There is currently no int16 quantization support in torch. This patch
adds a new mlir type to correspond to the missing "torch.qint16" type,
and enables lowering of quantization-related onnx ops using int16 types.
In follow-up patches, custom quantization logic for ops like
aten.matmul/aten.mm/aten.convolution may need to be revisited to allow
support for qint16. The passes in FuseQuantizedOps.cpp may also need
slight modifications.
This PR fixes the bugs for `Torch::AtenOneHotOp` by:
1) Using `Torch::kUnknownSize` as the default value for `numClasses` in
the pattern matching stage in `DecomposeAtenOneHotOp`
2) Adding `AtenIntScalarOp` to the patterns in `TorchToArith`
3) Handling both `int` and `float` types for `off` and `on` values in
`TorchOnnxToTorch` conversion
It also includes:
1) A new test in `TorchToArith/basic.mlir`, for `torch.aten.Int.Scalar`,
and
2) A new test in `decompose-complex-ops.mlir`, for `torch.aten.one_hot`
**Dependencies**
This PR is dependent on #3334.
This change enables more customization with operand quantization, and
generalizes the patterns QuantizeOperands and QuantizeTransposeOperands
to QuantizeOperandsPastCommutingOps.
This allows for passing quantization through operations which are
functionally unaffected by quantization, such as view-like ops. The
purpose of this change is to address a myriad of quantization issues
seen in quantized onnx models that have some reshape-like operations
sandwiched in between a dequant and something like a matmul (whose other
operand is immediately quantizable).
While playing with TorchDynamo on ResNet18. I notice following issues:
- `prims.convert_element_type` can’t be canonicalized even if the input
and the output share the same type
- `aten.max_pool2d_with_indices` is always used instead of
`aten.max_pool2d`, even if the second returned output (indices) has no
user
This PR fixes above issues by adding a folder to the
PrimsConvertElementTypeOp and a canonicalizer to the
AtenMaxPool2dWithIndicesOp
Lit test:
`cmake --build build --target check-torch-mlir-all`
---------
Co-authored-by: Ze Zhang <ze.zhang@getcruise.com>
This is part 1 of ~3, formatting all miscellaneous text files and CPP files matched by a first run of pre-commit. These tend to be low change-traffic and are likely not disruptive.
Subsequent patches will format Python files and remaining CPP files.
Previously, it could only handle the situations where outputsize == (1,
1) or outputsize == (input_H, input_W). Now it supports all situations
where input_H % output_H== 0 && input_W % output_W == 0
When lowering `torch.aten.convolution`, it is expected that the
'transposed' argument is a torch.constant operation. In some cases, the
argument was a `from_i1` operation converting an `arith.constant`
operation into a torch.bool. This is not wrong semantically, but instead
of generalizing the legality of the `torch.aten.convolution` op, we
canonicalize `arith.constant` ops followed by `from_i1` ops to
`torch.bool` ops.
For example:
```
//===-------------------------------------------===//
Legalizing operation : 'torch.aten.convolution'(0x124705b90) {
%33 = "torch.aten.convolution"(%arg0, %20, %21, %31, %29, %30, %19, %32, %0) : (!torch.vtensor<[1,1,28,28],f32>, !torch.vtensor<[10,1,5,5],f32>, !torch.vtensor<[10],f32>, !torch.list<int>, !torch.list<int>, !torch.list<int>, !torch.bool, !torch.list<int>, !torch.int) -> !torch.vtensor<[1,10,24,24],f32>
* Fold {
} -> FAILURE : unable to fold
* Pattern : 'torch.aten.convolution -> ()' {
** Failure : unimplemented: only constant transposed supported. <-- Resolved by this PR
} -> FAILURE : pattern failed to match
* Pattern : 'torch.aten.convolution -> ()' {
** Failure : not a supported Scalar to Tensor like op
} -> FAILURE : pattern failed to match
* Pattern : 'torch.aten.convolution -> ()' {
** Failure : not a supported elementwise op
} -> FAILURE : pattern failed to match
* Pattern : 'torch.aten.convolution -> ()' {
** Failure : not a supported reduce op
} -> FAILURE : pattern failed to match
