diff --git a/master/.buildinfo b/master/.buildinfo index c479d8e8e..98840ce8d 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: 4a57db4e5b36e9c2997013e2fd53e962 +config: 425a19caee966fd0c51df8134917a3e4 tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/master/.doctrees/environment.pickle b/master/.doctrees/environment.pickle index 03db45c4a..9678a64fa 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 811d41183..46fec9a51 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 cb430f903..e67efa910 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 c61c46856..7db584650 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 aecf9b653..976d92637 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 23dd85ab9..b97769018 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 f02a8ee1b..c4ccdbd58 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/06-fused-attention.doctree b/master/.doctrees/getting-started/tutorials/06-fused-attention.doctree index 92853194d..104dc62e7 100644 Binary files a/master/.doctrees/getting-started/tutorials/06-fused-attention.doctree and b/master/.doctrees/getting-started/tutorials/06-fused-attention.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/07-libdevice-function.doctree b/master/.doctrees/getting-started/tutorials/07-libdevice-function.doctree index ca7e3136d..6a7f99a7c 100644 Binary files a/master/.doctrees/getting-started/tutorials/07-libdevice-function.doctree and b/master/.doctrees/getting-started/tutorials/07-libdevice-function.doctree differ diff --git a/master/.doctrees/getting-started/tutorials/index.doctree b/master/.doctrees/getting-started/tutorials/index.doctree index 854223af1..994d056ee 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 3326187a1..5bb350994 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 728e46098..451dc5611 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 799804886..ffb513516 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 72e4eb96d..f5691178a 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 5d0517443..6935a4871 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 9fe2772e6..b489a295a 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 0597aeade..b90c50ada 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 13458cb7d..ba6d3b5f8 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 c3a36bc59..faf367350 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 20202e0dc..d1d25fd12 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_and.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_and.doctree index 519bb6f83..cabbdeecc 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_and.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_and.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 cb1fea995..56935b61f 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 8e57b2795..0a715f758 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 b2e571e2f..79683b5d1 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_or.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_or.doctree index 2e19d3c74..a61f5f15b 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_or.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_or.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 c0b47384d..14f4a0678 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.atomic_xor.doctree b/master/.doctrees/python-api/generated/triton.language.atomic_xor.doctree index 91f82e7bf..01e971e31 100644 Binary files a/master/.doctrees/python-api/generated/triton.language.atomic_xor.doctree and b/master/.doctrees/python-api/generated/triton.language.atomic_xor.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 28449b4c2..7877db32f 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 5382c67db..76fc75432 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 e56722bd4..562e2ca63 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 712e09346..47098d09c 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 f1124f6b6..2ef77945c 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 cda7145f2..ce72fbf9c 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 f2b7ba97f..da918afcf 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 54fc9d62f..1f96ecded 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 8dcbcd5ed..0aef405db 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 3047efa7a..ee4618eb2 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 871732098..9151a6538 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 ae096cbbc..de3eaffb8 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 fea15c59e..01ea31963 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 f5cf111b1..4afb14e75 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 52851d40e..530bb655e 