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`.
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.
After noticing a number of commits with unrelated formatting changes,
I think something was changed with clang-format at one point and we're
seeing a number of unrelated changes. Doing a refresh can help avoid
this.
The changes made here came from
```
find lib -iname *.h -o -iname *.cpp | xargs clang-format -i --style=llvm
find include -iname *.h -o -iname *.cpp | xargs clang-format -i --style=llvm
find projects -iname *.h -o -iname *.cpp | xargs clang-format -i --style=llvm
```
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.
The logic here is very similar to the conversion for AdaptiveAvgPool1d
#2661 with a few modifications:
1. buffVal = -inf instead of 0
2. the main linalg generic op accumulates a max, instead of a sum, to
the first output tensor
3. avg pooling requires dividing the sum pool by the kernel width, which
we stored as an auxilliary tensor (kSizeTensor). Here, the auxiliary
tensor will be recording the indices. Strangely enough, the only
signature available for this function is to return indices, and it
appears that they must be computed whether the user desires them or not.
See
[pytorch/torch/nn/functional.py](https://github.com/pytorch/pytorch/blob/main/torch/nn/functional.py#L1174).
Before writing other adaptive pooling conversions, the logic of this
decomposition should be rolled into a helper function that will work for
both max and avg pooling ops. Even the auxiliary tensor should likely be
automated. This code was written in a slightly more tedious way than
strictly necessary (often using loops to fill SmallVectors up to rank-2,
which is only two in this case), in order to more easily facilitate the
transition to a helper function.
convolution with [time,batch,channel] ordering, as opposed to the
default [batch, channel, time]. Currently implementing by transposing
the input and output, but may need to get its own implementation in the
future because this is supposed to be an op that gives a speedup. This
is used by fairseq
(https://github.com/facebookresearch/fairseq/issues/172).
(in case you were wondering like me, this is different from transposed
convolution. Transposed convolution has fractional strides).
---------
Co-authored-by: Xida Ren <xida.ren.dev@gmail.com>
Co-authored-by: Frederik Harwath <frederik.harwath@amd.com>
Handle both `torch.dequantize` and `torch.quantize_per_tensor` including
the op based quantization parameter tracking. This includes adding
`qint32` to torch types as it was missing during the initial type
inclusion.
For testing we only have `torch.int8` and `torch.float` types on
function boundaries as the `qint8` types require passing the scale
and zero point quantization information which is not supported yet.
Adds a lowering to Linalg for reflection_pad1d. Based on ideas/code from draft PR
https://github.com/llvm/torch-mlir/pull/2693.
---------
Co-authored-by: Kumar Deepak <kumar@xilinx.com>
The expression for HardSigmoid in Onnx
(https://onnx.ai/onnx/operators/onnx__HardSigmoid.html): max(0, min(1,
alpha * x + beta))
is inherently different from HardSigmoid in Torch
(https://pytorch.org/docs/stable/generated/torch.nn.Hardsigmoid.html)
which is: if x < -3 -> 0
elif x > 3 -> 1
else x/6 + 1/2
That being said, it was just better to compute out the entire expression
when translating the Onnx expression to Torch mlir, which is done in
this PR. Some of the logic is shared from the files in
`DecomposeComplexOps`. Therefore, refactored some shared logic between
`DecomposeComplexOps` and `DefaultDomainGToP` and put it in a `Utils`
file.
This commit adds the OnnxToTorch support for BitwiseXor, BitwiseOr, Div, Equal, Cast,
Ceil, Floor, Cos, and Clip op.
This commit also adds the TorchToLinalg support for aten.clamp.Tensor and aten.clamp_min.Tensor op.
Signed-Off By: vivekkhandelwal1424@gmail.com
Adds a lowering for the torch.aten.argmin operator to linalg via decomposition into torch.aten.min.dim.
---------
Co-authored-by: Franz Haniel <franz.haniel@amd.com>
This commit adds the OnnxToTorch support for Atan, Bitshift, BitwiseAnd,
and BitwiseNot op.
This commit also adds the TorchToLinalg support for AtenBitwiseLeftShiftTensorOp.
Signed-Off By: vivekkhandelwal@nod-labs.com
The aten.reshape ops in the decomposition are replaced with prims.collapse
and prims.split_dim ops, which means that the cases where the lowering of
reshape from torch to linalg which are not supported, are avoided.
Essentially, by using the collapse and split_dim ops instead of the
reshape ops, we are not "losing" the information that the reshapes do not
arbitrarily mix dimensions. Which makes lowering easy.
3 additional tests added:
- fully dynamic,
- dynamic only the spatial dimensions,
- dynamic only in the non-spatial dimensions.
