llvm
/
torch-mlir
mirror of https://github.com/llvm/torch-mlir
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
torch-mlir/test/Dialect/TorchConversion/verify-invariants-before-ba...

37 lines
1.4 KiB
MLIR
Raw Normal View History

Move TorchConversion dialect and TorchTo* into torch-mlir
2021-09-24 11:59:12 +08:00
// RUN: torch-mlir-opt -split-input-file -verify-diagnostics %s -torch-verify-invariants-before-backend-lowering
Generalize support for elementwise ops. We plumb through e2e a fair number of interesting cases: - unary, binary, ternary elementwise ops - ops like `torch.aten.add.Tensor` that also take a scalar parameter - static size-1 broadcasting We allow the static size-1 broadcasting case, but emit a runtime error in the case of dynamic size-1 broadcasting. This seems like a sweet spot subset of things that can be lowered directly to linalg, while not being overly constraining to users. This is consistent with what IREE is doing for CHLO->Linalg lowering as well ([code](https://github.com/google/iree/blob/50bf7a87e465d2048c527bc27724edde40519b7e/iree/compiler/InputConversion/MHLO/BroadcastingToLinalgPatterns.cpp#L1)). To test the static size-1 case, we added support for the `torch.aten.unsqueeze` op and lowering for it through `linalg.tensor_expand_shape`. This involved a generalization of `MaximizeValueSemantics` able to handle it (the solution there also works for `torch.aten.flatten.using_ints` which we need for ResNet anyway) Also, a few minor additional changes: - Add `VerifyInvariantsBeforeBackendLowering` pass, which catches a large class of errors before we get to backend lowering (now that we are doing dialect conversion, the errors are way nicer if we just emit them up front rather than in the guts of a random pattern). - Minor change to RefBackend to allow `linalg.tensor_expand_shape`. Recommended review order: - e2e tests in elementwise.py - `ConvertElementwiseOp` in TorchToLinalg.cpp + elementwise.mlir test - `ConvertAtenUnsqueezeOp` in TorchToLinalg.cpp + unsqueeze.mlir test - RefineTypes.cpp + tests - MaximizeValueSemantics changes + test - VerifyInvariantsBeforeBackendLowering pass + test
2021-06-26 08:25:09 +08:00
// -----
mlir: bump llvm tag to 5380e3 (#856) In addition to updating the llvm-project submodule, this patch also: 1. updates shape functions and tests so that `func` and `call` operations refer to the `func` dialect 2. avoid duplicate registration of dialects
2022-05-17 03:54:35 +08:00
func.func @unknown_rank(%arg0: !torch.vtensor<[],f32>) {
Generalize support for elementwise ops. We plumb through e2e a fair number of interesting cases: - unary, binary, ternary elementwise ops - ops like `torch.aten.add.Tensor` that also take a scalar parameter - static size-1 broadcasting We allow the static size-1 broadcasting case, but emit a runtime error in the case of dynamic size-1 broadcasting. This seems like a sweet spot subset of things that can be lowered directly to linalg, while not being overly constraining to users. This is consistent with what IREE is doing for CHLO->Linalg lowering as well ([code](https://github.com/google/iree/blob/50bf7a87e465d2048c527bc27724edde40519b7e/iree/compiler/InputConversion/MHLO/BroadcastingToLinalgPatterns.cpp#L1)). To test the static size-1 case, we added support for the `torch.aten.unsqueeze` op and lowering for it through `linalg.tensor_expand_shape`. This involved a generalization of `MaximizeValueSemantics` able to handle it (the solution there also works for `torch.aten.flatten.using_ints` which we need for ResNet anyway) Also, a few minor additional changes: - Add `VerifyInvariantsBeforeBackendLowering` pass, which catches a large class of errors before we get to backend lowering (now that we are doing dialect conversion, the errors are way nicer if we just emit them up front rather than in the guts of a random pattern). - Minor change to RefBackend to allow `linalg.tensor_expand_shape`. Recommended review order: - e2e tests in elementwise.py - `ConvertElementwiseOp` in TorchToLinalg.cpp + elementwise.mlir test - `ConvertAtenUnsqueezeOp` in TorchToLinalg.cpp + unsqueeze.mlir test - RefineTypes.cpp + tests - MaximizeValueSemantics changes + test - VerifyInvariantsBeforeBackendLowering pass + test
2021-06-26 08:25:09 +08:00
// expected-error@+2 {{unsupported by backend lowering: tensor with unknown rank or dtype}}
Fix error message. RefineTypes doesn't handle shape refinement anymore.
