The new cases added for quantized matmuls are:
1. vec-vec
2. vec-mat
3. mat-vec
each of which are now lowered to expand(s), quantized_matmul, and
collapse.
1. onnx.MatMulInteger now converts to aten.matmul instead of aten.mm
2. aten.matmul, for ranks >=2, now allows quantized inputs and will
lower to linalg::quantized_matmul or linalg::quantized_batch_matmul.
3. added AtenMatmulOp to the FuseQuantizeOps rewrite patters
QuantizeOperands, QuantizeTransposedOperands, and QuantizeAccumulator
4. added several tests, including some to test AtenMmOp with varying
quantization signed-ness.
5. a quantized matmul mat-vec test is added to verify the failure to
lower to linalg; cleaned of out-of-date code related to common
torch-mlir lowering xfails.
6. in debugging a real model with quantized matmuls, I found a bug on
the scalarize-shapes pass which resulted from the aten.full op folder
returning an incompatible result type. This is fixed by the small change
here to
[lib/Dialect/Torch/IR/TorchOps.cpp](https://github.com/llvm/torch-mlir/compare/main...zjgarvey:torch-mlir:MatMulIntegerFix?expand=1#diff-dc8ed165c207918e606490eee3984b1ad51d7034e6aac36fc046bf47f6f03f4f).
- Added linalg lowering for `AtenFloorDivideScalarOp`
- Needed `AtenDivScalarModeOp` for the decomp.
- Added linalg lowering for `AtenDivScalarModeOp`
- Moved linalg payload logic to `createDivModePayload()` since the logic
was nearly identical for both `AtenDivScalarModeOp` and
`AtenDivTensorModeOp`. Just a template function
- Added `AtenDivScalarModeOp` lowering for stablehlo
Pytorch's
[`torch.floor_divide()`](https://pytorch.org/docs/stable/generated/torch.floor_divide.html)
in a previous version (for a reason unknown to me) preformed a
truncation instead of "floor". The already implemented op
`AtenFloorDivideTensorOp` was done before this change. However, this
wasn't caught because our testcases only tested positive floor division.
I changed this to floor as well as adding a few test cases.
If there is only a single value scattered there can be an implicit batch
dimension. This includes a check for the implicit batch dimension when
reshaping the update tensor. It includes an e2e test to verify
correctness.
Fix the case PrimListUnpackOp's result num is not equal to PrimList
length.
See the following example:
```python
def forward(self, x):
if len(x.shape) == 5:
b0, t, c0, h0, w0 = x.shape
b, c, h, w = torch.mul(b0, t), c0, h0, w0
else:
b1, c1, h1, w1 = x.shape
b, c, h, w = b1, c1, h1, w1
res = torch.reshape(x, [b, c, h, w])
return res
```
Without this fix, the following error message will occur：
```
/root/torch-mlir/externals/llvm-project/mlir/lib/IR/PatternMatch.cpp:118: virtual void mlir::RewriterBase::replaceOp(mlir::Operation *, mlir::ValueRange): Assertion `op->getNumResults() == newValues.size() && "incorrect # of replacement values"' failed.
```
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
1. Changes the linalg lowering for dequantization ops to always sign
cast to float to prevent misrepresenting uint32 overflow on subtraction
with zero point.
2. Adds a basic quantized model test which only quantizes and
dequantizes and now passes with these changes in linalg and onnx
configs.
3. Changes the aten.mm lowering to allow mismatched quantized types.
4. If a quantized matmul arg is uint8, we shift by 128 to faithfully
represent the quantization as a signed i8 quantization. This worked fine
in the AtenMmOp lowering, but I'd be happy to move it to a rewrite in
FuseQuantizedOps.cpp instead if that seems more appropriate.
With the changes 3 and 4, the QuantizedMLP_basic and
QuantizedSingleLayer_basic e2e tests now passes with the onnx config.
…ute_reshape_shape
as that `aten.view` support at most one `-1` in dim list. The original
calculation of `numel` is wrong when there is a `-1` in dim list.
This PR only performs a lit test. In lieu of an e2e test, https://github.com/nod-ai/SHARK-TestSuite/pull/142 makede sure that the lowering works & the numbers check out.