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 9887ac481..f2d6003da 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 e15efa5a8..480be8e57 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 4cbfe57b0..dafe2545d 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 ba09fda23..26143b3f9 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 2e20b06ed..c86d0e32e 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 2117725b6..ce6a0c41e 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 0b1de387b..4c5d6b5fe 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 698ca3890..898242456 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 9678a2765..e455a1bf9 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 29fc1e1f3..a60921fd0 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 9f51fb2b3..f2a6e7c65 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 29ac090cf..d7bdd20d0 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 975ae94c6..900dfc9a0 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 86dd8d89a..23b9c986d 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 6574f4065..2a00fac9c 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 bc59e5383..cbf799458 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 de66e9061..14b3c5ff6 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 315595e25..a5f80dee2 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 fe39d4bde..45a6c1789 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 95645eac3..d5d216864 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 8a5ae6f47..0bb48a080 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 c007f8d58..6b6ec14fb 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 9b3d950c8..3fc0df325 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 9ab66e0cc..d0cfaf59d 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 8667d45b4..b5bd8e924 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 b2b55cf10..5b53f105e 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 504ea6dfc..b485b921e 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 10474b987..bbeed02d0 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 ff375cdeb..33f55ac1d 100644 --- a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -233,19 +233,19 @@ 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 9.600000 9.600000 - 1 8192.0 19.200000 15.999999 + 1 8192.0 19.200000 19.200000 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 - 6 262144.0 384.000001 384.000001 + 6 262144.0 341.333321 384.000001 7 524288.0 472.615390 472.615390 8 1048576.0 614.400016 614.400016 9 2097152.0 722.823517 722.823517 10 4194304.0 780.190482 780.190482 11 8388608.0 812.429770 812.429770 12 16777216.0 833.084721 833.084721 - 13 33554432.0 842.004273 842.004273 + 13 33554432.0 842.004273 843.811163 14 67108864.0 847.448255 848.362445 15 134217728.0 849.737435 850.656574 @@ -255,7 +255,7 @@ We can now run the decorated function above. Pass `print_data=True` to see the p .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 1 minutes 41.831 seconds) + **Total running time of the script:** ( 1 minutes 48.722 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 75ab495ca..b860ed557 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 190.511628 - 1 384.0 614.400016 585.142862 151.703707 - 2 512.0 655.360017 606.814814 156.038096 + 0 256.0 512.000001 546.133347 186.181817 + 1 384.0 614.400016 585.142862 153.600004 + 2 512.0 655.360017 585.142849 154.566038 3 640.0 706.206879 640.000002 160.000000 4 768.0 722.823517 664.216187 163.839992 .. ... ... ... ... - 93 12160.0 812.359066 405.333344 199.038365 - 94 12288.0 812.429770 415.222812 199.197579 - 95 12416.0 812.498981 411.296057 198.805107 - 96 12544.0 811.745227 412.971190 199.012395 - 97 12672.0 811.007961 412.097543 199.167004 + 93 12160.0 812.359066 405.755985 198.936606 + 94 12288.0 812.429770 415.661740 199.197579 + 95 12416.0 812.498981 411.722274 198.755369 + 96 12544.0 810.925276 412.971190 199.012395 + 97 12672.0 811.007961 412.097543 199.069228 [98 rows x 4 columns] @@ -306,7 +306,7 @@ In the above plot, we can see that: .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 3 minutes 28.967 seconds) + **Total running time of the script:** ( 3 minutes 32.036 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 dfa507b50..e3dd39cb7 100644 --- a/master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt +++ b/master/_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt @@ -459,37 +459,37 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we matmul-performance: M cuBLAS ... Triton Triton (+ LeakyReLU) - 0 256.0 2.978909 ... 3.276800 3.276800 + 0 256.0 2.730667 ... 2.978909 3.276800 1 384.0 7.372800 ... 8.507077 8.507077 - 2 512.0 14.563555 ... 16.384000 16.384000 + 2 512.0 14.563555 ... 