2022-04-08 05:28:06 +08:00
// expected-note@+1 {{this is likely due to a missing shape transfer function in shape_lib_gen.py}}
Generalize support for elementwise ops. We plumb through e2e a fair number of interesting cases: - unary, binary, ternary elementwise ops - ops like `torch.aten.add.Tensor` that also take a scalar parameter - static size-1 broadcasting We allow the static size-1 broadcasting case, but emit a runtime error in the case of dynamic size-1 broadcasting. This seems like a sweet spot subset of things that can be lowered directly to linalg, while not being overly constraining to users. This is consistent with what IREE is doing for CHLO->Linalg lowering as well ([code](https://github.com/google/iree/blob/50bf7a87e465d2048c527bc27724edde40519b7e/iree/compiler/InputConversion/MHLO/BroadcastingToLinalgPatterns.cpp#L1)). To test the static size-1 case, we added support for the `torch.aten.unsqueeze` op and lowering for it through `linalg.tensor_expand_shape`. This involved a generalization of `MaximizeValueSemantics` able to handle it (the solution there also works for `torch.aten.flatten.using_ints` which we need for ResNet anyway) Also, a few minor additional changes: - Add `VerifyInvariantsBeforeBackendLowering` pass, which catches a large class of errors before we get to backend lowering (now that we are doing dialect conversion, the errors are way nicer if we just emit them up front rather than in the guts of a random pattern). - Minor change to RefBackend to allow `linalg.tensor_expand_shape`. Recommended review order: - e2e tests in elementwise.py - `ConvertElementwiseOp` in TorchToLinalg.cpp + elementwise.mlir test - `ConvertAtenUnsqueezeOp` in TorchToLinalg.cpp + unsqueeze.mlir test - RefineTypes.cpp + tests - MaximizeValueSemantics changes + test - VerifyInvariantsBeforeBackendLowering pass + test
2021-06-26 08:25:09 +08:00
%0 = torch.aten.mul.Tensor %arg0, %arg0 : !torch.vtensor<[],f32>, !torch.vtensor<[],f32> -> !torch.vtensor<*,f32>
return
}
// -----
mlir: bump llvm tag to 5380e3 (#856) In addition to updating the llvm-project submodule, this patch also: 1. updates shape functions and tests so that `func` and `call` operations refer to the `func` dialect 2. avoid duplicate registration of dialects
2022-05-17 03:54:35 +08:00
func.func @unknown_dtype(%arg0: !torch.vtensor<[],f32>) {
Generalize support for elementwise ops. We plumb through e2e a fair number of interesting cases: - unary, binary, ternary elementwise ops - ops like `torch.aten.add.Tensor` that also take a scalar parameter - static size-1 broadcasting We allow the static size-1 broadcasting case, but emit a runtime error in the case of dynamic size-1 broadcasting. This seems like a sweet spot subset of things that can be lowered directly to linalg, while not being overly constraining to users. This is consistent with what IREE is doing for CHLO->Linalg lowering as well ([code](https://github.com/google/iree/blob/50bf7a87e465d2048c527bc27724edde40519b7e/iree/compiler/InputConversion/MHLO/BroadcastingToLinalgPatterns.cpp#L1)). To test the static size-1 case, we added support for the `torch.aten.unsqueeze` op and lowering for it through `linalg.tensor_expand_shape`. This involved a generalization of `MaximizeValueSemantics` able to handle it (the solution there also works for `torch.aten.flatten.using_ints` which we need for ResNet anyway) Also, a few minor additional changes: - Add `VerifyInvariantsBeforeBackendLowering` pass, which catches a large class of errors before we get to backend lowering (now that we are doing dialect conversion, the errors are way nicer if we just emit them up front rather than in the guts of a random pattern). - Minor change to RefBackend to allow `linalg.tensor_expand_shape`. Recommended review order: - e2e tests in elementwise.py - `ConvertElementwiseOp` in TorchToLinalg.cpp + elementwise.mlir test - `ConvertAtenUnsqueezeOp` in TorchToLinalg.cpp + unsqueeze.mlir test - RefineTypes.cpp + tests - MaximizeValueSemantics changes + test - VerifyInvariantsBeforeBackendLowering pass + test
2021-06-26 08:25:09 +08:00
// expected-error@+2 {{unsupported by backend lowering: tensor with unknown rank or dtype}}
Fix error message. RefineTypes doesn't handle shape refinement anymore.
