llvm
/
torch-mlir
mirror of https://github.com/llvm/torch-mlir
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
3,109 Commits
47 Branches
1195 Tags
91 MiB
Commit Graph

3109 Commits (c71728b18217de0eb56afbb0cb6321715d1b79d3)
 

Author SHA1 Message Date
Peiming Liu ba16bad8c7
[torch-mlir] bump stablehlo/llvm version (#3471) 
Update to llvm/llvm-project@5207632f86
Update to openxla/stablehlo@d41390c3a7
 2024-06-18 16:59:53 -07:00
Vivek Khandelwal 822d763308
[ONNX] Add OnnxToTorch lowering for Optional, OptionalGetElement op (#3467) 
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
 2024-06-18 19:40:18 +05:30
Branko Trifkovic 676fa8cc09
Implement lowering of torch.aten.renorm (#3388) 
Closes
[nod-ai/SHARK-Turbine/issues/689](https://github.com/nod-ai/SHARK-Turbine/issues/689)

---------

Co-authored-by: Branko Trifkovic <branko.trifkovic@syrmia.com>
 2024-06-17 10:40:57 -07:00
Umang Yadav 59bade3376
[ONNX] Add missing "Abs" in GlobalLpPool (#3460) 
Taking `abs` is required to mimic same logic as onnx/onnxruntime. 
Without `abs`, it wouldn't produce correct results for negative values. 

Reference code : 

f5b6f6dc26/onnxruntime/core/providers/cpu/nn/pool_functors.h (L604)


375c161c67/onnx/reference/ops/op_lp_pool.py (L31)
 2024-06-17 11:17:16 +05:30
ptrifunovic98 4555629246
Implement lowering of torch.aten.kthvalue (#3360) 
Closes
[nod-ai/SHARK-Turbine#620](https://github.com/nod-ai/SHARK-Turbine/issues/620)
 2024-06-15 11:18:39 +05:30
Andrea 🦈 51902ec2dc
Create MLIR functions for ONNX operators that are functions (#3409) 
Resolves #3384.

Many ONNX operators are defined by functions and therefore could be
expanded into simpler ONNX operations during importing, avoiding the
need for tools downstream to support these operators directly.

This commit adds this capability to onnx_importer.py. When importing a
node, the schema for the node's operator is retrieved. If the schema
provides a function for the operator, a specialized version for the
node's types and attributes will be created and imported as an MLIR
function with private visibility. An MLIR function call will then be
emitted, instead of a normal operator node. Caching is used to avoid
generating redundant functions within the same module.

In order to avoid a disruptive change to the importer output for a
large number of operators that already have TorchOnnxToTorch support,
an allowlist strategy is used by default. With this commit, only one
operator is allowlisted for expansion, MeanVarianceNormalization.
However, many other operators can be correctly expanded by the current
code, so hopefully the allowlist can be gradually extended. It is
possible to disable the allowlist in the configuration, in which case
all functions are expanded (useful for testing).

Tools downstream of the importer may now need to do inlining when
consuming the output of the importer, e.g.:

  cat imported.mlir | torch-mlir-opt --inline --convert-onnx-to-torch

Explanations for subtle code changes:

- Looking up the correct schema and function for an operator requires
  knowing the opset version. NodeImporter retrieves this from the
  opset imports on the ModelProto retained by the GraphInfo. Previously,
  the model_proto field on GraphInfo was None when importing a subgraph
  in import_regions, but this conflicts with the new need for opset
  version info. Since the apparent purpose of setting it to None was to
  control how GraphInfo generates its input map, a new flag is added to
  GraphInfo (is_subgraph) to control this behavior, so that the actual
  ModelProto can now be provided without breaking this. This also turned
  out to be useful for getting the Config via ModelInfo via GraphInfo.
- Some operators' functions are context-dependent, which means the
  function definition depends on the types of the inputs. Therefore node
  importing now needs to look up the types of a node's inputs, not just
  its outputs as was the case previously. Consequently the operand to
  find_type_proto_for_name() may now be a graph input or initializer in
  some cases, so it has to be updated.
 2024-06-14 10:11:26 -07:00
Manupa Karunaratne d2b663ece7
Add onnx op LRN lowering (#3432) 
This commit adds support for lowering
Onnx LRN op to aten.
 2024-06-14 16:44:43 +00:00
Arham Khan 09c988046c
[ONNX] Add OnnxToTorch lowering for Onnx.NegativeLogLikelihoodLoss Op (#3380) 
This implements the Onnx.NegativeLogLikelihoodLoss op using the
signature provided
[here](https://onnx.ai/onnx/operators/onnx__NegativeLogLikelihoodLoss.html)
by replacing it with a `NLLLossForward` op.

