pytorch/benchmarks/cpp/nvfuser
jjsjann123 b21a6ff639 [NVFuser] Upstream push 0811 (#83239)
Syncing nvfuser devel branch to upstream master. https://github.com/csarofeen/pytorch/

Code changes includes:

- codegen improvements:
  1. double support in expression evaluator
- bug fixes:
  1. dropout fix - rework RNG to support broadcasted dropout (Fixes #82784)
  2. expand fix - Patch expand+reduction, expand+view, rework view analysis and guard
- scheduler:
  1. manual transpose schedule example
  2. WIP transpose scheduler

Commits that's in this PR from the devel branch:

```
b7435afcd22c917713c2f41a7237bc26e1183f14 Transpose scheduler, step 1 (#1854)
8a45dbf72034684eb8e18b1835b533e90b68f184 Add an example on how to manually schedule transpose (#1889)
83dbf56a9554b2efbd5416461d938fff477b0b27 Patch dropout fix (#1898)
69d3519a532250719b1aa8341b50e067b181b42d Expand+Reduction, Expand+View support, rework View analysis and guards (#1883)
15091c488e96343bdc49e3990acbf238a3b3da51 Rework RNG to correctly support broadcasted dropout (#1888)
aafe2d048aaac596e503596a41303423619f3954 Make ExpressionEvaluator support Double (#1885)
```

RUN_TORCHBENCH: nvfuser

Differential Revision: [D38657074](https://our.internmc.facebook.com/intern/diff/D38657074)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/83239
Approved by: https://github.com/davidberard98
2022-08-25 02:23:22 +00:00
..
batch_norm_channels_first.cpp Upstream master bump 0513 (#77471) 2022-05-18 11:48:50 -07:00
batch_norm_channels_first_backward.cpp Upstream master bump 0513 (#77471) 2022-05-18 11:48:50 -07:00
batch_norm_channels_last.cpp Upstream master bump 0513 (#77471) 2022-05-18 11:48:50 -07:00
batch_norm_channels_last_backward.cpp Upstream master bump 0513 (#77471) 2022-05-18 11:48:50 -07:00
bert.cpp [NVFuser] Upstream push 0811 (#83239) 2022-08-25 02:23:22 +00:00
broadcast.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
CMakeLists.txt [BE] Add append_cxx_flag_if_supported macro (#82883) 2022-08-10 14:32:26 +00:00
gelu_backward.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
heuristic_cache.cpp Upstream master bump 0513 (#77471) 2022-05-18 11:48:50 -07:00
heuristic_lookup.cpp Upstream master bump 0513 (#77471) 2022-05-18 11:48:50 -07:00
instance_norm.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
layer_norm.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
layer_norm_backward.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
lstm_cell.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
main.cpp
reduction.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
rms_norm.cpp Upstream master bump 0513 (#77471) 2022-05-18 11:48:50 -07:00
rms_norm_backward.cpp Upstream master bump 0513 (#77471) 2022-05-18 11:48:50 -07:00
scale_bias_relu.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
shape_inference.cpp Upstream master bump 0513 (#77471) 2022-05-18 11:48:50 -07:00
softmax.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
softmax_backward.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
softmax_dropout.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
timm.cpp [nvfuser_upstream_push] Reland: nvfuser code base bump 060822 (#79406) 2022-06-16 17:52:21 +00:00
transpose.cpp [NVFuser] Upstream push 0809 (#83067) 2022-08-10 21:02:56 +00:00
utils.cpp Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00
utils.h Check all CUDA API calls for errors in benchmarks/cpp/nvfuser (#74920) (#81817) 2022-08-24 18:59:05 +00:00