Co-authored-by: Xida Ren <xida.ren.dev@gmail.com>
* as that `TorchMLIRTorchConversionPasses` missing dependencies of
`TorchMLIRTorchToStablehlo` and `TorchMLIRTorchToTensor`.
* use `TorchMLIRConversionPasses` instead of scattered targets.
Squeezes can be ambiguous without the output shape information. For
instance (1, 1, 256) squeezed can be either (1, 256) or (256). We need
to check the resulting shape to know what the shape should look like.
Shapes can be processed as tensors to represent the set of dimensions.
As reshapes take a list of scalars this can result in a single dynamic
dimension blocking the adjacent static dimensions.
This pass attempts to de-couple tensor computations related to shapes
and propagate values to better support lowering scalar tensor
computations.
This commit also cleans up the OnnxToTorch lowering for the ReduceMean
op and adds the support for handling edge cases.
Signed-Off By: Vivek Khandelwal vivekkhandelwal1424@gmail.com
The `convertTensorToElementType` function expects it's argument to have
a valid tensor type that is not `Torch::NoneType`. This PR checks that
the bias tensor is not of type `Torch::NoneType` before calling
`convertTensorToElementType` on the bias tensor argument in the
`matchAndRewrite` member function of the `ConvertAtenConvolutionOp`
class.
See the related issues here:
[SHARK-Turbine#556](https://github.com/nod-ai/SHARK-Turbine/issues/556)
1. Adds uint8 casting to onnx.Cast op
2. Fixes an issue with onnx.DequantizeLinear when the scale comes with
shape [1].
3. Adds support for unsigned types in an AtenItemOp folder
4. Adds a simpler quantized model for easier debugging
5. Adds a fusion pass to convert [quant -> dequant -> transpose -> mm]
patterns to [transpose -> quant -> mm].
6. Moved some xfails that are still not passing, but for different
reasons than onnx.cast failures.
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.
Now there no lowing for `aten.Int.bool` in `convert-torch-to-arith`
pass. this PR add this support.
Below is the UT.
```
func.func @torch.aten.Int.bool(%arg0: !torch.bool) -> !torch.int {
%0 = torch.aten.Int.bool %arg0 : !torch.bool -> !torch.int
return %0 : !torch.int
}
```
Fix bug of DecomposeAtenSelectIntOp. Because it may use resultTy when
resultTy has not been inferred.
```
auto resultTy = op.getType().cast<BaseTensorType>();
if (sliceTy.getSizes().size() == resultTy.getSizes().size()) {
rewriter.replaceOp(op, slice);
return success();
}
```
So I add restriction.
Two e2e tests (AdaptiveAveragePool1/2dUnitOutputSizeDynamic) were
failing due to numerics. This was as a result of passing -1 as the
kernel size in the lowering for the corresponding onnx op
GlobalAveragePool.
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 commit adds the OnnxToTorch lowering for the Mish, Softplus,
HardSwish, Trilu, ThresholdedRelu op
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
The previous conversions for AtenAdaptiveAvgPool1dOp and
AtenAdaptiveMaxPool2dOp are refactored into a general templated
conversion that works for all of the AtenAdaptive...PoolNdOp's.
New support is added for the following ops:
1. AtenAdaptiveMaxPool1d
2. AtenAdaptiveMaxPool3d
3. AtenAdaptiveAvgPool3d
Support is also provided for passing inputs without batch dimensions.
For example, applying adaptive_avg_pool2d to an input tensor of rank 3.
After [pytorch #118162](https://github.com/pytorch/pytorch/pull/118162)
gets down to torch-mlir, I'll add a test for AdaptiveMaxPool1d with
return_indices (which will pass with that upstream fix).
---------
Co-authored-by: James Newling <james.newling@gmail.com>
This adds support for converting DynamicQuantizeLinear from torch-onnx
to torch.
I could not get an e2e test to pass, since there seems to be some issues
with uint8 casting somewhere lower in the pipeline. For example
compiling with IREE for llvm-cpu, I would get either the correct zero
point (if zp < 128) or the correct zero-point minus 256 (if zp >= 128).
