This commit makes the following changes needed to update bump LLVM:
- Replace `linalg.init_tensor` with `tensor.empty` (see:
https://reviews.llvm.org/D135129)
- Replace `NoSideEffect` with `Pure` (see
https://reviews.llvm.org/D135505)
- Replace `body` region accessor for `ReduceOp` and `ReduceWindowOp`
with `getBody`
- Fix incorrect use of `tosa::ReduceSumOp` in `AtenNativeLayerNormOp`
conversion pattern. The result type of `tosa::ReduceSumOp` must have
the same rank as the input type. (see:
https://www.mlplatform.org/tosa/tosa_spec.html#_reduce_sum)
Co-authored-by: Ashay Rane <ashay@users.noreply.github.com>
Co-authored-by: Ashay Rane <ashay@users.noreply.github.com>
This commit removes the `weight` tensor from the inputs of one of the
`linalg.generic` ops generated by the `aten.convolution` linalg
lowering, since the indexed values are not actually used by the body
of the `linalg.generic`. Moreover, in general the `weight` tensor does
not have the same shape as the output tensor of the `linalg.generic`,
so both tensors being indexed by the same indexing maps is wrong.
-- This commit adds e2e support for `aten.Mish` op.
-- `aten.Mish` op is decomposed as following :-
Mish(x) = x * Tanh(Softplus(x))
Signed-off-by: Abhishek Varma <avarma094@gmail.com>
Signed-off-by: Abhishek Varma <avarma094@gmail.com>
This commit adds lowering of `aten.div.int` and `aten.bitwise_or.Tensor`
ops. Both these ops are required in order to support bloom_560m model.
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
This commit updates the linalg conversion of `AtenMaxDimOp` to use
`arith.maxf` instead of `arith.select` to calculate the maximum. This
allows better vectorization further downstream, since the operation
can be converted to a simple max reduction when the `indices` result
is not used. See: https://github.com/iree-org/iree/issues/10666.
Summary of changes:
- Updated references to the Arith dialect
(https://reviews.llvm.org/D134762)
- Switched to prefixed accessors for MemRef dialect
(https://reviews.llvm.org/D134995)
- Fixed warnings about signed/unsigned comparisons, ignored return
values, and unused variables
* Fix c10::prim::Constant conversion; Added CAPI for passes; Added passes to base lazy backend
* Update ivalue_importer to use ImportOptions; Added tests for non-value/value tensor types
* Added tests for scalar Constant import; Updated MB::importFunction to use ImportOptions
* Test updates
* Move back module variable name
* Remove RefineTypes from TorchMlirLoweringContext::Build()
* Rename pass; Remove passes from base lazy backend
* Rename pass to VerifyBackendContractPass
* Aligned cmd pass name; Fixed TorchConversion passes registration
The auto-update of the PyTorch version broke the Torch-MLIR build
because it did not update the shape library. Going forward, we should
add the shape library update to the PyTorch version update action.
This commit adds support for TorchToTosa lowering of
`aten.broadcast_to` op for cases:
1.) When the rank of input and output tensor is equal.
2.) When the rank of input tensor is zero.
Signed-Off By: Vivek Khandelwal<vivek@nod-labs.com>
Summary of changes:
- Renamed OptionalArrayRefParameter since the name conflicts with an
upstream symbol that has a different meaning
(https://reviews.llvm.org/D133819)
- Removed extraneous dependency between TorchMLIRTorchToMhlo and
ChloOps, since the existing dependency on MhloDialect is sufficient
- Fixed code to prevent warnings related to comparisons between signed
and unsigned values
Strength the shape inference for aten.arange-like op by
1. registering aten.sub and aten.ceil.Scalar op and design folders for them.
2. register a new constant-like op: Torch::ConstantNumberOp and design canonicalizer for it.
This PR adds an `AllowedInModuleInitializer` trait to keep track of ops that are permitted in the module initializer. We have a handful of such ops that are produced by the IValue importer, and so this change avoids maintaining a list of ops in `TorchOps.cpp` that could lead to spurious merge conflicts, and help us integrate torch-mlir in our downstream compiler better. Please let me know if you'd prefer a better name for the trait itself. Feedback is welcome!
