Raghavan Raman 0d94c04247 [NNC] Change fuseLoops API to return bool flag and not throw any exceptions (#56353) ...

Summary:
Partial fix for https://github.com/pytorch/pytorch/issues/56357

Changes the `fuseLoops` API to the following form:
```
static bool fuseLoops(const std::vector<For*>& loops, For** fused);
```

Also, adds a new API to check for loop-carried dependences:
```
static bool hasLoopCarriedDependence(For* loop);
```

Pull Request resolved: https://github.com/pytorch/pytorch/pull/56353

Reviewed By: bertmaher

Differential Revision: D27856214

Pulled By: navahgar

fbshipit-source-id: 443557088692585657faee296602c547a00117dd

2021-04-19 17:20:40 -07:00

..

operators

NNC depthwise conv2d implementation (#54920)

2021-04-08 21:56:53 -07:00

analysis.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

block_codegen.cpp

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

block_codegen.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

bounds_inference.cpp

Revert D27448156: irange for size_t

2021-04-03 19:14:00 -07:00

bounds_inference.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

bounds_overlap.cpp

[NNC] Simplify and fix some bugs in Bounds Inference (#47450)

2020-11-09 21:37:04 -08:00

bounds_overlap.h

[NNC] add hazard analysis to Bounds Inference (#47684)

2020-11-12 11:34:31 -08:00

codegen.cpp

[te] Don't throw when re-registering a CodeGen factory (#49174)

2020-12-10 23:37:29 -08:00

codegen.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

cpp_codegen.cpp

[NNC] Generate C++ code for Allocate and Free (#51070)

2021-02-01 13:06:51 -08:00

cpp_codegen.h

[NNC] Generate C++ code for Allocate and Free (#51070)

2021-02-01 13:06:51 -08:00

cuda_codegen.cpp

[reland][ROCm] use hiprtc precompiled header (#55965)

2021-04-15 15:47:56 -07:00

cuda_codegen.h

Implemented getCodeText(string attr) in llvm/cuda codegen and added python bindings for it - #52974 (#53664)

2021-03-11 11:57:39 -08:00

cuda_random.h

[TensorExpr] Add CUDA codegen. (#34227)

2020-03-16 11:49:29 -07:00

dim_arg.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

eval.cpp

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

eval.h

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

exceptions.h

[TensorExpr] Add IRVerifier. (#52901)

2021-03-01 20:38:00 -08:00

execution_counter.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

expr.cpp

NNC depthwise conv2d implementation (#54920)

2021-04-08 21:56:53 -07:00

expr.h

NNC depthwise conv2d implementation (#54920)

2021-04-08 21:56:53 -07:00

external_functions_registry.cpp

[TensorExpr] Resubmit: Introduce ExternalCall nodes to TE IR. (#51594)

2021-02-03 10:22:54 -08:00

external_functions_registry.h

[TensorExpr] Resubmit: Introduce ExternalCall nodes to TE IR. (#51594)

2021-02-03 10:22:54 -08:00

external_functions.cpp

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

external_functions.h

[TensorExpr] Resubmit: Introduce ExternalCall nodes to TE IR. (#51594)

2021-02-03 10:22:54 -08:00

half_support.h

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

hash_provider.cpp

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

hash_provider.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

intrinsic_symbols.cpp

[nnc] Expose vectorized math functions to jit fuser. (#51190)

2021-01-28 22:35:07 -08:00

intrinsic_symbols.h

[nnc] Expose vectorized math functions to jit fuser. (#51190)

2021-01-28 22:35:07 -08:00

ir_mutator.cpp

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

ir_mutator.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

ir_printer.cpp

Revert D27448156: irange for size_t

2021-04-03 19:14:00 -07:00

ir_printer.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

ir_simplifier.cpp

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

ir_simplifier.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

ir_verifier.cpp

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

ir_verifier.h

[TensorExpr] Add IRVerifier. (#52901)

2021-03-01 20:38:00 -08:00

ir_visitor.cpp

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

ir_visitor.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

ir.cpp

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

ir.h

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

IRSpecification.md

[TensorExpr] Remove stale docs from DesignOverview.md. (#55000)

2021-04-01 19:48:05 -07:00

kernel.cpp

[TensorExpr] Add support for constant tensors in tensorexpr kernel. (#56319)

2021-04-17 11:15:35 -07:00

kernel.h

[TensorExpr] Add support for constant tensors in tensorexpr kernel. (#56319)

2021-04-17 11:15:35 -07:00

llvm_codegen.cpp

[nnc][trivial] Trailing underscore style for llvmCode, asmCode members (#56118)

2021-04-15 14:01:28 -07:00

llvm_codegen.h

Resubmit: Adding parallel support for the LLVM backend. (#54122)

2021-03-18 07:19:37 -07:00

llvm_jit.cpp

Resubmit: Adding parallel support for the LLVM backend. (#54122)

2021-03-18 07:19:37 -07:00

llvm_jit.h

Resubmit: Adding parallel support for the LLVM backend. (#54122)

2021-03-18 07:19:37 -07:00

loopnest.cpp

[NNC] Change fuseLoops API to return bool flag and not throw any exceptions (#56353)

2021-04-19 17:20:40 -07:00

loopnest.h

[NNC] Change fuseLoops API to return bool flag and not throw any exceptions (#56353)

2021-04-19 17:20:40 -07:00

mem_arena.cpp

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

mem_arena.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

mem_dependency_checker.cpp

Revert D27448156: irange for size_t

2021-04-03 19:14:00 -07:00

mem_dependency_checker.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

reduction.cpp

Remove ReduceOp::accumulator (#52196)

2021-02-17 23:36:23 -08:00

reduction.h

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

registerizer.cpp

[TensorExpr] Remove mask field from Load and Store classes. (#55825)

2021-04-13 12:08:51 -07:00

registerizer.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

stmt.h

[NNC] Make normalization transformation in-place (#56158)

2021-04-18 23:54:13 -07:00

tensor.cpp

[TensorExpr] Rename Tensor::call to Tensor::load to be consistent with Buf and Placeholder. (#55826)

2021-04-13 12:08:53 -07:00

tensor.h

[TensorExpr] Rename Tensor::call to Tensor::load to be consistent with Buf and Placeholder. (#55826)

2021-04-13 12:08:53 -07:00

tensorexpr_init.cpp

[NNC] Change fuseLoops API to return bool flag and not throw any exceptions (#56353)

2021-04-19 17:20:40 -07:00

tensorexpr_init.h

[TensorExpr] Add python bindings. (#49698)

2021-01-14 21:02:47 -08:00

types.cpp

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

types.h

[BE] Make torch/csrc/jit/tensorexpr/ clang-tidy clean (#55628)

2021-04-08 19:44:14 -07:00

unique_name_manager.cpp

[TensorExpr] Compiler warnings cleanups. (#35925)

2020-04-03 12:18:42 -07:00

unique_name_manager.h

[TensorExpr] Pull changes to core classes for representing expressions and statements from the side branch. (#34224)

2020-03-16 11:47:47 -07:00

var_substitutor.h

Remove ReduceOp::accumulator (#52196)

2021-02-17 23:36:23 -08:00