16.384000 15.420235 3 640.0 22.260869 ... 24.380953 24.380953 4 768.0 32.768000 ... 35.389441 34.028308 - 5 896.0 39.025776 ... 40.140799 39.025776 - 6 1024.0 49.932191 ... 53.773130 52.428801 + 5 896.0 37.971025 ... 40.140799 39.025776 + 6 1024.0 49.932191 ... 53.773130 53.092457 7 1152.0 45.242181 ... 48.161033 48.161033 8 1280.0 51.200001 ... 57.690139 57.690139 - 9 1408.0 64.138541 ... 69.009825 68.147202 + 9 1408.0 64.138541 ... 69.009825 67.305878 10 1536.0 80.430545 ... 81.355034 79.526831 - 11 1664.0 63.372618 ... 63.372618 62.492442 - 12 1792.0 72.983276 ... 73.460287 59.467852 + 11 1664.0 62.929456 ... 63.372618 62.492442 + 12 1792.0 72.512412 ... 73.460287 59.467852 13 1920.0 69.120002 ... 71.626943 71.257735 14 2048.0 73.908442 ... 78.398206 77.314362 - 15 2176.0 83.500614 ... 87.876193 86.367588 + 15 2176.0 83.500614 ... 87.876193 85.998493 16 2304.0 68.446623 ... 78.064941 77.057651 - 17 2432.0 71.305746 ... 85.915795 83.366361 - 18 2560.0 77.833728 ... 81.715711 81.310171 - 19 2688.0 83.369354 ... 90.532356 90.102270 - 20 2816.0 81.445766 ... 84.035084 83.873477 - 21 2944.0 81.564701 ... 83.477440 82.921853 - 22 3072.0 82.420822 ... 89.735509 88.750943 - 23 3200.0 84.544253 ... 97.116842 95.096582 - 24 3328.0 83.905938 ... 85.806075 83.808259 - 25 3456.0 82.773682 ... 90.180725 90.687926 - 26 3584.0 87.042978 ... 99.244365 98.268190 - 27 3712.0 81.482335 ... 88.718781 88.248537 - 28 3840.0 82.531346 ... 89.043476 89.912191 - 29 3968.0 86.911637 ... 92.652949 84.094627 - 30 4096.0 93.368854 ... 83.313299 89.928129 + 17 2432.0 71.305746 ... 85.393507 75.522751 + 18 2560.0 77.833728 ... 82.125311 80.908642 + 19 2688.0 83.922689 ... 90.966561 89.464755 + 20 2816.0 81.067298 ... 84.360174 83.873477 + 21 2944.0 81.967162 ... 83.337844 81.832567 + 22 3072.0 82.420822 ... 89.310890 88.473602 + 23 3200.0 83.879425 ... 95.238096 87.671229 + 24 3328.0 82.369902 ... 85.602017 81.994643 + 25 3456.0 80.864158 ... 84.332184 90.281712 + 26 3584.0 87.127323 ... 97.947050 97.205829 + 27 3712.0 84.159518 ... 89.035062 87.552452 + 28 3840.0 81.138664 ... 86.332554 90.279183 + 29 3968.0 87.913500 ... 91.954739 86.358055 + 30 4096.0 93.271527 ... 84.254693 82.418802 [31 rows x 5 columns] @@ -499,7 +499,7 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 6 minutes 37.798 seconds) + **Total running time of the script:** ( 7 minutes 19.813 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 d1778b13a..adcadc885 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 0.012 seconds) + **Total running time of the script:** ( 0 minutes 0.281 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 9e45abe49..c6dd97c1d 100644 --- a/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt +++ b/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt @@ -38,34 +38,34 @@ Layer Normalization layer-norm: N Triton Torch Apex - 0 1024.0 585.142849 277.694907 468.114273 + 0 1024.0 606.814814 277.694907 468.114273 1 1536.0 630.153868 323.368435 511.999982 - 2 2048.0 668.734716 337.814445 520.126988 - 3 2560.0 694.237267 362.477870 518.481028 - 4 3072.0 712.347810 378.092307 501.551037 - 5 3584.0 725.873439 384.859062 458.751978 - 6 4096.0 728.177767 383.251446 455.111095 - 7 4608.0 670.254540 396.387087 423.724136 - 8 5120.0 688.403381 395.748783 417.959197 - 9 5632.0 704.000002 396.969169 413.357796 - 10 6144.0 702.171410 404.543206 409.600010 + 2 2048.0 682.666643 337.814445 520.126988 + 3 2560.0 694.237267 362.477870 512.000013 + 4 3072.0 712.347810 378.092307 506.721668 + 5 3584.0 725.873439 384.859062 455.111115 + 6 4096.0 728.177767 381.023256 451.972420 + 7 4608.0 670.254540 396.387087 431.157877 + 8 5120.0 688.403381 397.669909 422.268057 + 9 5632.0 704.000002 395.228063 415.262685 + 10 6144.0 702.171410 402.885254 409.600010 11 6656.0 700.631610 400.360920 400.360920 - 12 7168.0 690.891575 391.426634 387.459443 - 13 7680.0 678.895043 392.587863 385.203746 - 14 8192.0 636.271854 388.937680 368.179771 - 15 8704.0 627.315309 387.922008 380.502740 - 16 9216.0 606.814809 405.098894 382.010363 - 17 9728.0 587.350922 409.599987 382.427505 - 18 10240.0 566.920437 408.578556 382.803739 - 19 10752.0 547.872604 411.559798 380.601764 - 20 11264.0 533.207081 401.389743 372.363645 - 21 11776.0 520.486200 408.711507 377.587162 - 22 12288.0 516.031509 413.911572 383.251457 - 23 12800.0 504.433489 410.420828 377.163903 - 24 13312.0 494.180982 404.159395 375.647260 - 25 13824.0 482.934503 410.359948 378.739711 - 26 14336.0 472.940209 403.121247 374.185964 - 27 14848.0 461.297068 405.406157 374.712936 + 12 7168.0 690.891575 392.767108 382.293315 + 13 7680.0 678.895043 393.846167 386.415087 + 14 8192.0 633.198054 394.795186 376.643677 + 15 8704.0 624.502255 389.005597 379.465939 + 16 9216.0 606.814809 406.214877 382.010363 + 17 9728.0 587.350922 408.524944 383.369452 + 18 10240.0 564.965524 409.600010 382.803739 + 19 10752.0 546.133312 411.559798 380.601764 + 20 11264.0 532.419472 404.089694 371.595879 + 21 11776.0 520.486200 409.599991 377.587162 + 22 12288.0 513.336807 413.911572 383.251457 + 23 12800.0 504.433489 409.599981 377.163903 + 24 13312.0 494.180982 406.473303 377.645399 + 25 13824.0 482.934503 412.656711 379.389355 + 26 14336.0 471.967074 402.414053 370.558967 + 27 14848.0 461.297068 406.794504 373.534584 28 15360.0 454.269882 406.214870 377.511515 29 15872.0 447.098578 407.627589 376.225175 @@ -393,7 +393,7 @@ Layer Normalization .