2022-04-08 05:28:06 +08:00
// expected-note@+1 {{this is likely due to a missing shape transfer function in shape_lib_gen.py}}
Generalize support for elementwise ops. We plumb through e2e a fair number of interesting cases: - unary, binary, ternary elementwise ops - ops like `torch.aten.add.Tensor` that also take a scalar parameter - static size-1 broadcasting We allow the static size-1 broadcasting case, but emit a runtime error in the case of dynamic size-1 broadcasting. This seems like a sweet spot subset of things that can be lowered directly to linalg, while not being overly constraining to users. This is consistent with what IREE is doing for CHLO->Linalg lowering as well ([code](https://github.com/google/iree/blob/50bf7a87e465d2048c527bc27724edde40519b7e/iree/compiler/InputConversion/MHLO/BroadcastingToLinalgPatterns.cpp#L1)). To test the static size-1 case, we added support for the `torch.aten.unsqueeze` op and lowering for it through `linalg.tensor_expand_shape`. This involved a generalization of `MaximizeValueSemantics` able to handle it (the solution there also works for `torch.aten.flatten.using_ints` which we need for ResNet anyway) Also, a few minor additional changes: - Add `VerifyInvariantsBeforeBackendLowering` pass, which catches a large class of errors before we get to backend lowering (now that we are doing dialect conversion, the errors are way nicer if we just emit them up front rather than in the guts of a random pattern). - Minor change to RefBackend to allow `linalg.tensor_expand_shape`. Recommended review order: - e2e tests in elementwise.py - `ConvertElementwiseOp` in TorchToLinalg.cpp + elementwise.mlir test - `ConvertAtenUnsqueezeOp` in TorchToLinalg.cpp + unsqueeze.mlir test - RefineTypes.cpp + tests - MaximizeValueSemantics changes + test - VerifyInvariantsBeforeBackendLowering pass + test
2021-06-26 08:25:09 +08:00
%0 = torch.aten.mul.Tensor %arg0, %arg0 : !torch.vtensor<[],f32>, !torch.vtensor<[],f32> -> !torch.vtensor<[],unk>
return
}
// -----
mlir: bump llvm tag to 5380e3 (#856) In addition to updating the llvm-project submodule, this patch also: 1. updates shape functions and tests so that `func` and `call` operations refer to the `func` dialect 2. avoid duplicate registration of dialects
2022-05-17 03:54:35 +08:00
func.func @unresolved_operator(%arg0: !torch.vtensor<[],f32>, %arg1: !torch.int) {
Generalize support for elementwise ops. We plumb through e2e a fair number of interesting cases: - unary, binary, ternary elementwise ops - ops like `torch.aten.add.Tensor` that also take a scalar parameter - static size-1 broadcasting We allow the static size-1 broadcasting case, but emit a runtime error in the case of dynamic size-1 broadcasting. This seems like a sweet spot subset of things that can be lowered directly to linalg, while not being overly constraining to users. This is consistent with what IREE is doing for CHLO->Linalg lowering as well ([code](https://github.com/google/iree/blob/50bf7a87e465d2048c527bc27724edde40519b7e/iree/compiler/InputConversion/MHLO/BroadcastingToLinalgPatterns.cpp#L1)). To test the static size-1 case, we added support for the `torch.aten.unsqueeze` op and lowering for it through `linalg.tensor_expand_shape`. This involved a generalization of `MaximizeValueSemantics` able to handle it (the solution there also works for `torch.aten.flatten.using_ints` which we need for ResNet anyway) Also, a few minor additional changes: - Add `VerifyInvariantsBeforeBackendLowering` pass, which catches a large class of errors before we get to backend lowering (now that we are doing dialect conversion, the errors are way nicer if we just emit them up front rather than in the guts of a random pattern). - Minor change to RefBackend to allow `linalg.tensor_expand_shape`. Recommended review order: - e2e tests in elementwise.py - `ConvertElementwiseOp` in TorchToLinalg.cpp + elementwise.mlir test - `ConvertAtenUnsqueezeOp` in TorchToLinalg.cpp + unsqueeze.mlir test - RefineTypes.cpp + tests - MaximizeValueSemantics changes + test - VerifyInvariantsBeforeBackendLowering pass + test
