Path Lines of Code benchmarks/compare-fastrnn-results.py 47 benchmarks/cpp/convolution.cpp 289 benchmarks/cpp/nvfuser/batch_norm.cpp 191 benchmarks/cpp/nvfuser/batch_norm_backward.cpp 211 benchmarks/cpp/nvfuser/bert.cpp 557 benchmarks/cpp/nvfuser/broadcast.cpp 260 benchmarks/cpp/nvfuser/gelu_backward.cpp 148 benchmarks/cpp/nvfuser/heuristic_cache.cpp 135 benchmarks/cpp/nvfuser/heuristic_lookup.cpp 135 benchmarks/cpp/nvfuser/instance_norm.cpp 165 benchmarks/cpp/nvfuser/layer_norm.cpp 168 benchmarks/cpp/nvfuser/layer_norm_backward.cpp 202 benchmarks/cpp/nvfuser/lstm_cell.cpp 163 benchmarks/cpp/nvfuser/main.cpp 2 benchmarks/cpp/nvfuser/reduction.cpp 258 benchmarks/cpp/nvfuser/scale_bias_relu.cpp 301 benchmarks/cpp/nvfuser/shape_inference.cpp 170 benchmarks/cpp/nvfuser/softmax.cpp 320 benchmarks/cpp/nvfuser/softmax_backward.cpp 255 benchmarks/cpp/nvfuser/softmax_dropout.cpp 300 benchmarks/cpp/nvfuser/utils.cpp 150 benchmarks/cpp/nvfuser/utils.h 103 benchmarks/cpp/tensorexpr/bench_approx.cpp 409 benchmarks/cpp/tensorexpr/bench_batchnorm.cpp 203 benchmarks/cpp/tensorexpr/bench_compile.cpp 78 benchmarks/cpp/tensorexpr/bench_concat.cpp 251 benchmarks/cpp/tensorexpr/bench_fuser_overhead.cpp 44 benchmarks/cpp/tensorexpr/bench_gemm.cpp 265 benchmarks/cpp/tensorexpr/bench_ops.py 84 benchmarks/cpp/tensorexpr/bench_parallel.cpp 61 benchmarks/cpp/tensorexpr/bench_prefix_sum.cpp 336 benchmarks/cpp/tensorexpr/bench_reduce.cpp 527 benchmarks/cpp/tensorexpr/bench_signed_log1p.cpp 143 benchmarks/cpp/tensorexpr/main.cpp 2 benchmarks/distributed/ddp/benchmark.py 214 benchmarks/distributed/ddp/compare/compare_ddp.py 181 benchmarks/distributed/ddp/compare/python_ddp.py 112 benchmarks/distributed/ddp/diff.py 56 benchmarks/distributed/pipeline/benchmark_dataset.py 37 benchmarks/distributed/pipeline/pipe.py 208 benchmarks/distributed/rpc/parameter_server/data/DummyData.py 37 benchmarks/distributed/rpc/parameter_server/data/__init__.py 4 benchmarks/distributed/rpc/parameter_server/launcher.py 438 benchmarks/distributed/rpc/parameter_server/metrics/CPUMetric.py 17 benchmarks/distributed/rpc/parameter_server/metrics/CUDAMetric.py 25 benchmarks/distributed/rpc/parameter_server/metrics/MetricBase.py 19 benchmarks/distributed/rpc/parameter_server/metrics/MetricsLogger.py 44 benchmarks/distributed/rpc/parameter_server/metrics/ProcessedMetricsPrinter.py 44 benchmarks/distributed/rpc/parameter_server/models/DummyModel.py 21 benchmarks/distributed/rpc/parameter_server/models/__init__.py 4 benchmarks/distributed/rpc/parameter_server/server/__init__.py 5 benchmarks/distributed/rpc/parameter_server/server/server.py 195 benchmarks/distributed/rpc/parameter_server/trainer/__init__.py 31 benchmarks/distributed/rpc/parameter_server/trainer/criterions.py 4 benchmarks/distributed/rpc/parameter_server/trainer/ddp_models.py 9 benchmarks/distributed/rpc/parameter_server/trainer/hook_states.py 12 benchmarks/distributed/rpc/parameter_server/trainer/hooks.py 58 benchmarks/distributed/rpc/parameter_server/trainer/iteration_steps.py 13 benchmarks/distributed/rpc/parameter_server/trainer/preprocess_data.py 6 benchmarks/distributed/rpc/parameter_server/trainer/trainer.py 144 benchmarks/distributed/rpc/parameter_server/utils.py 43 benchmarks/distributed/rpc/rl/agent.py 103 benchmarks/distributed/rpc/rl/coordinator.py 89 benchmarks/distributed/rpc/rl/launcher.py 146 benchmarks/distributed/rpc/rl/observer.py 39 benchmarks/fastrnns/__init__.py 7 benchmarks/fastrnns/bench.py 210 benchmarks/fastrnns/cells.py 79 benchmarks/fastrnns/conftest.py 13 benchmarks/fastrnns/custom_lstms.py 338 benchmarks/fastrnns/factory.py 350 benchmarks/fastrnns/fuser.py 33 benchmarks/fastrnns/profile.py 99 benchmarks/fastrnns/runner.py 57 benchmarks/fastrnns/scratch.py 35 benchmarks/fastrnns/test.py 119 benchmarks/framework_overhead_benchmark/C2Module.py 29 