} -> FAILURE : no matched legalization pattern
//===-------------------------------------------===//
<stdin>:21:11: error: failed to legalize operation 'torch.aten.convolution' that was explicitly marked illegal
%17 = torch.operator "onnx.Conv"(%arg0, %0, %1) {torch.onnx.dilations = [1 : si64, 1 : si64], torch.onnx.group = 1 : si64, torch.onnx.kernel_shape = [5 : si64, 5 : si64], torch.onnx.pads = [0 : si64, 0 : si64, 0 : si64, 0 : si64], torch.onnx.strides = [1 : si64, 1 : si64]} : (!torch.vtensor<[1,1,28,28],f32>, !torch.vtensor<[10,1,5,5],f32>, !torch.vtensor<[10],f32>) -> !torch.vtensor<[1,10,24,24],f32>
^
<stdin>:21:11: note: see current operation: %33 = "torch.aten.convolution"(%arg0, %20, %21, %31, %29, %30, %19, %32, %0) : (!torch.vtensor<[1,1,28,28],f32>, !torch.vtensor<[10,1,5,5],f32>, !torch.vtensor<[10],f32>, !torch.list<int>, !torch.list<int>, !torch.list<int>, !torch.bool, !torch.list<int>, !torch.int) -> !torch.vtensor<[1,10,24,24],f32>
```
Additionally, we require the canonicalization of `to_i1` operating on a
torch.constant bool to an `arith.constant ... : i1` for the e2e tests to
pass successfully.
Reshaping tensors depend on directly matching individual dimensions to
their corresponding dim in the `torch.view` reshape dimensions. This
involves decoupling dynamic dimensions from their static counterparts
and support cleanup / canonicalization.
This folds small version of the tensor-scalar comparison operators as
they are commonly used for shape computations. This includes le, lt, ge,
gt, eq, and ne.
A handful of operations are commonly used in shape calculations (slice,
concat, broadcast). Added these additional folders to better propagate
simple shape computations.
A bunch of small fixes are interlinked and trigger crashes if not
addressed as a group. This includes:
- aten view when expand from a rank-0 tensor
- slice folder with negative indices
- `aten._shape_as_tensor` folder on a rank-0 tensor
- `aten.cat` of a tensor with a length-0 tensor
We collapsed and broadcasted scatter indices to a single element
version. We should instead upport `tm_tensor.scatter`s support for
multiple indices and the implicitly broadcasted behavior. This avoids
the serialization and materializing a needlessly large indices tensor.
This enables better re-use in downstreams which use different func
implementations and should have no impact on those that don't except in
opt pipelines if using the old form. With interfaces, explicit pipelines
via `--pass-pipeline=` must be used.
Simple folder for limited size aten tensor operations. This is primarily
useful for shape computation folding as they unfortunately can use
`aten` operators. Add, sub, mul are common examples of these folders.
Some operations include a backend matcher for specialized operations. We
map these back to generics so they appropriately match to the high
performance versions. This is done for the attention operation.
Fixes https://github.com/llvm/torch-mlir/issues/2866
Some backends / downstream projects expect that a "fully converted"
program has no remaining ops or attributes from the original dialect(s).
Folds aten::index_select ops under the following conditions:
1. If the input and output are the same shape, the indexing operation is
a NOP, so just return the input.
2. If the input has shape <1x1x...xNx...x1> (all 1's except for one
dim), and the output shape is <1x1x...x1> (all 1's), then there is a
single index, so extract the single element value and return a tensor
with that value.
---------
Co-authored-by: Dave Liddell <dliddell@xilinx.com>
If a tensor is initialized by a list with a single constant integer,
this folder turns it into a torch.vtensor.literal
---------
Co-authored-by: Dave Liddell <dliddell@xilinx.com>
Leaning on the QDQ functionality in torch we can support the QLinearConv
operation by piggybacking through `torch.Convolution`. This includes
some changes such as allowing the `onnx` rewriter to run recursively.
Doing so allows `QLinearConv` to decopmose to `onnx.Convolution` which
is then lowered to `torch`.
