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`.
Attempt to solve https://github.com/llvm/torch-mlir/issues/2490
Changes for Non Value Semantic Ops having the
`IsTrailingUnderscoreInplaceVariant` trait :
- AnyTorchTensorType -> Torch_NonValueTensorType
- AnyTorchOptionalTensorType -> AnyTorchOptionalNonValueTensorType
- AnyTorchListOfOptionalTensorType ->
AnyTorchListOfOptionalNonValueTensorType
- AnyTorchListOfTensorType -> AnyTorchListOfNonValueTensorType
Created three new tensor types for optional and list non value tensors.
The last llvm bump in https://github.com/llvm/torch-mlir/pull/2511
pointed to
b44b3494f6,
however the bazel build upstream was not clean at this point:
```
ERROR: /root/.cache/bazel/_bazel_root/b89349c08f7224396763d14fe35cba11/external/llvm-project/mlir/BUILD.bazel:5837:18: TdGenerate
external/llvm-project/mlir/include/mlir/Dialect/LLVMIR/NVVMOpsInterface.h.inc failed: (Exit 1): mlir-tblgen failed: error executing command ...
external/llvm-project/mlir/include/mlir/Dialect/LLVMIR/NVVMOps.td:20:9: error: Could not find include file 'mlir/Dialect/LLVMIR/BasicPtxBuilderInterface.td'
include "mlir/Dialect/LLVMIR/BasicPtxBuilderInterface.td"
^
external/llvm-project/mlir/include/mlir/Dialect/LLVMIR/NVVMOps.td:20:9: error: Unexpected token at top level
include "mlir/Dialect/LLVMIR/BasicPtxBuilderInterface.td"
^
```
The bazel fixes followed in a subsequent commit at
28b27c1b10.
This PR bumps LLVM by a few more commits (to include the bazel fixes)
which helps restore Torch-MLIR's bazel build back to 🟢 .
GHA workflow to test bazel build:
https://github.com/sjain-stanford/torch-mlir/actions/runs/6555101471/job/17803082508
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>
Strict symbolic shapes allow us to assume numpy-style dynamic broadcasts
never occur. This allows us to strengthen the folder for broadcasts to
cases where the rank is the same and all shapes match (including dynamic
sentinel values).
Add linspace/cumprod/roll ops to ODS and add shape inference functions
to make it work with LTC.
Also, add some tensor utils to LTC library for searching for non-detach
copy nodes.
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.
Stella Laurenzo
Yuanqiang Liu
saienduri
Sambhav Jain
Zhekun(Josh) Zhang
Daniel Garvey
xiaolou86
JianzheXiao
Ze Zhang
Sarthak Gupta
Vivek Khandelwal
Chi_Liu
Ramiro Leal-Cavazos
Quinn Dawkins
Jae Hoon (Antonio) Kim