Additionally, I included a helper function `get_loss_reduction_enum` to
convert from a string `reduction` parameter to the corresponding
intended integer value since this is an operation that will be reused
for any loss function module. This differs from `get_reduction_enum` in
`TorchUpstream.cpp` which handles the `reduce` parameter from
`scatter_reduce` type operations.
 2024-06-14 22:01:11 +05:30
Vivek Khandelwal 2ea2bc3948
[ONNX] Add OnnxToTorch Lowering for GroupNormalization op (#3458) 
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
 2024-06-14 16:18:53 +00:00
Umang Yadav 04c6479350
[ONNX] Add onnx parser for LpPool operator (#3449) 
Similar to https://github.com/llvm/torch-mlir/pull/3435

Solves https://github.com/nod-ai/SHARK-Turbine/issues/728
 2024-06-14 21:41:18 +05:30
Xinyu Yang 6f94c7b0aa
[Torch] Add support for Meshgrid (#3462) 2024-06-14 23:59:08 +08:00
Wu Yuan a02e14e971
[FxImporter] Add aten._scaled_dot_product_flash_attention_for_cpu to default decomposition table (#3456) 2024-06-14 10:52:09 +08:00
Phaneesh Barwaria 919b599ebe
onnx.MaxPool add atenMaxPool1d lowering support (#3452) 
fixes #3422
 2024-06-13 15:37:11 +05:30
Vinayak Dev 39d882f7c9
[torch] Add OnnxToTorch lowering for the Col2Im op (#3424) 
Adds OnnxToTorch lowering for the `onnx.Col2Im` op.
 2024-06-13 08:42:06 +00:00
Surya Jasper de7f058a0e
[MLIR][ONNX] Add OnnxToTorch support for MaxRoiPool Op (#3395) 
This PR adds OnnxToTorch support for MaxRoiPool op
 2024-06-13 10:46:14 +05:30
Umang Yadav 9b76a2e3eb
[ONNX] add onnx lowering for global lp pool operator (#3435) 
Solves https://github.com/nod-ai/SHARK-Turbine/issues/727

Uses AvgPool to implement GlobalLpPool similar to this
https://github.com/onnx/onnx/blob/main/onnx/reference/ops/op_lp_pool.py

cc: @vivekkhandelwal1
 2024-06-13 10:37:08 +05:30
Lei Zhang 77d7f64472
Update to llvm/llvm-proect@27ac46e6be (2024-6-12) (#3454) 
This would require to bump stablehlo at the same time.
 2024-06-12 19:34:01 -07:00
Chi_Liu ae6f5e8251
[ONNX] Fix AveragePool attributes support (#3235) 
Issues was found here https://github.com/nod-ai/SHARK-Turbine/issues/643
    - [ONNX] Fix padding attributes for onnx.AveragePool
    - [Linalg] Add countIncludePad false support for AtenAvgPool1/2dOp
    - [Linalg] Add an avg_pool2d countIncludePad False e2e tests
    - [Linalg] Fix conflict with AtenAvgPool3dOp
    - [Linalg] Fix e2e crash with AtenAvgPool1dOp
    - [Linalg] Add dynamic dim support for AtenAvgPool2dOp
    - [Linalg] Fix AvgPool2dDivisorOverrideModule crash
 2024-06-12 12:16:43 -07:00
Suraj Sudhir 41d04a8995
[onnx] Resize supports default-valued attributes (#3450) 
Handles onnx exporters emitting default-valued attributes.

Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
 2024-06-12 09:23:42 -07:00
zjgarvey c0eb6d89c0
[ONNX] add some args to the onnx importer to assist shape_inference (#3445) 
Adds the following arguments:
- "--clear-domain": enabling this flag (default False) will delete the
domain attribute from each node in the onnx model before importing.
Shape inference does not seem to work for onnx ops in custom domains. In
the rare case when these ops have a corresponding counterpart in base
onnx, enabling this flag might allow shape inference to work properly.
- "--opset-version": allows setting the opset version manually. This
will cause the importer to attempt to update the opset_version of the
onnx model before importing. Newer opset versions sometimes have more
robust shape inference patterns.
 2024-06-12 10:55:14 -05:00
zjgarvey de28c8540b
[ONNX] add int16 quantization support (#3446) 
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.
 2024-06-12 10:37:22 +05:30
zjgarvey 7cd3368b20
[ONNX] Fix resize ceil numerics and add half_pixel_symmetric support (#3443) 
This patch fixes several failing tests in our [external test
suite](https://github.com/nod-ai/SHARK-TestSuite/tree/main/iree_tests/onnx/node/generated),
and addresses some of the issues discussed in #3420
 2024-06-11 22:35:50 -05:00
Matthias Gehre e07a0bfc54
onnx.resize: Add support for coordTfMode "half_pixel" (#3441) 
half_pixel is also the default mode used by ONNX, see
https://onnx.ai/onnx/operators/onnx__Resize.html
 2024-06-10 20:59:29 +02:00
Aart Bik d77bab37d1
[torch-mlir][sparse] re-enable all sparse tests (#3444) 
this fixes the following issue:

https://github.com/llvm/torch-mlir/issues/3418
 2024-06-10 11:19:32 -07:00
Sambhav Jain 7e0e23c668
Test custom op import with symbolic shapes (#3431) 
Tests the basic constructs of registering a custom op and its abstract
implementations (with FakeTensors) in python, going through TorchDynamo
export, followed by importing the shape expressions in the Torch
dialect.

Also fixes the importer were previously the symbolic bind op insertion
was not gated in one place.
 2024-06-09 00:32:49 -07:00
Vivek Khandelwal 5bc626465b
[ONNX] Lower Onnx.Concat lowering version (#3437) 
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
 2024-06-09 12:07:20 +05:30
Vivek Khandelwal d35b6b412a
[ONNX] Add OnnxToTorch Lowering for Sequence Ops (#3425) 
This commit adds the lowering for SequenceAt, SequenceEmpty,
SequenceInsert, SequenceErase op

Signed-Off By: Vivek Khandelwal<vivekkhandelwal1424@gmail.com>
 2024-06-08 09:58:11 +05:30
Yuanqiang Liu 689efc8917
[Torch] fix toBuiltinTensor() (#3415) 
* Let `toBuiltinTensor()` reflects the original dtype of
`!torch.vtensor`.
* Backend handles dtype conversion themselves.
 2024-06-08 09:36:32 +08:00
Rob Suderman 75af64fc12
[torch] Add support for f8 types for linalg conversion (#3436) 
Linalg conversion requires mapping for f8 types
 2024-06-07 13:59:38 -07:00
Rob Suderman 7f188eb824
Add f8 types to fx importer (#3434) 
Missing types for tracing float8 types.
 2024-06-07 13:58:18 -07:00
aldesilv f794582b18
add resize nearest mode round_prefer_floor, round_prefer_ceil, ceil (#3421) 2024-06-07 14:04:11 -05:00
Vivek Khandelwal 1a9c0a35a9
[Onnx] Add Onnx->Torch lowering for Onnx.Shrink Op (#3385) 
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
 2024-06-07 22:47:27 +05:30
Suraj Sudhir 1c2778dd56
[ONNX] Conv op adds support for asymmetric padding. (#3426) 
Supports asymmetric padding by performing a torch.nn.functional.pad on
the input before performing the convolution.