Adds support for lowering to prims split_op.
Similar design to collapse op lowering in
https://github.com/llvm/torch-mlir/pull/2572, with some
small differences, because the split_dim op (in pytorch) is
view-changing whereas the collapse is not. The difference
means that
1) it must be registered in the function Torch::isViewLikeOp
2) it must be be added to the "expected fail" set for the torch dynamo backend.
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.
… AtenBernoulli_FloatOp
It fixing case like: `%2110 = torch.aten.arange.start_out %int1,
%int1517, %int1, %2109 : !torch.int, !torch.int, !torch.int,
!torch.tensor -> !torch.tensor`.
`aten.arange.start_out` doesn't have value semantics also, means`%2110`
is an alias for %2109.
So I decompose it to `aten.arange.start` + `torch.contents.overwrite`.
The complex decomposition logic is target to handle cases like view and
dtype cast which I add in e2e tests.
Steps taken:
1) add generator code to torch_ods_gen.py, run update_torch_ods.sh
2) add (custom) shape and type inference generator code to
abstract_interp_lib_gen.py, run update_abstract_interp_lib.sh
3) Implement lowering to tensor.collapse_dims. Requires the `start` and
`end` values to be constant, else lowering fails
4) Update xfail_sets.py (append to LTC_XFAIL_SET) after running
/tools/e2e_test.sh --filter Collapse --verbose -c XX for all support
backends (XX).
Motivation:
- Supporting the collapse operation will be useful for lowering of
pixel_shuffle (see Issue #2559)
For static tests (that is when the shape is know) for example:
```
@annotate_args([None, ([3, 18, 2, 2], torch.float32, True)])
```
The e2e passes. But only if the replacement op's return type is set as
undefined (optional shape and type must be explicitly made unset),
otherwise there's a error about the function return type.
For dynamic cases, for example if the above is replaced with
```
@annotate_args([None, ([-1, -1, -1, -1], torch.float32, True)])
```
There is a failure to lower to linalg from torch ("view op explicitly
labelled as illegal"). This seems to be because the support for lowering
from torch to linalg with dynamic shapes is limited.
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.
NonValueSemantic Ops like Add_, div_, etc. expect result DType to be the
same as the first input. However, current implementation would result in
wrong result type for case like:
```python
a = torch.randn(3, 3).half() # float16
b = torch.randn(3, 3) # float32
a += b # i.e. torch.ops.aten.add_(a, b)
```
torch expects `a` to be float16, but dtype refinement would infer
float32 type, since it's replaced by `aten.add`.
Add aten.isclose op
Add its torch-to-tosa lowering
Update the TorchToTosa/basic.mlir tests
To test e2e tosa lowering:
`python -m e2e_testing.main -v -c=tosa`
---------
Co-authored-by: Ze Zhang <ze.zhang@getcruise.com>
Add aten.unflatten.int op
Add its torch-to-tosa lowering
Update the TorchToTosa/basic.mlir tests
To test e2e tosa lowering:
`python -m e2e_testing.main -v -c=tosa`
---------
Co-authored-by: Ze Zhang <ze.zhang@getcruise.com>
Set PyTorch and TorchVision version to nightly release 2023-09-28.
aten.baddbmm changes done because upstream PyTorch has now added
support for fp16 gemm on CPU.
Refer: 9399e0b1ff
When importing dynamic shaped programs from Dynamo, via torch.compile or
torch.export, we can assume that strict symbolic shape checks have been
done prior to generating torch IR. Among other shape checking, this
eliminates the case where an unknown dimension can be dynamically '1' in
a way that signals a broadcast.
Adds a `isAssumingStrictSymbolicShapes` utility which consults a
`torch.assume_strict_symbolic_shapes` attribute on an enclosing scope
and returns true if present.
In the linalg pipeline, many runtime checks are elided when this returns
true.
Set PyTorch and TorchVision version to nightly release 2023-09-26.
aten._convolution.deprecated changes done because upstream PyTorch has
now added support for fp16 native convolution on CPU.
Refer: 7c9052165a
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
Making the same PR with #2457, as I accidentally thought the review was already made and merged it (reverted).
Add decompose empty_strided op.
Referring to #1776, this decomposition op only supports default stride values, because accessing the tensor or indexing over that, the indices are determined by the strides.
In MLIR, this is not implicitly supported but assumes that the strides are default while iterating over the tensor.