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 5 minutes 35.089 seconds) + **Total running time of the script:** ( 5 minutes 37.451 seconds) .. _sphx_glr_download_getting-started_tutorials_05-layer-norm.py: diff --git a/master/_sources/getting-started/tutorials/06-fused-attention.rst.txt b/master/_sources/getting-started/tutorials/06-fused-attention.rst.txt index 4fef02825..b1397b3d3 100644 --- a/master/_sources/getting-started/tutorials/06-fused-attention.rst.txt +++ b/master/_sources/getting-started/tutorials/06-fused-attention.rst.txt @@ -385,7 +385,7 @@ This is a Triton implementation of the Flash Attention algorithm .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 0 minutes 0.072 seconds) + **Total running time of the script:** ( 0 minutes 0.073 seconds) .. _sphx_glr_download_getting-started_tutorials_06-fused-attention.py: diff --git a/master/_sources/getting-started/tutorials/07-libdevice-function.rst.txt b/master/_sources/getting-started/tutorials/07-libdevice-function.rst.txt index 297ebf116..7db38fb6e 100644 --- a/master/_sources/getting-started/tutorials/07-libdevice-function.rst.txt +++ b/master/_sources/getting-started/tutorials/07-libdevice-function.rst.txt @@ -152,7 +152,7 @@ We can also customize the libdevice library path by passing the path to the `lib .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 0 minutes 0.010 seconds) + **Total running time of the script:** ( 0 minutes 0.254 seconds) .. _sphx_glr_download_getting-started_tutorials_07-libdevice-function.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 7ff0a7d7e..719cec871 100644 --- a/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt +++ b/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt @@ -5,20 +5,20 @@ Computation times ================= -**17:23.779** total execution time for **getting-started_tutorials** files: +**18:18.630** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:37.798 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 07:19.813 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:35.089 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 05:37.451 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:28.967 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:32.036 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:41.831 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:48.722 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``) | 00:00.072 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.281 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.012 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.254 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_07-libdevice-function.py` (``07-libdevice-function.py``) | 00:00.010 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_06-fused-attention.py` (``06-fused-attention.py``) | 00:00.073 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/master/getting-started/tutorials/01-vector-add.html b/master/getting-started/tutorials/01-vector-add.html index 7f6683d06..bcc3949f6 100644 --- a/master/getting-started/tutorials/01-vector-add.html +++ b/master/getting-started/tutorials/01-vector-add.html @@ -325,24 +325,24 @@ for different problem sizes.

vector-add-performance:
            size      Triton       Torch
 0        4096.0    9.600000    9.600000
-1        8192.0   19.200000   15.999999
+1        8192.0   19.200000   19.200000
 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
-6      262144.0  384.000001  384.000001
+6      262144.0  341.333321  384.000001
 7      524288.0  472.615390  472.615390
 8     1048576.0  614.400016  614.400016
 9     2097152.0  722.823517  722.823517
 10    4194304.0  780.190482  780.190482
 11    8388608.0  812.429770  812.429770
 12   16777216.0  833.084721  833.084721
-13   33554432.0  842.004273  842.004273
+13   33554432.0  842.004273  843.811163
 14   67108864.0  847.448255  848.362445
 15  134217728.0  849.737435  850.656574
-

Total running time of the script: ( 1 minutes 41.831 seconds)

+

Total running time of the script: ( 1 minutes 48.722 seconds)