diff --git a/master/.buildinfo b/master/.buildinfo index 08dd12f3b..65493edc0 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: 5d1e5336b0fe1254665c1a22d9c46408 +config: e596642ff1cf86c1376bbeb43852c411 tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/master/.doctrees/environment.pickle b/master/.doctrees/environment.pickle index 94eb69708..ae5f340f8 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 d77309df7..74dae0692 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 537eaeae3..af02e2ecd 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 ea9a22638..a09c9be45 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 5f86ffa16..0f1d59f04 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 a0d44397b..1122c1094 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 ef52d63d1..78abc4c36 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 737d02547..da72c84ce 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 e6da6530f..656bfbc8b 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 3a229ff1c..97b2d803b 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 dc97f532e..852d7ceac 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 e5e15d601..1f484cc36 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 db8e4e9ff..a95e7d7e3 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 37a2da6a6..fb430a37c 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 34d6a474a..ba5aa8909 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 a4a74df82..8ab1889c8 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 59b2bb7fc..3372b9667 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 4a026e3eb..a83923fd1 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 e403e2005..827f90ebd 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 538a31622..eb351adee 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 23badf315..70dabd398 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 10167f7d2..26c8d139e 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 50fe71f81..9d17b9268 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 f25abfe2c..4482ab6db 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 d0c862025..d9c750b8a 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 6eb4519e4..d333e4969 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 d05a98e7b..eb3fa26cb 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 3975fb810..52bcadf3f 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 445862c9b..cdf45a142 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 bb9203f5a..3a6d7dc8f 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 d6d0284db..10c25537c 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 e163ccc4b..8c0ad1cbb 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 e19b565b5..af8b70d0b 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 8a435cd66..578224806 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 a3f2fa289..0398be857 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 7f7444ffe..6e97a3c2a 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 291b4f0f5..b17b38448 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 5cdfabfcf..317334f10 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 0db2d6093..567abd67a 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 7db8a3e5e..167b753ab 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 39781c95a..fec8f3938 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 ee39c71fe..5f487b2ca 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 aa8f7a4fa..795541527 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 af796393b..f3888a39b 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 34084dc96..b30385924 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 b362a283a..090fa9084 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 22d4a2abf..96afa3235 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 3514e2e2e..59ba62ad0 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 8e7de10a4..988611e1d 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 a5ad0abee..55c481323 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 b5b4716b9..cc53800df 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 6a1777038..09410d5e2 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 06a01cb1f..682d80e67 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 6b7737460..6a2a8a270 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 945fbf47e..504d41892 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 c8cb5564e..1128e2dcd 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 5517fab6b..fea2726e1 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 5a990ce42..e00e048ba 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 b04c489ee..3c0fa8bbe 