asraa c66b72f8ce [mlir][tensor] remove tensor.insert constant folding out of canonicalization (#142671) ...

Follow ups from https://github.com/llvm/llvm-project/pull/142458/
In particular concerns that indiscriminately folding tensor constants
can lead to bloating the IR as these can be arbitrarily large.

Signed-off-by: Asra Ali <asraa@google.com>

2025-06-05 14:53:33 -07:00

..

CMakeLists.txt

[mlir][tensor] Add runtime verification for cast/dim/extract/insert/extract_slice (#141332)

2025-06-05 12:06:47 +09:00

TensorDialect.cpp

[mlir][tensor] Add runtime verification for cast/dim/extract/insert/extract_slice (#141332)

2025-06-05 12:06:47 +09:00

TensorInferTypeOpInterfaceImpl.cpp

[mlir][Tensor] Rework ReifyRankedShapedTypeInterface implementation for tensor.expand_shape op. (#113501)

2025-01-27 07:05:34 -08:00

TensorOps.cpp

[mlir][tensor] remove tensor.insert constant folding out of canonicalization (#142671)

2025-06-05 14:53:33 -07:00

TensorTilingInterfaceImpl.cpp

[mlir][NFC] Simplify constant checks with isOneInteger and renamed isZeroInteger. (#139340)

2025-05-20 14:53:02 -07:00

ValueBoundsOpInterfaceImpl.cpp

[mlir][ValueBounds] memref.dim and tensor.dim are always positive (#122804)

2025-01-13 17:48:03 -06:00