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`.
The existing `flatten` lowering did not define what the intermediate
shape was. This could result in failures to lower further to linalg as
the intermediate shape was unknown. Added a shape refinement section.
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>
`[build]
D:\Dev\iree\third_party\torch-mlir\lib\Conversion\TorchOnnxToTorch\DefaultDomainGtoP.cpp(734):
warning C4305: 'argument': truncation from 'double' to 'float'`
`torch` requires that padding be symmetric for pooling operations. To
support non-symmetric pad we need to separately materialize out the
padding operation.
---------
Co-authored-by: James Newling <james.newling@gmail.com>
We do not support average pool when `countIncludePad is set to false.
However if the input is unpadded then the setting of the boolean is
unneeded. Extended use by checking if padding is zero before rejecting
the lowering.
With the recent LLVM integrate and changes from
https://github.com/llvm/llvm-project/pull/78260, we hit this build error
in Stablehlo (which is quite old).
```
external/stablehlo/stablehlo/transforms/StablehloRefineShapes.cpp:1020:14: error: no member named 'startRootUpdate' in 'mlir::PatternRewriter'
rewriter.startRootUpdate(op);
~~~~~~~~ ^
external/stablehlo/stablehlo/transforms/StablehloRefineShapes.cpp:1026:16: error: no member named 'finalizeRootUpdate' in 'mlir::PatternRewriter'
rewriter.finalizeRootUpdate(op);
~~~~~~~~ ^
external/stablehlo/stablehlo/transforms/StablehloRefineShapes.cpp:1029:16: error: no member named 'cancelRootUpdate' in 'mlir::PatternRewriter'
rewriter.cancelRootUpdate(op);
~~~~~~~~ ^
external/stablehlo/stablehlo/transforms/StablehloRefineShapes.cpp:1108:14: error: no member named 'updateRootInPlace' in 'mlir::PatternRewriter'
rewriter.updateRootInPlace(op->getParentOp(), [&]() { return; });
~~~~~~~~ ^
4 errors generated.
Target @torch-mlir//:torch-mlir-opt failed to build
```
I'm still puzzled as to how this didn't fail with the CMake merge gating
CI (do we not test Stablehlo builds/tests?). In any case, bumping our
submodule to https://github.com/openxla/stablehlo/pull/1918 fixes it.
It exposes a new failing lit test in TorchToStablehlo though, that I
have looped stablehlo developers into
([here](https://discord.com/channels/999073994483433573/999074539138990131/1201235845391331419)).
```
bazel run @torch-mlir//test/Conversion:TorchToStablehlo/scatter.mlir.test
...external/torch-mlir/test/Conversion/TorchToStablehlo/scatter.mlir
within split at <stdin>:1 offset :33:8: error: unexpected error: Expects non-empty reduction block for type inference
%0 = torch.aten.scatter.src %arg0, %int0, %arg1, %arg2 : !torch.vtensor<[?,?],si64>, !torch.int, !torch.vtensor<[?,?],si64>, !torch.vtensor<[?,?],si64> -> !torch.vtensor<[?,?],si64>
^
LLVM ERROR: Failed to infer result type(s).
```
Bazel CI:
https://github.com/sjain-stanford/torch-mlir/actions/runs/7732673480/job/21083102228
`onnx` explicitly specifies that `raw_data` is stored in `little-endian`
layout. While converting
to `torch` we need to convert from a known endian format to an internal
format of consistent
layout. This means endianness must be correct during the import of
`onnx.Constant`.
---------
Co-authored-by: Xida Ren (Cedar) <cedar.ren@gmail.com>
Required some massaging of LTC to make it warning clean, and I had to
manually disable some warnings on the generated source files (which we
don't control).
The project is warning clean now.
The `-Werror` flag is disabled by default as we can't control everywhere
people will try to build/install. The CI enables it via
-DTORCH_MLIR_ENABLE_WERROR_FLAG=ON.