benchmarks/framework_overhead_benchmark/SimpleAddModule.py 13 benchmarks/framework_overhead_benchmark/framework_overhead_benchmark.py 62 benchmarks/framework_overhead_benchmark/pt_wrapper_module.py 23 benchmarks/framework_overhead_benchmark/utils.py 28 benchmarks/functional_autograd_benchmark/audio_text_models.py 90 benchmarks/functional_autograd_benchmark/compare.py 37 benchmarks/functional_autograd_benchmark/functional_autograd_benchmark.py 136 benchmarks/functional_autograd_benchmark/ppl_models.py 52 benchmarks/functional_autograd_benchmark/torchaudio_models.py 330 benchmarks/functional_autograd_benchmark/torchvision_models.py 466 benchmarks/functional_autograd_benchmark/utils.py 52 benchmarks/functional_autograd_benchmark/vision_models.py 76 benchmarks/fuser/plot_speedups.py 18 benchmarks/fuser/run_benchmarks.py 228 benchmarks/instruction_counts/applications/__init__.py 1 benchmarks/instruction_counts/applications/ci.py 59 benchmarks/instruction_counts/core/__init__.py 1 benchmarks/instruction_counts/core/api.py 236 benchmarks/instruction_counts/core/expand.py 140 benchmarks/instruction_counts/core/types.py 11 benchmarks/instruction_counts/core/utils.py 69 benchmarks/instruction_counts/definitions/__init__.py 1 benchmarks/instruction_counts/definitions/setup.py 23 benchmarks/instruction_counts/definitions/standard.py 78 benchmarks/instruction_counts/execution/__init__.py 1 benchmarks/instruction_counts/execution/runner.py 188 benchmarks/instruction_counts/execution/work.py 152 benchmarks/instruction_counts/main.py 25 benchmarks/instruction_counts/worker/__init__.py 1 benchmarks/instruction_counts/worker/main.py 93 benchmarks/operator_benchmark/__init__.py 1 benchmarks/operator_benchmark/benchmark_caffe2.py 113 benchmarks/operator_benchmark/benchmark_core.py 242 benchmarks/operator_benchmark/benchmark_pytorch.py 101 benchmarks/operator_benchmark/benchmark_runner.py 113 benchmarks/operator_benchmark/benchmark_test_generator.py 12 benchmarks/operator_benchmark/benchmark_utils.py 158 benchmarks/operator_benchmark/c2/__init__.py 1 benchmarks/operator_benchmark/common/__init__.py 1 benchmarks/operator_benchmark/common/repeat_benchmark.py 45 benchmarks/operator_benchmark/operator_benchmark.py 4 benchmarks/operator_benchmark/pt/__init__.py 1 benchmarks/operator_benchmark/pt/configs.py 101 benchmarks/operator_benchmark/pt_extension/extension.cpp 18 benchmarks/operator_benchmark/pt_extension/setup.py 5 benchmarks/overrides_benchmark/bench.py 52 benchmarks/overrides_benchmark/common.py 22 benchmarks/overrides_benchmark/pyspybench.py 22 benchmarks/profiler_benchmark/profiler_bench.py 84 benchmarks/profiler_benchmark/resnet_memory_profiler.py 18 benchmarks/record_function_benchmark/record_function_bench.py 83 benchmarks/serialization/simple_measurement.py 26 benchmarks/sparse/__init__.py 2 benchmarks/sparse/dlmc/__init__.py 2 benchmarks/sparse/dlmc/matmul_bench.py 98 benchmarks/sparse/dlmc/utils.py 131 benchmarks/sparse/spmm.py 82 benchmarks/sparse/spmv.py 80 benchmarks/sparse/utils.py 42 benchmarks/static_runtime/deep_wide_pt.cc 124 benchmarks/static_runtime/deep_wide_pt.h 103 benchmarks/static_runtime/deep_wide_pt_bench.cc 163 benchmarks/tensorexpr/__main__.py 288 benchmarks/tensorexpr/attention.py 63 benchmarks/tensorexpr/benchmark.py 239 benchmarks/tensorexpr/broadcast.py 240 benchmarks/tensorexpr/concat.py 99 benchmarks/tensorexpr/conv.py 87 benchmarks/tensorexpr/elementwise.py 188 benchmarks/tensorexpr/matmul.py 49 benchmarks/tensorexpr/microbenchmarks.py 205 benchmarks/tensorexpr/normalization.py 62 benchmarks/tensorexpr/pooling.py 50 benchmarks/tensorexpr/pt_engine.py 50 benchmarks/tensorexpr/reduction.py 215 benchmarks/tensorexpr/rnn_eltwise.py 87 benchmarks/tensorexpr/softmax.py 42 benchmarks/tensorexpr/swish.py 39 benchmarks/tensorexpr/tensor_engine.py 34 benchmarks/upload_scribe.py 120