diff --git a/master/.buildinfo b/master/.buildinfo index a64410ba7..10636e3f8 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: 956ebdf863b4bcdc6d83c6236bf829bb +config: 450f101380eaf48378e1ad74a6cdb220 tags: 645f666f9bcd5a90fca523b33c5a78b7 diff --git a/master/.doctrees/environment.pickle b/master/.doctrees/environment.pickle index 863072bb7..ed4436d91 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 9e3f870a8..f98c50e32 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 322b1c132..18341a38e 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 b036cd134..7bce0fddb 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 7fc419175..23e02f5a0 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 e797b4b47..64b8c2544 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 143a2c92c..bcd93a0fb 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 fb792633d..b9d9e129c 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 e6c4dae89..f30691fba 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 5c76de670..33e3bf825 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 164566958..fc9fb46f0 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 a6ee772c8..d9a560e20 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 834599e5d..a0050a934 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 da22c9cba..54c618759 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 783dd1f7a..603c67592 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 23b8d1153..dccee891f 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 0fcd3cdc8..1db15dedb 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 018de081c..8cefc21ca 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 1588c6032..094c11736 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 e997b0092..967edcbb0 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 190bc90dc..dbc0467ca 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 d7faa50ee..0a660c51a 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 1c0e5d58b..6b4702539 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 07e92e1d2..684dfbeda 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 8cfc248c8..38032a563 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 e0403094a..e9b0e1880 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 8d42b2360..245e2ca55 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 5529ca8dd..c84bc3a03 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 e31812bb6..6bc270677 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 0ab735f43..f33776369 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 5c771e5ea..4744128e3 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 10a90eece..146f8c259 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 f4a47bc75..83705d193 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 28836a93a..98eba1d55 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 8bbf57414..2f70fcdc8 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 b461f4685..283c6eb85 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 901c8db1c..041607f25 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 84ce181c1..4791f702c 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 391576acf..6565074ae 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 75d378767..546eb2308 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 79ef9e59b..0d7e9be54 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 fbc553716..ef6a3641b 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 76b752e75..0190dfe0a 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 e8b345aad..fc521e530 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 1809a0dcd..8fcc1efd3 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 3cc591907..8fe64670e 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 a05c790f1..803f2b302 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 2efe1a7dd..be819cc87 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 416fd03f3..b3c17847e 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 925e7bb73..b68247cdb 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 211c39589..f14d6f064 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 200b80f1b..9ec2b9b09 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 e12f0ae7b..153be3bf4 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 2d7d8ee7c..c1335d97c 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 7ea84b849..3e25d2b88 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 8a914ecad..a05f818ae 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 6229c9f92..9ce28b361 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 263226059..761eee340 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 27a74c0f6..a85748236 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 aab91bb9c..d13e18ee8 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 d20b43d28..3cb322987 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 9b166c1c4..da1512a69 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 95a4892db..7fd4092f7 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 3bce9195b..de44d46b3 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 a2e372d34..117fee167 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 53f0cf9e9..796237cd5 100644 --- a/master/_sources/getting-started/tutorials/01-vector-add.rst.txt +++ b/master/_sources/getting-started/tutorials/01-vector-add.rst.txt @@ -234,14 +234,14 @@ 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 38.400001 31.999999 + 2 16384.0 31.999999 31.999999 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 341.333321 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 41.611 seconds) + **Total running time of the script:** ( 1 minutes 46.703 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 d6dc6ee45..bf93a9624 100644 --- a/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt +++ b/master/_sources/getting-started/tutorials/02-fused-softmax.rst.txt @@ -279,16 +279,16 @@ 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 188.321838 - 1 384.0 585.142862 558.545450 151.703707 + 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 + 3 640.0 682.666684 640.000002 160.000000 4 768.0 722.823517 664.216187 163.839992 .. ... ... ... ... - 93 12160.0 814.058574 405.755985 198.733401 - 94 12288.0 814.111783 415.661740 198.895304 - 95 12416.0 814.163950 411.722274 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 199.038365 + 94 12288.0 814.111783 415.222812 199.298541 + 95 12416.0 814.163950 412.149375 198.954424 + 96 12544.0 814.214963 412.546756 199.111113 + 97 12672.0 814.265046 411.679167 199.264875 [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 25.996 seconds) + **Total running time of the script:** ( 3 minutes 28.363 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 0396bb3da..fd320e260 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 3.276800 - 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 ... 