caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
f2e7285b03fbfc263c8a2eaa2b5e2e1cfafc6abd
clang-p2996/mlir/lib/Conversion
History
Cullen Rhodes 781883ea62 [mlir][ArmSME] Split lowering of arith.constant from vector.transfer_write 
An 'arith.constant dense<0>' is currently lowered to 'arm_sme.zero' as
part of the 'vector.transfer_write' lowering during '-vector-to-arm-sme'
conversion. This patch makes this lowering independent of the
'vector.transfer_write'. This can then be extended for further tile
types and non-zero constants.

Reviewed By: awarzynski

Differential Revision: https://reviews.llvm.org/D156802
2023-08-03 08:57:33 +00:00
..
AffineToStandard
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
AMDGPUToROCDL
[mlir][LLVM] NFC - Remove createIndexConstant method
2023-08-02 07:24:29 +00:00
ArithCommon
…
ArithToLLVM
[mlir][Arith] Add arith.is_nan and arith.is_inf predicates
2023-08-02 14:42:25 +00:00
ArithToSPIRV
[mlir][Arith] Add arith.is_nan and arith.is_inf predicates
2023-08-02 14:42:25 +00:00
ArmNeon2dToIntr
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
ArmSMEToSCF
[mlir][ArmSME] Use memref indices for load and store
2023-08-03 08:50:12 +00:00
AsyncToLLVM
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
BufferizationToMemRef
[mlir][bufferization] Add lowering of bufferization.dealloc to memref.dealloc
2023-07-19 14:28:01 +00:00
ComplexToLibm
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
ComplexToLLVM
[mlir] Port Conversion Passes to LLVM to use TableGen generated constructors and options
2023-02-10 20:47:18 +01:00
ComplexToSPIRV
[mlir][spirv] Improve integer cast during type conversion
2023-07-12 14:38:11 -07:00
ComplexToStandard
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
ControlFlowToLLVM
[mlir] Port Conversion Passes to LLVM to use TableGen generated constructors and options
2023-02-10 20:47:18 +01:00
ControlFlowToSPIRV
…
FuncToLLVM
[mlir][llvm] Add comdat attribute to functions
2023-06-27 07:26:59 +00:00
FuncToSPIRV
…
GPUCommon
[mlir][LLVM] NFC - Remove createIndexConstant method
2023-08-02 07:24:29 +00:00
GPUToNVVM
[MLIR] Provide bare pointer memref lowering option on gpu-to-nvvm pass
2023-06-18 22:53:50 +05:30
GPUToROCDL
[MLIR][ROCDL] Add conversion for gpu.lane_id to ROCDL
2023-07-26 15:12:48 +00:00
GPUToSPIRV
[mlir][gpu] Support arith.extf in subgroup MMA elementwise ops
2023-08-01 21:12:37 -07:00
GPUToVulkan
[mlir][GPU] Rename MLIRGPUOps CMake target to MLIRGPUDialect
2023-05-16 14:25:08 +02:00
IndexToLLVM
…
LinalgToStandard
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
LLVMCommon
[mlir][LLVM] NFC - Remove createIndexConstant method
2023-08-02 07:24:29 +00:00
MathToFuncs
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
MathToLibm
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
MathToLLVM
[mlir][llvm] Ensure immediate usage in intrinsics
2023-06-12 06:57:42 +00:00
MathToSPIRV
[mlir][spirv] Improve integer cast during type conversion
2023-07-12 14:38:11 -07:00
MemRefToLLVM
[mlir][LLVM] NFC - Remove createIndexConstant method
2023-08-02 07:24:29 +00:00
MemRefToSPIRV
[mlir][spirv] memref.cast to SPIR-V conversion
2023-07-26 13:20:21 +02:00
NVGPUToNVVM
[mlir] Fix build after D155680
2023-07-21 13:33:54 +02:00
NVVMToLLVM
[mlir][nvvm] Add populate function (nfc)
2023-07-13 14:53:51 +02:00
OpenACCToSCF
[mlir][NFC] Avoid OpBuilder::setListener when possible
2023-07-19 09:13:38 +02:00
OpenMPToLLVM
Add OpenMPToLLVM conversion pattern for taskgroup
2023-05-24 11:25:38 +01:00
PDLToPDLInterp
[mlir] Move casting calls from methods to function calls
2023-05-26 10:29:55 +02:00
ReconcileUnrealizedCasts
…
SCFToControlFlow
[mlir][IR] Clean up mergeBlockBefore and mergeBlocks
2023-03-06 13:46:08 +01:00
SCFToGPU
[mlir][NFC] Use getConstantIntValue instead of casting to ConstantIndexOp
2023-07-04 14:08:37 +02:00
SCFToOpenMP
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
SCFToSPIRV
[mlir][spirv] Fix scf.yield pattern conversion
2023-03-14 18:47:34 -04:00
ShapeToStandard
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
SPIRVCommon
[mlir][spirv] Allow vectors of index types in elementwise conversions
2023-03-17 13:33:56 -04:00
SPIRVToLLVM
[mlir][llvm] Add branch weight op interface
2023-07-20 10:46:04 +00:00
TensorToLinalg
…
TensorToSPIRV
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
TosaToArith
[mlir] Move casting calls from methods to function calls
2023-05-12 11:21:25 +02:00
TosaToLinalg
TOSA-to-Linalg lowering for element-wise ops
2023-07-21 22:08:33 +00:00
TosaToSCF
Lowering for 'tosa.scatter'
2023-05-30 14:28:52 -07:00
TosaToTensor
[MLIR] [TOSA]: Move reshape(reshape(x)) -> reshape(x) from canonicalization to fold
2023-07-17 10:14:37 +02:00
UBToLLVM
[mlir] Convert ub.poison to llvm.poison
2023-07-24 18:40:12 +02:00
UBToSPIRV
[mlir][spirv] Convert ub.poison to spirv.undef
2023-07-25 00:23:09 +02:00
VectorToArmSME
[mlir][ArmSME] Split lowering of arith.constant from vector.transfer_write
2023-08-03 08:57:33 +00:00
VectorToGPU
[mlir][gpu] Support arith.extf in subgroup MMA elementwise ops
2023-08-01 21:12:37 -07:00
VectorToLLVM
[mlir][vector] Improve lowering to LLVM for minf, maxf reductions
2023-08-02 20:26:59 +03:00
VectorToSCF
[mlir][vector] Use DenseI64ArrayAttr for ExtractOp/InsertOp positions
2023-07-31 15:25:37 +02:00
VectorToSPIRV
[mlir][spirv][vector] Fix vector shuffle conversion for scalar inputs
2023-07-31 20:13:30 -04:00
CMakeLists.txt
[mlir][ArmSME] Add conversion from ArmSME to SCF to materialize loops
2023-08-01 08:20:02 +00:00