I've upstreamed the necessary quantized linalg Op with the
"channel-first" ordering used by torch
(https://github.com/llvm/llvm-project/pull/107740) for 2d convolution.
This patch changes the lowering for the quantized 2d case of
`aten.convolution` accordingly, which saves three transpositions per
convolution (input, weights, result) and therefore removes the
requirement to try to optimize these away in downstream passes.
Torch-to-linalg pass fails for `EmbeddingBag` when the training only
specific properties of the operator are set to `true.` For instance,
this operator's `sparse` input/property is training-specific, and if the
value of this property is `true,` the existing lowering bails out.
However, we don't need to check for training-specific parameters and
bailout from the legalization since we don't care about these properties
during the eval/inference mode.
---------
Co-authored-by: Hanumanth Hanumantharayappa <hhanuman@ah-hhanuman-l.dhcp.mathworks.com>
# Description
Implementation of the op for `torch.aten.unfold`: [TorchToLinalg Op
Support #347](https://github.com/nod-ai/SHARK-ModelDev/issues/849)
Documentation of op can be found here: [PyTorch
Docs](https://pytorch.org/docs/stable/generated/torch.Tensor.unfold.html)
For this op, we apply a sliding window of some `size` along a single
`dimension`, with `step` in between iterations.
`Declaration: aten::unfold(Tensor(a) self, int dimension, int size, int
step) -> Tensor(a)`
The resulting `unfolded` tensor modifies the shape of `dimension` to be
equal to the number of blocks that the sliding windows extracts/inserts,
with an additional dimension of `size` appended (the number of cols of
the output tensor directly translates from the size of the sliding
window).
So if we had a tensor of rank 3 (A x B x C), with dimension = 1, size =
2 and step = 2:
(A x B x C) |=> (A x (B - size) // step + 1 x C x size)
After extracting the window from the input tensor, we insert the (1 x
size) slice into the output tensor. We can make this simpler by mapping
the output indices from the input indices, like they do in the official
implementation:
[PyTorch
Code](https://github.com/pytorch/pytorch/blob/main/torch/_inductor/lowering.py#L1694)
This commit adds the support for the 1-d depthwise convolution as a
special case of 1-d group convolution.
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
This commit adds the support for negative step values in
aten.slice.Tensor op. Although, PyTorch does not allow negative step
value for slice op but the Onnx.Slice op supports negative step value
which eventually lowers to torch.aten.slice.Tensor op. Hence, the
support is added for handling those kind of values during the
Torch->Linalg lowering of aten.slice.Tensor op.
Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
Follow up cleanup for [this
PR](https://github.com/llvm/torch-mlir/pull/3689), which introduced a
decomposition for `aten.fmod.Tensor`. This means that the lowering for
this operator in linalg is no longer needed.
Thanks to @vivekkhandelwal1 for pointing this out.
---------
Co-authored-by: Srinath Avadhanula <srinath.avadhanula@getcruise.com>
The lowering pattern for `aten.T` uses transposition implemented via
`linalg.generic`. For downstream passes it is advantageous to use named
ops wherever possible, so this patch changes the lowering to use
`linalg.transpose` instead.
The current implementation uses a `linalg.generic` to broadcast the bias
tensor for the lowering of convolutions. This is suboptimal for later
pattern matching. This patch changes it to use the respective named op,
`linalg.broadcast`, instead.
Closes#3575
The PyTorch remainder operator is meant to compute the Python modulus
operator entrywise:
https://pytorch.org/docs/stable/generated/torch.remainder.html#torch.remainder
In python the modulus operator is meant to always return a result with
the same sign as the divisor:
https://docs.python.org/3/reference/expressions.html#binary-arithmetic-operations
In other words, torch.aten.remainder should return a Python-style
modulus instead of a C-style modulus. However the remainder operator was
simply translated into arith.ModSI or arith.ModF, which both effectively
compute the C-style modulus. Now the lowering has been modified so that
the modulus operator works properly with negative numbers, both in the
dividend, and the divisor.
This patch adds basic support for lowering graphs with per-channel
quantization. Per-channel quantized ops have to be excluded from
`FuseQuantizedOps` for now but can be used in QDQ quantized form.
Using this patch, we're able to import and execute (on the linalg
backend) graphs with per-channel quantization applied using the "new"
PyTorch 2.0 Export Quantization.
Following up from the discussion in
<https://github.com/llvm/torch-mlir/pull/3550>, I've edited the lowering
to prevent OOB extracts in a more direct fashion (i.e., just clamping
directly).
I don't think this affects the lit tests at all, but I've tested the
changes in our external test suite at
<https://github.com/nod-ai/SHARK-TestSuite/tree/main/>. I found the
issue when I was unexpectedly getting `nan`'s along the output image
border for a resize test there.
Change linalg.matmul_unsigned to linalg.matmul with unsigned type_fn
Signed-off-by: Max Dawkins <max.dawkins@gmail.com>
Co-authored-by: Max Dawkins <max.dawkins@gmail.com>
There were two issues related to `ignore_index` being set
(1) the onnx-to-linalg pass as not reading the value correctly (2) the
mean pass was not considering the `ignore_index` value
For (2) when taking the mean we need to know how many of the values were
considered in the sum and therefore we cannot divide by the total number
of elements. Adding a summation across the total number should correct
this issue.
