0 87.495257 ... 89.597949 93.336389 [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 55.944 seconds) + **Total running time of the script:** ( 6 minutes 7.559 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 96ca34cf2..d1778b13a 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 0.323 seconds) + **Total running time of the script:** ( 0 minutes 0.012 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 9369c9baf..98ad217ff 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 97.912354 303.407414 - 1 1536.0 405.098894 134.540150 341.333333 - 2 2048.0 496.484863 161.154101 323.368435 - 3 2560.0 465.454542 181.238943 326.808501 - 4 3072.0 519.211251 192.501302 321.956335 - 5 3584.0 558.545477 208.271186 311.652167 - 6 4096.0 561.737163 220.907859 297.890900 - 7 4608.0 502.690905 232.825259 287.251954 - 8 5120.0 525.128191 242.366855 287.102804 - 9 5632.0 540.671974 243.107920 289.438969 - 10 6144.0 546.133354 248.661056 286.879370 - 11 6656.0 527.207907 256.000009 285.257135 - 12 7168.0 503.017523 260.260201 284.821192 - 13 7680.0 483.779539 262.938666 280.121579 - 14 8192.0 463.698115 266.406514 284.526763 - 15 8704.0 414.476194 267.472468 284.987724 - 16 9216.0 428.651187 271.724806 287.999990 - 17 9728.0 436.396262 280.278512 290.027323 - 18 10240.0 446.025405 286.433562 290.153487 - 19 10752.0 428.651173 246.935876 290.267711 - 20 11264.0 426.397479 245.536784 286.980888 - 21 11776.0 421.198220 249.888595 288.981596 - 22 12288.0 416.542386 254.673582 294.617366 - 23 12800.0 410.695192 254.094291 288.180121 - 24 13312.0 409.075539 253.360814 290.443638 - 25 13824.0 405.098897 257.390218 292.056329 - 26 14336.0 394.116833 254.862216 286.959121 - 27 14848.0 385.662341 257.852379 289.952797 - 28 15360.0 380.433442 257.970599 286.433562 - 29 15872.0 370.552519 261.626369 290.341468 + 0 1024.0 361.411758 99.902435 315.076934 + 1 1536.0 405.098894 133.083026 344.523365 + 2 2048.0 496.484863 158.554837 334.367350 + 3 2560.0 461.954908 182.857144 330.322572 + 4 3072.0 519.211251 191.501303 320.556515 + 5 3584.0 554.941930 208.271186 309.410081 + 6 4096.0 564.965515 220.412561 298.796351 + 7 4608.0 502.690905 231.849059 286.507772 + 8 5120.0 527.381977 244.294240 286.433562 + 9 5632.0 542.843364 244.426754 292.571431 + 10 6144.0 550.208948 251.202731 288.000001 + 11 6656.0 534.260858 256.000009 286.793541 + 12 7168.0 513.528374 253.734520 277.470965 + 13 7680.0 488.912481 266.743841 284.884090 + 14 8192.0 468.114289 258.694729 278.087683 + 15 8704.0 415.300208 267.472468 286.158893 + 16 9216.0 429.483477 273.066667 289.129410 + 17 9728.0 438.857162 279.942444 289.308559 + 18 10240.0 444.412281 287.102804 290.153487 + 19 10752.0 427.940303 246.935876 290.104546 + 20 11264.0 429.104745 246.432094 287.897767 + 21 11776.0 421.198220 249.888595 289.573776 + 22 12288.0 417.131525 254.673582 294.323369 + 23 12800.0 411.244989 253.884294 290.084977 + 24 13312.0 409.599999 252.959629 289.391298 + 25 13824.0 405.594132 256.991469 292.056329 + 26 14336.0 395.475867 255.619613 288.402346 + 27 14848.0 385.245405 256.922861 288.544136 + 28 15360.0 380.041240 258.332158 288.450715 + 29 15872.0 372.000001 263.071829 290.341468 @@ -339,7 +339,7 @@ Layer Normalization .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 2 minutes 14.484 seconds) + **Total running time of the script:** ( 2 minutes 13.781 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 69e3eba2a..895c68fba 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 ================= -**14:18.825** total execution time for **getting-started_tutorials** files: +**13:21.234** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:55.944 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:07.559 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:27.921 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:19.085 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:14.484 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:13.781 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:40.152 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:40.796 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.323 | 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 | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/master/getting-started/tutorials/01-vector-add.html b/master/getting-started/tutorials/01-vector-add.html index 3b902a8fc..f49d233b2 100644 --- a/master/getting-started/tutorials/01-vector-add.html +++ b/master/getting-started/tutorials/01-vector-add.html @@ -324,7 +324,7 @@ for different problem sizes.

size Triton Torch 0 4096.0 9.600000 9.600000 1 8192.0 19.200000 19.200000 -2 16384.0 31.999999 31.999999 +2 16384.0 38.400001 38.400001 3 32768.0 76.800002 76.800002 4 65536.0 127.999995 127.999995 5 131072.0 219.428568 219.428568 @@ -340,7 +340,7 @@ for different problem sizes.

15 134217728.0 849.737435 850.656574 -

Total running time of the script: ( 1 minutes 40.152 seconds)

+

Total running time of the script: ( 1 minutes 40.796 seconds)