So that the CumSum Op in OPT can get the constant that it requires to be lowered to TMTensor
---------
Co-authored-by: Rob Suderman <rob.suderman@gmail.com>
Co-authored-by: Xida Ren <xida.ren.dev@gmail.com>
Linalg has quantized specific operations. We can lower to these
operations when there is a known zeropoint and scale operations. This
allows the `convolution` to occur with lower bitwidth's, improving the
overall performance.
We were seeing some assertion failures after some checks around folders
were tightened up in LLVM:
https://github.com/llvm/llvm-project/pull/75887 . This PR essentially
moves the logic that used to be applied at the LLVM level into the
folder, which seems to be the suggested fix.
I'm not sure if the IR that caused issues for us _should_ be valid?
```
%1 = torch.aten.detach %arg0 : !torch.tensor<[1],f32> -> !torch.tensor
```
A better fix might be to create a verifier ensuring the result of
`aten.detach` has the same type as its operand.
---------
Co-authored-by: aaron-stgeorge <aaron.stgeorge@getcruise.com>
This adds an encoding field to the torch type, using the interfaces for
printing, parsing, and verification. Note that although this change
prepares adding sparsity to the torch type (as illustrated by the round
trip and invalid tests), nothing in this change depends on the actual
contents of the encoding field!
This includes custom op matching for decomposed operations and fusing
dequantization into dense operations. As a validation we compare
to the dequant+mm torch implementation.
This lifts the core of the jit_ir_importer and ltc out of the pt1
project, making them peers to it. As a side-effect of this layering, now
the "MLIR bits" (dialects, etc) are not commingled with the various
parts of the pt1 project, allowing pt1 and ltc to overlay cleanly onto a
more fundamental "just MLIR" Python core. Prior to this, the Python
namespace was polluted to the point that this could not happen.
That "just MLIR" Python core will be introduced in a followup, which
will create the space to upstream the FX and ONNX pure Python importers.
This primary non-NFC change to the API is:
* `torch_mlir.dialects.torch.importer.jit_ir` ->
`torch_mlir.jit_ir_importer`.
The rest is source code layering so that we can make the pt1 project
optional without losing the other features.
Progress on #2546.
- adds support for an optional verifier to the generated torch op
tablegen (GeneratedTorchOps.td)
- uses the above to add a verifier for the torch permute op.
Motivation: I hit an unclear error from linalg while developing a
decomposition pass for pixel_shuffle. The error would have been clearer
if the problem had been detected earlier in the invalid aten.permute op.
Testing: new tests added. To run added tests, from the base directory
run
```
./build/bin/llvm-lit test/Dialect/Torch/invalid.mlir
```
This is a first step towards the structure we discussed here:
https://gist.github.com/stellaraccident/931b068aaf7fa56f34069426740ebf20
There are two primary goals:
1. Separate the core project (C++ dialects and conversions) from the
hard PyTorch dependencies. We move all such things into projects/pt1 as
a starting point since they are presently entangled with PT1-era APIs.
Additional work can be done to disentangle components from that
(specifically LTC is identified as likely ultimately living in a
`projects/ltc`).
2. Create space for native PyTorch2 Dynamo-based infra to be upstreamed
without needing to co-exist with the original TorchScript path.
Very little changes in this path with respect to build layering or
options. These can be updated in a followup without commingling
directory structure changes.
This also takes steps toward a couple of other layering enhancements:
* Removes the llvm-external-projects/torch-mlir-dialects sub-project,
collapsing it into the main tree.
* Audits and fixes up the core C++ build to account for issues found
while moving things. This is just an opportunistic pass through but
roughly ~halves the number of build actions for the project from the
high 4000's to the low 2000's.
It deviates from the discussed plan by having a `projects/` tree instead
of `compat/`. As I was thinking about it, this will better accommodate
the follow-on code movement.
Once things are roughly in place and the CI passing, followups will
focus on more in-situ fixes and cleanups.
zjgarvey
Sambhav Jain
Angel Zhang
Aaron St George
Benoit Jacob
Vivek Khandelwal
Xida Ren (Cedar)
Ze Zhang
Yuanqiang Liu
Stella Laurenzo
Xinyu Yang
Thomas Dietert
Rob Suderman
Scott Todd
Dave Liddell
Xida Ren (Cedar)
Aart Bik
Han-Chung Wang
Zhekun(Josh) Zhang
James Newling