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 de340db21..3aa7eced9 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 db485525f..e204b6eff 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 44463ebc3..aafd1ea5a 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 4ee6a0715..a570c86a7 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 f07cee5b7..e8fa2b923 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 9737bca4d..85d94d7a9 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 6398d5a48..cb7937efe 100644 --- a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -235,13 +235,13 @@ We can now run the decorated function above. Pass `print_data=True` to see the p 0 4096.0 9.600000 9.600000 1 8192.0 19.200000 19.200000 2 16384.0 38.400001 38.400001 - 3 32768.0 63.999998 63.999998 + 3 32768.0 76.800002 76.800002 4 65536.0 127.999995 127.999995 5 131072.0 219.428568 219.428568 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 702.171410 + 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 @@ -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 24.953 seconds) + **Total running time of the script:** ( 1 minutes 38.189 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 c05d61ac5..8bcefb043 100644 --- a/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt +++ b/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt @@ -278,16 +278,16 @@ 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 190.511628 - 1 384.0 585.142862 558.545450 151.703707 + 0 256.0 546.133347 546.133347 188.321838 + 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 .. ... ... ... ... - 93 12160.0 814.058574 405.755985 198.530610 - 94 12288.0 814.111783 415.222812 198.794749 + 93 12160.0 814.058574 405.755985 198.631953 + 94 12288.0 814.111783 415.661740 198.794749 95 12416.0 814.163950 412.149375 198.457532 - 96 12544.0 814.214963 412.971190 198.618504 + 96 12544.0 814.214963 412.971190 198.716830 97 12672.0 814.265046 411.679167 198.776477 [98 rows x 4 columns] @@ -306,7 +306,7 @@ In the above plot, we can see that: .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 3 minutes 19.032 seconds) + **Total running time of the script:** ( 3 minutes 22.664 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 47fc37fd4..5f6010d0d 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 ... 2.978909 3.276800 - 1 384.0 7.372800 ... 7.899428 7.899428 - 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 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 62.929456 ... 63.372618 62.929456 - 12 1792.0 72.983276 ... 63.499573 63.142831 - 13 1920.0 68.776119 ... 71.257735 71.257735 - 14 2048.0 73.584279 ... 78.398206 78.033565 - 15 2176.0 83.500614 ... 87.115360 86.739860 - 16 2304.0 68.251065 ... 78.320893 77.810656 - 17 2432.0 71.305746 ... 75.726318 75.522751 - 18 2560.0 77.833728 ... 82.331658 81.715711 - 19 2688.0 83.552988 ... 90.966561 90.966561 - 20 2816.0 82.602666 ... 84.687779 84.523664 - 21 2944.0 82.921853 ... 83.758038 84.182483 - 22 3072.0 82.181572 ... 89.170242 88.197981 - 23 3200.0 81.321474 ... 95.238096 94.395283 - 24 3328.0 82.939284 ... 86.320498 85.908470 - 25 3456.0 80.140726 ... 87.727494 91.407671 - 26 3584.0 87.381330 ... 100.128496 99.684470 - 27 3712.0 83.247783 ... 87.629253 89.194055 - 28 3840.0 84.228485 ... 92.236860 85.533390 - 29 3968.0 91.885495 ... 85.093402 90.589410 - 30 4096.0 91.616198 ... 93.792965 91.242506 + 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 ... 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 39.025776 + 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 67.305878 + 10 1536.0 79.526831 ... 79.526831 79.526831 + 11 1664.0 62.929456 ... 63.372618 62.929456 + 12 1792.0 72.512412 ... 63.142831 62.790080 + 13 1920.0 69.120002 ... 71.257735 70.892307 + 14 2048.0 73.262953 ... 78.033565 77.672296 + 15 2176.0 83.155572 ... 87.115360 86.739860 + 16 2304.0 68.251065 ... 77.810656 77.810656 + 17 2432.0 71.305746 ... 75.522751 75.320281 + 18 2560.0 77.833728 ... 82.539044 82.125311 + 19 2688.0 83.737433 ... 91.185232 90.748936 + 20 2816.0 84.523664 ... 81.445766 84.523664 + 21 2944.0 81.298583 ... 83.899046 84.040530 + 22 3072.0 82.540970 ... 90.164177 89.735509 + 23 3200.0 84.656085 ... 96.385543 96.240602 + 24 3328.0 83.226931 ... 85.602017 84.249616 + 25 3456.0 81.849303 ... 85.133652 84.864807 + 26 3584.0 87.466332 ... 99.684470 99.354022 + 27 3712.0 81.548851 ... 84.159518 87.706180 + 28 3840.0 84.874902 ... 86.535214 91.398346 + 29 3968.0 88.040360 ... 92.442373 86.480463 + 30 4096.0 93.760204 ... 