* view_as_real test case, allow dtype in testutils.randn
* abstract python upstream func implemented
* fixed upstream dtype func, implemented view_as_real backend op
* formatted AtenViewAsRealOp, removed change in e2etest/framework
* removed test suit from reshape_like.py, because it's moved to basic.py
* implemented C-API wrapper for mlirComplexF128 type
* fixed torch.complex dtype width in MLIR and Torch MLIR, deleted float16 dtype dict
* Changed IR input of aten fft_fft unit test
* code refactored
* code refactored and fixed ci test
* refactored: removed white spaces, and rolled back to having both input/output affine expr
* refactored: deleted output affine expr to reduce redundancy
* xfail ltc backend
* removed ComplexImag and ComplexReal from torchdynamo xfail set
* copied and pasted from main branch as there's no change to be made in this file
* refactored abstract_interp_lib_gen.py
* refactored: torchtypes.td, formatted, removed commented out code
* [MLIR][TORCH] Fix aten.cumsum lowering for int32 input (#2351)
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
[Stablehlo] Add converter to stablehlo for aten.(Int,Float,Bool).Tensor op (#2340)
[Stablehlo] Add converter to stablehlo for aten.(Int,Float,Bool).Tensor op and configure crashing e2e sets for stablehlo backend.
update PyTorch version to 2.1.0.dev20230729 (#2354)
- torch version: 2.1.0.dev20230729
- torch commit hash: b638df0afb83572724032c824c64e481bb4499a0
- torchvision version: 0.16.0.dev20230729
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
update PyTorch version to 2.1.0.dev20230730 (#2356)
- torch version: 2.1.0.dev20230730
- torch commit hash: 0ff243ff350268cc98fe03fa6364375ee2824742
- torchvision version: 0.16.0.dev20230730
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
update PyTorch version to 2.1.0.dev20230731 (#2359)
- torch version: 2.1.0.dev20230731
- torch commit hash: 6298ac688f8caafe30d71ff2ea2e20fbb32065c7
- torchvision version: 0.16.0.dev20230731
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
LTC->MLIR Debug Info support (#1922)
* LTC->MLIR Debug Info support
* SW-95317 Propagate Lazy->Jit->MLIR scope name.
* Enhance location information based on op names
Currently, the location information attached to the ops just considers
the filename, line number and column number. Attaching operation name
would help identify the type of computation by just looking at the
profile of execution.
* Update locations logic; updated debug-info.py test
* Use {scope}/{op_name} format to track names by default
---------
Co-authored-by: Gleb Kazantaev <gleb.kazantaev@cerebras.net>
Co-authored-by: Mark Browning <mark@cerebras.net>
Co-authored-by: Vimal Patel <vimal@polymagelabs.com>
build: update llvm tag to 41895843
Summary of changes:
- Update tags
llvm: 41895843b5915bb78e9d02aa711fa10f7174db43
mhlo: 4726d31f7025da66de0dea709bd56c462edb83c2
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
update PyTorch version to 2.1.0.dev20230802 (#2366)
- torch version: 2.1.0.dev20230802
- torch commit hash: c89b16917755c2abbef7b6420e340baf9ae8089e
- torchvision version: 0.16.0.dev20230802
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
Change Python version from 3.10 to 3.11 in installation instructions (#2370)
Add CITATION file (#2371)
Add packaging as an install dependency (#2369)
Needed by `torch_mlir._version`. Resolves#2368.
[Torch Dialect] emit aten.masked_scatter and aten.masked_scatter_ op (#2358)
* [Torch Dialect] emit aten.masked_scatter and aten.masked_scatter_ op
update PyTorch version to 2.1.0.dev20230803 (#2372)
- torch version: 2.1.0.dev20230803
- torch commit hash: f89c73be3a3e8274d025ac46a33a780853841c9e
- torchvision version: 0.16.0.dev20230803
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
Prevent failed stable CI job from cancelling nightly jobs (#2373)
The CI jobs that use stable PyTorch are currently not required to pass
in order for a patch to get merged in `main`. This commit makes sure
that if a CI job for stable PyTorch fails, it does not cancel the
other required jobs.
[Torch Dialect] emit aten.tile op and decompose it into aten.repeat (#2355)
update
update xfail sets
update xfail_sets
update
fix xfail_sets
update:
update
update:
update
parent 22e88d523b1970b2e904eb5421d49d987a3d255e
author jianzhe.xiao <jianzhe.xiao@bytedance.com> 1691114110 +0800
committer jianzhe.xiao <jianzhe.xiao@bytedance.com> 1691114119 +0800
[Stablehlo] Add converter to stablehlo for aten.(Int,Float,Bool).Tensor op (#2340)
[Stablehlo] Add converter to stablehlo for aten.(Int,Float,Bool).Tensor op and configure crashing e2e sets for stablehlo backend.