Signed-off-by: Suraj Sudhir <suraj.sudhir@arm.com>
 2024-06-07 09:54:39 -07:00
Sambhav Jain 94838ca44d
[Bazel] Add BuiltinDialectTdFiles dep to MLIRTorchOpsIncGen (#3430) 
This is needed after https://github.com/llvm/torch-mlir/pull/3372.
 2024-06-07 05:02:17 -07:00
Sambhav Jain d0a818a03e
Representing Symbolic Shape Expressions in Torch Dialect (#3372) 
Torch Dialect with symbolic shape expressions:
```ll
module {                                                                                                                                                                                                     
  func.func @main(%arg0: !torch.vtensor<[?,?,3],f32>, %arg1: !torch.vtensor<[?,?,3],f32>) -> !torch.vtensor<[?,?,3],f32> {                                                                                   
    %0 = torch.symbolic_int "s0" {min_val = 5, max_val = 10} : !torch.int                                                                                                                                    
    %1 = torch.symbolic_int "s1" {min_val = 0, max_val = 100} : !torch.int                                                                                                                                   
    %2 = torch.symbolic_int "s3" {min_val = 0, max_val = 50} : !torch.int                                                                                                                                    
    
    torch.bind_symbolic_shape %arg0, [%0, %1], #affine_map<()[s0, s1] -> (s0, s1, 3)> : !torch.vtensor<[?,?,3],f32>                                                                                          
    torch.bind_symbolic_shape %arg1, [%0, %2], #affine_map<()[s0, s1] -> (s0, s1, 3)> : !torch.vtensor<[?,?,3],f32>                                                                                          
    
    %3 = torch.aten.tanh %arg0 : !torch.vtensor<[?,?,3],f32> -> !torch.vtensor<[?,?,3],f32>                                                                                                                  
    torch.bind_symbolic_shape %3, [%0, %1], #affine_map<()[s0, s1] -> (s0, s1, 3)> : !torch.vtensor<[?,?,3],f32>                                                                                             
    
    %4 = torch.aten.sigmoid %arg1 : !torch.vtensor<[?,?,3],f32> -> !torch.vtensor<[?,?,3],f32>                                                                                                               
    torch.bind_symbolic_shape %4, [%0, %2], #affine_map<()[s0, s1] -> (s0, s1, 3)> : !torch.vtensor<[?,?,3],f32>                                                                                             
    
    %5 = torch.prim.ListConstruct %3, %3, %4 : (!torch.vtensor<[?,?,3],f32>, !torch.vtensor<[?,?,3],f32>, !torch.vtensor<[?,?,3],f32>) -> !torch.list<vtensor>                                               
    %int1 = torch.constant.int 1                                                                                                                                                                             
    %6 = torch.aten.cat %5, %int1 : !torch.list<vtensor>, !torch.int -> !torch.vtensor<[?,?,3],f32>                                                                                                          
    torch.bind_symbolic_shape %6, [%0, %1, %2], #affine_map<()[s0, s1, s2] -> (s0, s1 * 2 + s2, 3)> : !torch.vtensor<[?,?,3],f32>                                                                            
    
    return %6 : !torch.vtensor<[?,?,3],f32>                                                                                                                                                                  
  }                                                                                                                                                                                                          
}              
```