91.992956 90.871857 [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:** ( 5 minutes 44.529 seconds) + **Total running time of the script:** ( 6 minutes 30.096 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 8c652cdd2..5b75c1d5e 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 0.013 seconds) + **Total running time of the script:** ( 0 minutes 0.324 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 c5efc1510..6aa377425 100644 --- a/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt +++ b/master/_sources/getting-started/tutorials/05-layer-norm.rst.txt @@ -40,34 +40,34 @@ Layer Normalization N Triton Torch Apex 0 1024.0 361.411758 97.912354 303.407414 1 1536.0 409.599994 134.540150 341.333333 - 2 2048.0 491.520012 161.154101 334.367350 - 3 2560.0 461.954908 181.238943 330.322572 - 4 3072.0 519.211251 192.501302 323.368415 - 5 3584.0 558.545477 208.271186 311.652167 - 6 4096.0 568.231237 220.907859 298.796351 - 7 4608.0 502.690905 232.825259 287.251954 - 8 5120.0 527.381977 242.366855 284.444444 - 9 5632.0 542.843364 243.107920 289.438969 + 2 2048.0 491.520012 161.154101 323.368435 + 3 2560.0 461.954908 181.238943 326.808501 + 4 3072.0 515.580429 192.501302 320.556515 + 5 3584.0 554.941930 208.271186 311.652167 + 6 4096.0 561.737163 220.907859 294.323343 + 7 4608.0 502.690905 232.825259 291.799469 + 8 5120.0 525.128191 242.366855 289.129408 + 9 5632.0 540.671974 243.107920 288.820505 10 6144.0 546.133354 248.661056 286.322318 - 11 6656.0 527.207907 256.000009 285.767438 - 12 7168.0 503.017523 259.867079 284.821192 - 13 7680.0 483.779539 262.938666 280.121579 - 14 8192.0 463.698115 266.587109 284.526763 - 15 8704.0 414.476194 267.815384 284.599455 - 16 9216.0 426.996150 271.391419 287.999990 - 17 9728.0 437.213490 280.278512 290.027323 - 18 10240.0 446.025405 286.433562 290.496460 - 19 10752.0 429.364408 247.172406 290.594591 - 20 11264.0 427.071098 245.313973 286.980888 - 21 11776.0 421.198220 249.667843 289.277383 - 22 12288.0 416.542386 254.893699 294.617366 - 23 12800.0 411.244989 253.884294 289.811310 + 11 6656.0 527.207907 256.000009 285.257135 + 12 7168.0 503.017523 260.063480 285.293536 + 13 7680.0 483.779539 262.938666 275.928134 + 14 8192.0 463.698115 266.767970 284.526763 + 15 8704.0 413.655443 267.472468 284.987724 + 16 9216.0 427.822068 271.724806 288.375482 + 17 9728.0 436.396262 280.615388 289.667485 + 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 11776.0 420.571432 249.667843 288.981596 + 22 12288.0 416.542386 254.673582 294.617366 + 23 12800.0 410.695192 253.884294 288.180121 24 13312.0 409.075539 252.959629 290.443638 - 25 13824.0 405.098897 257.390218 292.056329 - 26 14336.0 395.021816 254.862216 287.198654 - 27 14848.0 386.498925 257.852379 289.717061 - 28 15360.0 380.433442 257.970599 287.550706 - 29 15872.0 370.552519 261.626369 290.120338 + 25 13824.0 404.604870 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 15872.0 370.192407 261.626369 290.562936 @@ -339,7 +339,7 @@ Layer Normalization .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 2 minutes 12.505 seconds) + **Total running time of the script:** ( 2 minutes 14.541 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 3ae762790..2e1f6608c 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 ================= -**12:41.032** total execution time for **getting-started_tutorials** files: +**13:45.813** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 05:44.529 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:30.096 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:19.032 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:22.664 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:12.505 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:14.541 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:24.953 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:38.189 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.013 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.324 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/master/getting-started/tutorials/01-vector-add.html b/master/getting-started/tutorials/01-vector-add.html index 1d945092c..22ef9f389 100644 --- a/master/getting-started/tutorials/01-vector-add.html +++ b/master/getting-started/tutorials/01-vector-add.html @@ -325,13 +325,13 @@ for different problem sizes.

0 4096.0 9.600000 9.600000 1 8192.0 19.200000 19.200000 2 16384.0 38.400001 38.400001 -3 32768.0 63.999998 63.999998 +3 32768.0 76.800002 76.800002 4 65536.0 127.999995 127.999995 5 131072.0 219.428568 219.428568 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 702.171410 +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 @@ -340,7 +340,7 @@ for different problem sizes.

15 134217728.0 849.737435 850.656574 -

Total running time of the script: ( 1 minutes 24.953 seconds)

+

Total running time of the script: ( 1 minutes 38.189 seconds)