The output tensor seems to always return a tensor of zeros, which also
occurs when running uint8 examples through QuantizeLinear.
Edit: the first problem can be resolved by casting the output back to
uint8 on output, the second problem is resolved with PR #3018
Added support for dynamic shapes in `flattenusingints` op in tosa
dialect. Due to this some Argmax tests pass
This PR fixes this issue https://github.com/llvm/torch-mlir/issues/3004
The following tests pass after this PR
```
1. "ArgmaxIntModule_basic"
2. "ArgmaxIntModule_multiple_maxs"
3. "ArgmaxModule_basic"
```
The only difference between version 7 and newer versions is support for
different data types. We should allow this pattern to match as early as
7. Earlier versions have a more manual broadcast specification through
attributes, so I did not include those versions.
See: [onnx.Div
docs](https://onnx.ai/onnx/operators/onnx__Div.html#l-onnx-doc-divl)
Reduce mean lowerings did not succesfully lower to `linalg` via torched.
There were two separate paths that could be consolidated to a single
simpler pass. This resulted in a significant improvement in test
coverage.
If the broadcast shape is length-1 at a dim while `?` in the input dim
then we need to broadcast to the dynamic dim. This is equivalent to
taking a max of two dimensions.
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.
The current padding operation was not functional for dynamic shapes.
Updated and enabled tests so that onnx.pad tests pass.
Work TBD for reflection padding.
We can support `onnx.Size` by requesing the size of each dimensions and
taking the product of the results, then packing it into a tensor.
---------
Co-authored-by: Scott Todd <scott.todd0@gmail.com>
This mostly copy-pastes the reduce minimum implementation to reduce max
to improve test coverage. We also improve the aten lowering for min/max
dim for unsigned types.
The addition of an e2e test is actually provided in the Shark-Testsuite.
This adds 2 test cases for the gridsampler e2e test.
Also as intended there were some items found which needed correction, so
the Gridsampler op has also a change.
Current implementation depends on using `aten.view` which has issues
inferring tensor collapse/expand operations during the lowering to
`linalg`. Using flatten and unsqueeze better infers what the later
reshape behavior.
Add e2d support for `aten.linalg_norm` by decompose it to
`aten.linalg_vector_norm`.
Lowering to `aten.linalg_matrix_norm` is still unsupported.
To Test:
`python -m e2e_testing.main -v`
---------
Co-authored-by: Ze Zhang <ze.zhang@getcruise.com>
`getRawBuffer` expects a densely packed vector of `i1` values however
`onnx` does not densely pack the values. Include code to handle the
packing / unpacking.
A handful of operations are commonly used in shape calculations (slice,
concat, broadcast). Added these additional folders to better propagate
simple shape computations.
Existing lowering via aten.view does not work as well for dynamic shapes
as the lowering to tensor.expand must re-infer dynamic shape matching.
Better to directly lower.
This is the lowering of gridsampler from onnx to torch using our prior
implementation of AtenGridSamplerOp.
Here are several checks for cornercases implemented. We may decide to
have part of these checks in AtenGridSamplerOp instead of the onnx
lowering portion.
Finish supporting importing the vast majority of `onnx` operations. This
includes:
- region support
- region value inherentance
- `torch.string` support
- `torch.list` support
- `torch.optional` support
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
The decomposition only suports a NCHW lowering however the operation can
support arbitrary spatial dimensions. Updated the lowering to better
support spatial dimensions.
zjgarvey
Vinayak Dev
Xinyu Yang
IanWood1
jinchen
Xinan Jiang(姜曦楠)
Rob Suderman
penguin_wwy
Yuanqiang Liu
Xida Ren (Cedar)
Vivek Khandelwal
Thomas Dietert
ptrifunovic98
Gaurav Shukla
Jiawei Wu
Xida Ren (Cedar)
schnkmwt
Abhishek-TyRnT
Pavani Chowdary
Nithin Meganathan
aldesilv
Andreas Falkenberg
Scott Todd
Ze Zhang
Chi_Liu
mmakevic