41.321411 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 ... 68.147202 68.147202 - 10 1536.0 79.526831 ... 79.526831 80.430545 - 11 1664.0 62.929456 ... 63.372618 63.372618 - 12 1792.0 72.983276 ... 63.499573 63.142831 - 13 1920.0 68.776119 ... 71.257735 70.892307 - 14 2048.0 73.262953 ... 78.033565 77.672296 - 15 2176.0 83.155572 ... 87.494120 86.739860 - 16 2304.0 68.446623 ... 78.064941 77.558029 - 17 2432.0 71.305746 ... 75.522751 75.320281 - 18 2560.0 77.833728 ... 82.331658 82.125311 - 19 2688.0 84.108772 ... 90.748936 90.532356 - 20 2816.0 83.233226 ... 83.873477 83.873477 - 21 2944.0 81.967162 ... 83.899046 84.182483 - 22 3072.0 81.707223 ... 88.890270 89.877939 - 23 3200.0 84.656085 ... 96.385543 96.240602 - 24 3328.0 83.226931 ... 84.995628 84.795401 - 25 3456.0 82.773682 ... 92.033756 89.779026 - 26 3584.0 86.540320 ... 95.148565 96.372338 - 27 3712.0 84.301560 ... 87.629253 88.248537 - 28 3840.0 81.079177 ... 88.050954 91.777595 - 29 3968.0 87.913500 ... 91.575185 84.915752 - 30 4096.0 92.500158 ... 88.011627 88.011627 + M cuBLAS ... Triton Triton (+ LeakyReLU) + 0 256.0 2.730667 ... 3.276800 2.978909 + 1 384.0 7.372800 ... 7.899428 8.507077 + 2 512.0 14.563555 ... 15.420235 15.420235 + 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 67.305878 + 10 1536.0 79.526831 ... 80.430545 79.526831 + 11 1664.0 63.372618 ... 63.372618 62.929456 + 12 1792.0 72.983276 ... 63.142831 62.790080 + 13 1920.0 68.776119 ... 71.257735 70.892307 + 14 2048.0 73.908442 ... 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 75.320281 + 18 2560.0 77.833728 ... 82.539044 82.125311 + 19 2688.0 83.552988 ... 91.625737 90.748936 + 20 2816.0 79.587973 ... 82.290955 84.197315 + 21 2944.0 81.232324 ... 83.477440 83.899046 + 22 3072.0 81.121923 ... 89.451983 89.735509 + 23 3200.0 84.656085 ... 96.240602 96.096095 + 24 3328.0 83.905938 ... 83.323259 82.939284 + 25 3456.0 82.519518 ... 86.876687 92.033756 + 26 3584.0 87.808000 ... 100.017124 99.354022 + 27 3712.0 84.874549 ... 88.561477 88.797643 + 28 3840.0 84.292684 ... 92.159996 85.597527 + 29 3968.0 91.816356 ... 87.976885 90.589410 + 30 4096.0 87.552332 ... 94.519528 88.011627 [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 14.105 seconds) + **Total running time of the script:** ( 6 minutes 48.929 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..96ca34cf2 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 0.323 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 8f6c2b69f..244ddea9b 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 2048.0 496.484863 161.154101 334.367350 + 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 4096.0 564.965515 220.907859 296.990947 - 7 4608.0 500.416301 232.336141 287.251954 - 8 5120.0 527.381977 242.366855 284.444444 - 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 + 5 3584.0 554.941930 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 284.444444 + 9 5632.0 542.843364 243.107920 290.060087 + 10 6144.0 544.118087 248.661056 286.879370 + 11 6656.0 527.207907 256.000009 285.767438 12 7168.0 503.017523 260.260201 284.821192 - 13 7680.0 483.779539 262.938666 280.121579 + 13 7680.0 482.513091 262.938666 280.121579 14 8192.0 463.698115 266.406514 284.526763 - 15 8704.0 414.476194 267.815384 284.987724 - 16 9216.0 426.996150 271.724806 287.999990 + 15 8704.0 414.476194 267.472468 284.987724 + 16 9216.0 428.651187 271.724806 287.999990 17 9728.0 437.213490 280.615388 290.027323 18 10240.0 446.025405 286.433562 290.153487 - 19 10752.0 429.364408 246.935876 290.267711 + 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 289.277383 + 21 11776.0 420.571432 249.888595 288.981596 22 12288.0 416.542386 254.673582 294.617366 - 23 12800.0 410.695192 253.884294 287.910035 - 24 13312.0 409.075539 252.959629 290.443638 - 25 13824.0 405.098897 257.390218 291.799461 - 26 14336.0 394.568805 254.862216 287.198654 - 27 14848.0 386.498925 257.852379 289.717061 - 28 15360.0 380.433442 257.790220 288.000007 - 29 15872.0 370.552519 261.806182 290.120338 + 23 12800.0 410.695192 254.094291 289.811310 + 24 13312.0 409.075539 253.160074 290.443638 + 25 13824.0 404.604870 257.390218 292.056329 + 26 14336.0 394.116833 255.051144 286.959121 + 27 14848.0 385.662341 257.852379 289.952797 + 28 15360.0 380.433442 257.970599 287.550706 + 29 15872.0 370.192407 261.806182 290.341468 @@ -339,7 +339,7 @@ Layer Normalization .. rst-class:: sphx-glr-timing - **Total running time of the script:** ( 2 minutes 14.046 seconds) + **Total running time of the script:** ( 2 minutes 14.282 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 9dca1041b..028862feb 100644 --- a/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt +++ b/master/_sources/getting-started/tutorials/sg_execution_times.rst.txt @@ -5,16 +5,16 @@ Computation times ================= -**13:35.769** total execution time for **getting-started_tutorials** files: +**14:18.601** total execution time for **getting-started_tutorials** files: +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:14.105 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 06:48.929 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:25.996 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 03:28.363 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:14.046 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_05-layer-norm.py` (``05-layer-norm.py``) | 02:14.282 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ -| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:41.611 | 0.0 MB | +| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 01:46.703 | 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_04-low-memory-dropout.py` (``04-low-memory-dropout.py``) | 00:00.323 | 0.0 MB | +---------------------------------------------------------------------------------------------------------+-----------+--------+ diff --git a/master/getting-started/tutorials/01-vector-add.html b/master/getting-started/tutorials/01-vector-add.html index c5e072179..912a0addd 100644 --- a/master/getting-started/tutorials/01-vector-add.html +++ b/master/getting-started/tutorials/01-vector-add.html @@ -324,14 +324,14 @@ for different problem sizes.

size Triton Torch 0 4096.0 9.600000 9.600000 1 8192.0 19.200000 19.200000 -2 16384.0 38.400001 31.999999 +2 16384.0 31.999999 31.999999 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 341.333321 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 41.611 seconds)

+

Total running time of the script: ( 1 minutes 46.703 seconds)