For reference, this is the TorchDynamo exported program with symbolic
shape expressions that the above Torch dialect program is imported from:
```py
ExportedProgram:                                                                                                                                                                                             
    class GraphModule(torch.nn.Module):                                                                                                                                                                      
        def forward(self, x: "f32[s0, s1, 3]", y: "f32[s0, s3, 3]"):                                                                                                                                         
            # File: /home/sambhav.jain/workspaces/cruise/src/3p/torch-mlir/test/python/fx_importer/symbolic_shape_expr_test.py:31 in forward, code: a = torch.tanh(x)                                        
            tanh: "f32[s0, s1, 3]" = torch.ops.aten.tanh.default(x);  x = None                                                                                                                               
                                                                                                                                                                                                             
            # File: /home/sambhav.jain/workspaces/cruise/src/3p/torch-mlir/test/python/fx_importer/symbolic_shape_expr_test.py:32 in forward, code: b = torch.sigmoid(y)                                     
            sigmoid: "f32[s0, s3, 3]" = torch.ops.aten.sigmoid.default(y);  y = None                                                                                                                         
                                                                                                                                                                                                             
            # File: /home/sambhav.jain/workspaces/cruise/src/3p/torch-mlir/test/python/fx_importer/symbolic_shape_expr_test.py:33 in forward, code: return torch.cat((a, a, b), dim=1)                       
            cat: "f32[s0, 2*s1 + s3, 3]" = torch.ops.aten.cat.default([tanh, tanh, sigmoid], 1);  tanh = sigmoid = None                                                                                      
            return (cat,)                                                                                                                                                                                    
                                                                                                                                                                                                             
Graph signature: ExportGraphSignature(input_specs=[InputSpec(kind=<InputKind.USER_INPUT: 1>, arg=TensorArgument(name='x'), target=None, persistent=None), InputSpec(kind=<InputKind.USER_INPUT: 1>, arg=TensorArgument(name='y'), target=None, persistent=None)], output_specs=[OutputSpec(kind=<OutputKind.USER_OUTPUT: 1>, arg=TensorArgument(name='cat'), target=None)])                                               
Range constraints: {s0: ValueRanges(lower=5, upper=10, is_bool=False), s1: ValueRanges(lower=0, upper=100, is_bool=False), s3: ValueRanges(lower=0, upper=50, is_bool=False)} 
```

Huge credit to @stellaraccident for the inputs that helped evaluate the
various design options and arrive at the representation of choice.


- [x] Op definitions for symbolic_int and bind_symbolic_shape ops
- [x] fx_importer updates to import range constraints + create
symbolic_int ops
- [x] fx_importer changes for AffineMapAttr building + adding
bind_symbolic_shape ops
- [x] custom printer/parser for inlined AffineMap expressions in mlir
assembly
- [x] Dialect lit test
- [x] fx_importer python lit tests
- [ ] Cleanup pass to remove these ops (can add in a follow-on)
 2024-06-07 04:04:03 -07:00
Xinyu Yang 431d98b405
[Stablehlo] Add lowering of GridSampler Op (#3084) 
Inspired by PyTorch decompositions.py.
See
ec58f1f74e/torch/_decomp/decompositions.py (L3923-L4086)
Only support paddingMode=0 or 1 and interpolationMode=0 or 1
 2024-06-07 16:06:07 +08:00
Vivek Khandelwal 72837fbb3d
build: manually update PyTorch version (#3340) 
Set PyTorch and TorchVision version to nightly release 2024-05-14.

Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
 2024-06-06 22:23:40 +05:30
penguin_wwy d59d0b6e5a
[Linalg] Promote type for compare tensor op (#3416) 2024-06-04 16:05:39 -07:00
Vivek Khandelwal 661be2d5b0
[MLIR][Torch] Add TorchToLinalg lowering for AtenAvgPool3dOp (#3030) 
This commit also fixes the average pool op' test failing for
OnnxToLinalg lowering.

Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
 2024-06-04 22:12:34 +05:30
Vivek Khandelwal 35dd8c52cd
[ONNX] Add OnnxToTorch Lowering for MaxUnpool op (#3413) 
This commit also adds the Torch declaration for aten.max_unpool2d and
aten.max_unpool3d op. The TorchToLinalg lowering for the same will be
added in a follow-up commit.

Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
 2024-06-04 21:09:53 +05:30
penguin_wwy 89f7d24fdc
[Bazel] Fix bazel deps (#3414) 
#3367 and #3364 introduced new dependencies, causing the [Bazel
workflow](https://github.com/llvm/torch-mlir/actions/workflows/bazelBuildAndTest.yml)
to fail. These need to be fixed in Bazel.
 2024-06-04 15:50:29 +08:00
Yuanqiang Liu 50f7103098
[Stablehlo] support uint8 (#3367) 
Support lowering unsigned integer type to stablehlo as discussed in
https://github.com/llvm/torch-mlir/pull/2184.