As @oroppas identified, literal strings that are over 16,380 characters
cause the MSVC compiler to throw an error (C2026), eventually causing
the Windows build of Torch-MLIR to fail because the length of the
generated MLIR for the shape library crosses the allowed threshold.
This patch fixes the problem by making the Python script generate one
literal string per line to satisfy the MSVC compiler.
Thanks to @oroppas for the bulk of the effort required to resolve this!
Summary of changes:
- Updated emitAccessorPrefix since the default value has changed
(https://reviews.llvm.org/D133179)
- Updated RefineTypes pass since Lattice::isUninitialized() is removed
(https://reviews.llvm.org/D132800)
- Updated MHLO tag so that it builds with the updated LLVM tag
- Disabled two tests that cause segfaults in the TOSA backend (see Issue
#1361)
* Add aten.frobenius_norm.dim op and init its conversion pattern to linalg and MHLO,
* run symbolic-shape-optimization before hlo-legalize-to-linalg to fit more mhlo e2e tests.
Summary of changes:
- Update the dataflow analysis in RefineTypes.cpp
- Add tosa-to-arith pass after tosa-to-linalg pass, since
tosa-to-linalg (and canonicalizations) can produce tosa.const() ops
- Fixed warning about not making `matchAndRewrite` as override
This commit adds decomposition of `aten.linear` op. Due to limited
support at tosa backend in case of dynamic dimensions, this
decomposition is currently disabled for tosa backend.
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
- Update MHLO commit to build with LLVM commit hash 00d648bd
- Update TorchToMhlo code to work with Stablehlo
- Re-enabled two failing TOSA tests, thus resolving Github Issue #1231
Caught in the wild here:
https://github.com/llvm/torch-mlir/runs/8046660640?check_suite_focus=true
It is common for a missing dependency to only surface as an issue on the
CI machines since they have fewer cores which prevents a "race" that
happens to cause the dependency to be built before the dependent.
An earlier patch (bb47c166) incorrectly replaced the now-dropped
`OpaqueElementsAttr` with `SparseElementsAttr` in one place and with
`DenseElementsAttr` in another. This patch fixes the problem by making
both replacements use the dense-equivalent type.
We were already hitting many cases where backends different in terms of
the legal ops that they wanted. This caused unnecessary coupling between
the backends. Examples:
- https://github.com/llvm/torch-mlir/pull/1161
- https://github.com/llvm/torch-mlir/pull/862
This PR centralizes all compilation to go through `torch_mlir.compile`
so that we can keep the logic centralized there. We should move these
lists closer to each backend. Especially cases like
https://github.com/llvm/torch-mlir/pull/862 where blocking a
decomposition is necessary to avoid a crash emphasize that the set of
decompositions is tightly coupled to the backend, and should be
"controlled by the backend" and not something arbitrarily tweakable.
Also:
- Fix a small bug in the way we passed through the backendLegalOps
option.
- Add better error messages in `torch_mlir.compile` for import errors.
One of the simplifications made by the pass `RefinePublicReturn`
currently only happens if the tensor in question only has one
user. However, the current method of checking this does not correctly
handle the case of a user having multiple uses of the same
tensor. This commit makes sure only unique users are considered.
This is a first step towards formalizing the set of ops in our backend
contract. The goal is to eventually formalize `torch` dialect ops into 3
categories:
1. Legal in backend contract
2. Illegal in backend contract
3. Conditionally legal in backend contract
The "conditionally legal" set are the ops that we can optionally
decompose for backends.
This patch adds relevant pass options for this throughout the compiler,
in preparation for a new set of traits which will formalize this
classification.
I recently fixed the handling of the `dim` argument in
`sum_mean_dim` (59fccab857). Therefore,
the checks that the `dim` input is `None` or `[]` are no longer needed.
This introduces a new pass LowerToBackendContract (better name very
welcome) which performs the bulk of the simplifications that we do,
such as
- shape refinement
- dtype refinement
- maximizing value semantics
- inlining global slots
- decomposing complex ops
The key difference from before is that it iterates the set of
transformations, which can help to break a number of "catch-22" issues
where one simplification depends on another, the latest example being
here:
https://github.com/llvm/torch-mlir/issues/1131
This also exposed that RefineTypes was sometimes crashing/asserting for
certain inputs. This commit hardens it a bit.