update PyTorch version to 2.1.0.dev20230729 (#2354)
- torch version: 2.1.0.dev20230729
- torch commit hash: b638df0afb83572724032c824c64e481bb4499a0
- torchvision version: 0.16.0.dev20230729
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
update PyTorch version to 2.1.0.dev20230730 (#2356)
- torch version: 2.1.0.dev20230730
- torch commit hash: 0ff243ff350268cc98fe03fa6364375ee2824742
- torchvision version: 0.16.0.dev20230730
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
update PyTorch version to 2.1.0.dev20230731 (#2359)
- torch version: 2.1.0.dev20230731
- torch commit hash: 6298ac688f8caafe30d71ff2ea2e20fbb32065c7
- torchvision version: 0.16.0.dev20230731
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
LTC->MLIR Debug Info support (#1922)
* LTC->MLIR Debug Info support
* SW-95317 Propagate Lazy->Jit->MLIR scope name.
* Enhance location information based on op names
Currently, the location information attached to the ops just considers
the filename, line number and column number. Attaching operation name
would help identify the type of computation by just looking at the
profile of execution.
* Update locations logic; updated debug-info.py test
* Use {scope}/{op_name} format to track names by default
---------
Co-authored-by: Gleb Kazantaev <gleb.kazantaev@cerebras.net>
Co-authored-by: Mark Browning <mark@cerebras.net>
Co-authored-by: Vimal Patel <vimal@polymagelabs.com>
build: update llvm tag to 41895843
Summary of changes:
- Update tags
llvm: 41895843b5915bb78e9d02aa711fa10f7174db43
mhlo: 4726d31f7025da66de0dea709bd56c462edb83c2
Signed-Off By: Vivek Khandelwal <vivek@nod-labs.com>
update PyTorch version to 2.1.0.dev20230802 (#2366)
- torch version: 2.1.0.dev20230802
- torch commit hash: c89b16917755c2abbef7b6420e340baf9ae8089e
- torchvision version: 0.16.0.dev20230802
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
Change Python version from 3.10 to 3.11 in installation instructions (#2370)
Add CITATION file (#2371)
Add packaging as an install dependency (#2369)
Needed by `torch_mlir._version`. Resolves#2368.
[Torch Dialect] emit aten.masked_scatter and aten.masked_scatter_ op (#2358)
* [Torch Dialect] emit aten.masked_scatter and aten.masked_scatter_ op
update PyTorch version to 2.1.0.dev20230803 (#2372)
- torch version: 2.1.0.dev20230803
- torch commit hash: f89c73be3a3e8274d025ac46a33a780853841c9e
- torchvision version: 0.16.0.dev20230803
Co-authored-by: Roll PyTorch Action <torch-mlir@users.noreply.github.com>
Prevent failed stable CI job from cancelling nightly jobs (#2373)
The CI jobs that use stable PyTorch are currently not required to pass
in order for a patch to get merged in `main`. This commit makes sure
that if a CI job for stable PyTorch fails, it does not cancel the
other required jobs.
[Torch Dialect] emit aten.tile op and decompose it into aten.repeat (#2355)
update
update xfail sets
update xfail_sets
update
fix xfail_sets
update:
update
update:
add support for adaptive_pool_id
update xfail sets
update xfail_sets
update
fix xfail_sets
update:
update:
* update
---------
Co-authored-by: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
The implementation at this place was a remnent of the times the pipeline was
run only once.
Rely instead on the backend verification, after optimizations have had an
opportunity to resolve some uncertainties. (e.g. `!torch.optional`).
* RecomposeComplexOps: Remove dead slice op
* lib/Dialect/Torch/IR/TorchOps.cpp: Fold slice ops even when they are on non-value tensors
* lib/Conversion/TorchToTosa/TorchToTosa.cpp: Fix slice start/end out of range/none
* lib/Dialect/Torch/IR/TorchOps.cpp: AtenSliceTensorOp::fold: Fold slices that go from 0:int_max
* More tests for aten.split.Tensor
Rob Suderman
Ilija Kalinić
Quinn Dawkins
MaheshRavishankar
zjgarvey
Xida Ren (Cedar)
Franz Haniel
John Wu
Sungsoon Cho
lonely eagle
James Newling
lisaliu1
Frederik Harwath
Vivek Khandelwal
Kunwar Grover
kumardeepakamd
Han-Chung Wang
JianzheXiao
Frederik Harwath
Mi Jiazhi
Stella Laurenzo
Yuanqiang Liu
Jiawei Wu
Zhekun(Josh) Zhang
saienduri
Daniel Garvey
Ze Zhang
Bruce Kim
Ramiro Leal-Cavazos
Arham Khan
Jerin Philip
Alexandre Rames
Matthias Gehre