- Adds support for lowering depthwise + quantized convolution ops to
linalg::DepthwiseConv2DNhwcHwcQOp
- Changed the variable name for groupSize (which is really C/G) to the
more appropriate numGroups (G).
- Discovered in e2e testing that linalg does not accept (Cin = groups &&
Cout = K*groups for K>1) as a "depthwise" conv, so this also updates the
case-checking to reflect this issue.
Pytorch and ONNX apparently round to nearest, ties go to nearest even,
but we were using `math::round` for the torch-to-linalg conversion of
`quantize_per_tensor`, which rounds away from zero on ties.
This PR adds a conversion in the TorchOnnxToTorch pass for the ONNX
Multinomial operation. It also adds a TorchToLinalg lowering for the
`aten.Multinomial` op and does a light refactor of some repeated code
that generates random floating point numbers in
`TorchToLinalg/Random.cpp`.
This patch adds a few misc pad op related changes:
1. Addresses issue <https://github.com/llvm/torch-mlir/issues/3457>
2. Addresses issue <https://github.com/llvm/torch-mlir/issues/3442>
3. Fixes the padding order for asymmetrically padded onnx.Conv ops
4. Enables passing quantization through those onnx.Conv op pre-paddings
5. Modifies the torch-to-linalg lowering of AtenReplicationPad2d op to
enable support for input rank != 4
Unfortunately, even with all of these changes, the e2e tests for the
ReplicationPad2d still fail the onnx config, since the torch export
procedure for rearranging the pad order is complicated enough that the
padding ints end up not being able to fold back to constants.
Addresses an issue with onnx.Gather lowering to linalg:
<https://github.com/nod-ai/SHARK-Turbine/issues/242>
The builder for tensor.expand_shape, without an explicitly provided
output shape, fails to infer an output shape in the case of multiple
dynamic reassociation dims. I tried adding the output shape explicitly
for tensor.expand_shape, but ran into compilation issues later on (see
<https://github.com/iree-org/iree/issues/17760>).
This PR adds support by lowering this op to tensor.reshape when multiple
dynamic reassociation dims are provided.
Before this PR, a statically shaped aten.convolution would generate
dynamically shaped linalg IR, and even `-canonicalize` would not be able
to fold it back into static shapes. This PR ensure that shape
calculations are folded on construction to directly generate statically
shaped linalg IR.
We achieve that by ensuring that `arith` ops involved in computing
shapes are created via `createOrFold`, so that later uses of
`getAsOpFoldResult` see constants instead of those ops.
For example
```
module {
func.func @forward(%arg0: !torch.vtensor<[32,336,112,112],f32>,
%arg1: !torch.vtensor<[336,168,3,3],f32>,
%arg2: !torch.vtensor<[336],f32>)
-> !torch.vtensor<[32,336,56,56],f32> {
%false = torch.constant.bool false
%int2 = torch.constant.int 2
%int1 = torch.constant.int 1
%0 = torch.prim.ListConstruct %int1, %int1 : (!torch.int, !torch.int) -> !torch.list<int>
%1 = torch.prim.ListConstruct %int2, %int2 : (!torch.int, !torch.int) -> !torch.list<int>
%2 = torch.prim.ListConstruct : () -> !torch.list<int>
%3 = torch.aten.convolution %arg0, %arg1, %arg2, %1, %0, %0, %false, %2, %int2
: !torch.vtensor<[32,336,112,112],f32>, !torch.vtensor<[336,168,3,3],f32>, !torch.vtensor<[336],f32>, !torch.list<int>,
!torch.list<int>, !torch.list<int>, !torch.bool, !torch.list<int>, !torch.int
-> !torch.vtensor<[32,336,56,56],f32>
return %3 : !torch.vtensor<[32,336,56,56],f32>
}
}
```
would result in
```
[...]
%padded = tensor.pad %2 low[%14, %15, %16, %17] high[%14, %15, %16, %17] {
^bb0(%arg3: index, %arg4: index, %arg5: index, %arg6: index):
tensor.yield %cst : f32
} : tensor<32x336x112x112xf32> to tensor<?x?x?x?xf32>
[...]
%45 = linalg.conv_2d_ngchw_gfchw {dilations = dense<1> : vector<2xi64>, strides = dense<2> : vector<2xi64>}
ins(%expanded, %expanded_37 : tensor<?x2x?x?x?xf32>, tensor<2x168x168x3x3xf32>)
outs(%expanded_44 : tensor<32x2x168x?x?xf32>) -> tensor<32x2x168x?x?xf32>
[...]
```
and with this PR all shapes are static.
This adds support for a few ops:
- torch.linalg_det
- torch._linalg_det (if the LU and pivot returns are unused)
- onnx.Det
An scf loop is used, since the row reduction algorithm applied here has
some loop-carried dependencies.
The current support being added here is very basic, and only works if no
permutations are required during row reduction, and assumes the matrices
are non-singular.
1. truncates zero-points to i32
2. modifies the default accumulator type for i8 from i64 to i32.
3. now uses the input dtype to infer accumulator dtype.
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
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.
Longsheng Mou
aldesilv
Rob Suderman
Felix Schneider
Hanumanth04
Stephen Baione
jinchen
Vivek Khandelwal
zjgarvey
Srinath Avadhanula
lingzhiz1998
Ian Wood
pkapris-syrmia
Rob Suderman
Ivan Butygin
Arham Khan
Max191
Matthias Gehre
Chi_Liu
Aart Bik
Yuanqiang Liu
penguin_wwy