Bumps the shape library:
- Updates the function signature for aten.arange.start_step
- upstream_shape_functions.mean_dim -> upstream_shape_functions.sum_mean_dim
The Torch dialect has an include to `mlir/Dialect/Func/IR/FuncOps.h` and
should therefore have a CMake dependency to the MLIRFuncDialect.
Otherwise, the build can fail since it may occur that
`mlir/Dialect/Func/IR/FuncOps.h.inc` isn't generated yet.
Summary of changes:
- Switch to C++17 (similar to https://reviews.llvm.org/D131348)
- Update MHLO to build with LLVM commit hash 061e0189
- Replace deprecated `hasValue()` and `getValue()` with `has_value()`
and `value()` respectively (https://reviews.llvm.org/D131349)
- Use `TypedAttr` (https://reviews.llvm.org/D130092)
- Use updated assembly format of `mhlo.compare` op (commit
d03ef01e70fbf9afd0fa1976fbb7ed31838929b3 in MHLO repo)
Rather than a per-global-slot initializer region, we now have one for
the whole module. For example, it might look like this:
```
torch.global_slot "private" @tensor : !torch.tensor
torch.global_slot "private" @list : !torch.list<tensor>
torch.global_slot.module_initializer {
%0 = torch.tensor.literal(dense<0.0> : tensor<f32>) : !torch.tensor
%1 = torch.prim.ListConstruct %0 : (!torch.tensor) -> !torch.list<tensor>
torch.initialize.global_slots [
@tensor(%0 : !torch.tensor)
@list(%1 : !torch.list<tensor>)
]
}
```
This new structure allows GlobalizeObjectGraph to create the initializer in a
much simpler way, avoiding the need to reason about whether different slots
alias each other. Reasoning about whether slots alias each other now is the
responsibility of InlineGlobalSlots, which has to do a much more complicated
analysis, implemented using MLIR's dataflow analysis framework.
Recommended review order:
- Check out the new IR constructs in the .mlir files of various passes
- Op definitions (*.td)
- Changes to GlobalizeObjectGraph pass.
- InlineGlobalSlots pass (~total rewrite)
- Misc changes:
- Moving torchMlirAdjustStaticInformation for sharing with C++ code.
- EraseModuleInitializer pass
To make this a bit nicer, it would be good to have a `torch.module` op
with an initializer region attached. That would be more invasive though.
This change has highlighted certain aspects of our project layering
which are worth calling out. None of our backends can handle global
slots, so we enforce that there are no global slots before backend
lowering. At an earlier stage in the project, we had aspirations of
transparently handling mutable global state and such, but for reasons
described below, that is no longer a goal. So really global slots should
be seen as a progressive lowering step as part of inlining all the
IValue's in the original program (GlobalizeObjectGraph is also one such
step).
Over time, with insights from work like IREE-JAX, it has become clear
that there isn't a reliable programming model we can compile for users
where we just transparently handle mutable global state (and some other
things, like lists and dictionaries). There is a need for an "outer
program" that orchestrates more restricted subroutines of the kind we
can handle in our compile flow here. The benefit of that is that it
decouples considerations like shapes, dtypes, etc. from the program
constructs used in the outer program. As long as the outer program can
efficiently invoke (pipelining/async/etc.) high-performance
data-parallel numerical subroutines of the kind we compile in our flow
here, then there is a complete programming model. This is also
consistent with the direction of upstream PyTorch which is becoming more
tracing-based (which inherently loses a lot of program structure, which
then has to be applied back with an "outer program" orchestrating the
traced subroutines).
Vivek Khandelwal
Chi_Liu
Ramiro Leal-Cavazos
Prashant Kumar
Abhishek Varma
Gaurav Shukla
Ashay Rane
Gleb Kazantaev
Daniel Ellis
AmosLewis
JakopinA
Eric Kunze
武家伟
Quinn Dawkins
Tanyo Kwok
Sambhav Jain
long.chen
Sean Silva
gpetters94
Quinn Dawkins
Alex Tsao
Yan Xu
nithinsubbiah
Vidush Singhal
Ramana Radhakrishnan
Marius Brehler
powderluv