2021-06-26 08:25:09 +08:00
// expected-error@+2 {{unsupported by backend lowering: `torch.operator` op}}
// expected-note@+1 {{this is likely due to a missing op that needs to be generated by torch_ods_gen.py}}
torch.operator "aten.mul.Scalar"(%arg0, %arg1) : (!torch.vtensor<[],f32>, !torch.int) -> !torch.vtensor<[],f32>
return
}
Rework how global slot initializers work. Rather than a per-global-slot initializer region, we now have one for the whole module. For example, it might look like this: ``` torch.global_slot "private" @tensor : !torch.tensor torch.global_slot "private" @list : !torch.list<tensor> torch.global_slot.module_initializer { %0 = torch.tensor.literal(dense<0.0> : tensor<f32>) : !torch.tensor %1 = torch.prim.ListConstruct %0 : (!torch.tensor) -> !torch.list<tensor> torch.initialize.global_slots [ @tensor(%0 : !torch.tensor) @list(%1 : !torch.list<tensor>) ] } ``` This new structure allows GlobalizeObjectGraph to create the initializer in a much simpler way, avoiding the need to reason about whether different slots alias each other. Reasoning about whether slots alias each other now is the responsibility of InlineGlobalSlots, which has to do a much more complicated analysis, implemented using MLIR's dataflow analysis framework. Recommended review order: - Check out the new IR constructs in the .mlir files of various passes - Op definitions (*.td) - Changes to GlobalizeObjectGraph pass. - InlineGlobalSlots pass (~total rewrite) - Misc changes: - Moving torchMlirAdjustStaticInformation for sharing with C++ code. - EraseModuleInitializer pass To make this a bit nicer, it would be good to have a `torch.module` op with an initializer region attached. That would be more invasive though. This change has highlighted certain aspects of our project layering which are worth calling out. None of our backends can handle global slots, so we enforce that there are no global slots before backend lowering. At an earlier stage in the project, we had aspirations of transparently handling mutable global state and such, but for reasons described below, that is no longer a goal. So really global slots should be seen as a progressive lowering step as part of inlining all the IValue's in the original program (GlobalizeObjectGraph is also one such step). Over time, with insights from work like IREE-JAX, it has become clear that there isn't a reliable programming model we can compile for users where we just transparently handle mutable global state (and some other things, like lists and dictionaries). There is a need for an "outer program" that orchestrates more restricted subroutines of the kind we can handle in our compile flow here. The benefit of that is that it decouples considerations like shapes, dtypes, etc. from the program constructs used in the outer program. As long as the outer program can efficiently invoke (pipelining/async/etc.) high-performance data-parallel numerical subroutines of the kind we compile in our flow here, then there is a complete programming model. This is also consistent with the direction of upstream PyTorch which is becoming more tracing-based (which inherently loses a lot of program structure, which then has to be applied back with an "outer program" orchestrating the traced subroutines).
2022-07-14 02:45:56 +08:00
// -----
// expected-error@+1 {{unsupported by backend lowering: module initializers}}
torch.global_slot.module_initializer {
torch.initialize.global_slots [
]
}