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>
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
```
Torch does not have an equivalent matmul operation for integers. Instead
it sidechannels the information via its quantized types. For this
lowering we setup these sidechannels then invoke `torch.mm`.
This preserves sparsity at the most obvious places of lowering TORCH
tensors to MLIR RankedTensorType tensors. Other places are marked for
audit. With some initial lowering tests.
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.
We can plumb the linear matmul into pytorch using its quantized types
with side channel information. To handle the final int8 operation we
dequantize and requantize.
This commit adds mapping from `onnx.pad` op to `torch.pad` op. Currently
it does not support `axes` parameter of `onnx.pad` op.
Signed-off-by: Gaurav Shukla <gaurav.shukla@amd.com>
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>
Currently transposed convolution is not handled correctly by
`TorchToTosa`. This PR allows transposed convolutions to pass through
the conversion so that they can be handled by other conversion passes
later in a pipeline.
An example input which produces a compilation error is:
```
func.func @forward(%input: !torch.vtensor<[1,64,1,100],f32>) -> !torch.vtensor<[1,64,2,200],f32> {
%true = torch.constant.bool true
%int1 = torch.constant.int 1
%int2 = torch.constant.int 2
%weight = torch.vtensor.literal(dense<0.0> : tensor<64x64x3x3xf32>) : !torch.vtensor<[64,64,3,3],f32>
%bias = torch.vtensor.literal(dense<0.0> : tensor<64xf32>) : !torch.vtensor<[64],f32>
%stride = torch.prim.ListConstruct %int2, %int2 : (!torch.int, !torch.int) -> !torch.list<int>
%int1x1 = torch.prim.ListConstruct %int1, %int1 : (!torch.int, !torch.int) -> !torch.list<int>
%output = torch.aten.convolution %input, %weight, %bias, %stride, %int1x1, %int1x1, %true, %int1x1, %int1 : !torch.vtensor<[1,64,1,100],f32>, !torch.vtensor<[64,64,3,3],f32>, !torch.vtensor<[64],f32>, !torch.list<int>, !torch.list<int>, !torch.list<int>, !torch.bool, !torch.list<int>, !torch.int -> !torch.vtensor<[1,64,2,200],f32>
return %output : !torch.vtensor<[1,64,2,200],f32>
}
```
This MLIR produces an error about a cast operation with a size mismatch
when passed through `torch-to-tosa`:
```
error: 'tensor.cast' op operand type 'tensor<1x64x1x50xf32>' and result type 'tensor<1x64x2x200xf32>' are cast incompatible
```
---------
Co-authored-by: Srinath Avadhanula <srinath.avadhanula@getcruise.com>
Introduced in 704cfdaf08 of @wu-s-john
g++ compiler error:
Pooling.cpp:177:13: error: explicit specialization in non-namespace
scope ‘class
Design looks good, g++ is just freaking out for no good reason.
Un-nesting the template classes fixes the error.
We don't have g++ CI. This hopefully happens infrequently enough that we
can just fix manually. My service to those folks who really like
building with g++... :)
We can make the per-tensor version of the operation to the dequantize
operation via marking with the make quantized tensor component. This
introductions the `qint*` and `quint*` tensor type that can be lowered
to teh appropriate dequantization behavior during the torch-to-linalg
conversion.
We can map the per_tensor case to the `torch.aten.quantize_per_linear`
operation. In this case we extract the `scale` and `zeropoint` values
and directly invoke the quantization, then return the integer
representation value.
Rob Suderman
Gaurav Shukla
Xida Ren (Cedar)
Ben Vanik
Sambhav Jain
Ilija Kalinić
Stella Laurenzo
Yuanqiang Liu
Aaron St George
aldesilv
Quinn Dawkins
MaheshRavishankar
Aart Bik
Vivek Khandelwal
Phaneesh Barwaria
lonely eagle
zjgarvey
Chi_Liu
James Newling
Ramiro Leal-Cavazos
Srinath Avadhanula
Franz Haniel
Dave Liddell
John Wu
Andreas Falkenberg
Ze Zhang