Peiming Liu b9589545c4 [mlir][sparse] introduce a new compressed(hi) dimension level type ...

`compressed(hi)` is similar to `compressed`, but instead of reusing the previous position high as the current position low, it uses a pair of positions for each sparse index.

The patch only introduces the definition (syntax) but does not provide codegen implementation.

Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D148664

2023-04-18 23:26:11 +00:00

..

AsyncPasses.cpp

…

DialectLinalg.cpp

…

DialectPDL.cpp

…

DialectQuant.cpp

…

DialectSparseTensor.cpp

[mlir][sparse] introduce a new compressed(hi) dimension level type

2023-04-18 23:26:11 +00:00

DialectTransform.cpp

…

ExecutionEngineModule.cpp

…

Globals.h

…

GPUPasses.cpp

…

IRAffine.cpp

[mlir][python] Mark operator== overloads as const

2023-03-28 11:06:13 -04:00

IRAttributes.cpp

[mlir] Remove unused using llvm::Twine declaration (NFC).

2023-04-17 13:15:45 +02:00

IRCore.cpp

[MLIR][python bindings] implement PyValue subclassing to enable operator overloading

2023-04-14 14:25:06 -05:00

IRInterfaces.cpp

…

IRModule.cpp

…

IRModule.h

[mlir][python] Mark operator== overloads as const

2023-03-28 11:06:13 -04:00

IRTypes.cpp

Fix mlir/lib/Bindings/Python/IRTypes.cpp for Float8E4M3B11FNUZType

2023-03-24 20:42:47 +00:00

LinalgPasses.cpp

…

MainModule.cpp

…

Pass.cpp

…

Pass.h

…

PybindUtils.cpp

…

PybindUtils.h

…

RegisterEverything.cpp

…

SparseTensorPasses.cpp

…