The things I do in this PR:
1. create `setupBackendTypeConversionForStablehlo()`,
`createFuncBackendTypeConversionForStablehloPass` and
`createFinalizingBackendTypeConversionForStablehloPass`.
2. remove `InferTypeOpInterface` from `torch_c.to_builtin_tensor`,
because it's different result type between linalg backend and stablehlo
backend:
```
// linalg backend
func.func @forward(%arg0: !torch.vtensor<[3],ui8>) -> tensor<3xf32> {
    %c = torch_c.to_builtin_tensor %arg0 : (!torch.vtensor<[3], ui8> -> tensor<3xi8>
    %0 = tensor.empty() : tensor<3xf32>
    %1 = linalg.generic {indexing_maps = [#map, #map], iterator_types = ["parallel"]} ins(%arg0 : tensor<3xi8>) outs(%0 : tensor<3xf32>) {
    ^bb0(%in: i8, %out: f32):
      %2 = arith.uitofp %in : i8 to f32
      linalg.yield %2 : f32
    } -> tensor<3xf32>
    return %1 : tensor<3xf32>
}
// stablehlo backend
func.func @forward(%arg0: !torch.vtensor<[3],ui8>) -> tensor<3xf32> {
    %c = torch_c.to_builtin_tensor %arg0 : (!torch.vtensor<[3], ui8> -> tensor<3xui8>
    %0 = stablehlo.convert %arg0 : (tensor<3xui8> -> tensor<3xf32>
    return %0 : tensor<3xf32>
}
```
3. fix stablehlo and linalg's conversion
 2024-06-04 09:04:59 +08:00
zjgarvey 56d21cba62
Link necessary op interface implementations (#3364) 
This patch adds two `memref` passes to `torch-mlir-opt`, which already
occur in the pass pipeline
`torch-backend-to-linalg-on-tensors-backend-pipeline`. Additionally,
necessary op interface external models are included to address issue
#3352.
 2024-06-03 19:43:28 -05:00
Rob Suderman 0a6861b1e8
Add conversion operation for bool resolved_literal (#3410) 
Resolving `bool` literals can result in a type change to uint8. This
needs to be converted back to the expected type before returning to the
wrapped `torch` operators.
 2024-06-03 14:43:38 -07:00
Xida Ren (Cedar) 11c3281a8a
Fix reducesum onnx lit test to linalg lowering fails (#3218) 
fixes https://github.com/nod-ai/SHARK-Turbine/issues/653

---------

Co-authored-by: Xida Ren <xida.ren.dev@gmail.com>
 2024-06-03 16:36:09 -04:00
Xida Ren (Cedar) 948981a773
Update development.md to use ld.lld (#3412) 
@kuhar mentioned in the previous PR that we should use ld.lld. I kept
using ld because for my LLD version, it worked.

After updating to a new LLD version, that became necessary.
 2024-06-03 14:10:48 -04:00
zjgarvey 8995c90879
[TorchToLinalg] add support for quantized group conv (#3341) 
This addresses 7 of the model failures I'm seeing in the test suite. See
[Shark-Turbine issue
#566](https://github.com/nod-ai/SHARK-Turbine/issues/566).

Need the op ```linalg.conv_2d_ngchw_gfchw_q``` to be added upstream
before merging this. See [llvm-project PR #92136
](https://github.com/llvm/llvm-project/pull/92136).

A small additional expansion to operand quantization is included in this
patch to address a model failure that occurs when unblocking the
quantized group convolutions in one of these onnx models.
 2024-06-03 21:57:44 +05:30
Vivek Khandelwal 6382dbbcc0
[ONNX] Add OnnxToTorch lowering for SpaceToDepth op (#3393) 
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
 2024-06-03 20:29:39 +05:30
Xinyu Yang 285b087a5d
[Torch] Emit rrelu and decompose it (#3250) 
as title
 2024-06-03 19:25:52 +08:00
Xinyu Yang 267052df2a
[Torch] decompose AtenLerpTensorOp (#3251) 
as title
 2024-06-03 15:25:09 +08:00