intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-01-23 07:58:23 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
c3579f01996a0ac018b9d452b8ae1cc2cac36acf
llvm/mlir/lib/Conversion
History
Sang Ik Lee c3579f0199 [MLIR][XeGPU][Conversion] Add 2D block op support for sub byte types (#169099) 
Some usage case or shapes for 2D block op with sub byte types can be
emulated with 2D block operations for non-sub byte types. Add sub byte
type i4 as a valid XeGPU type. And add lowering of certain 2D
block operations by emulating with larger element types.
2025-12-08 09:23:07 -08:00
..
AffineToStandard
…
AMDGPUToROCDL
[mlir][amdgpu] memory_counter_wait tensor counter support (#171153)
2025-12-08 20:02:40 +03:00
ArithCommon
…
ArithToAMDGPU
…
ArithToAPFloat
[mlir][arith] arith-to-apfloat: Add vector support (#171024)
2025-12-07 20:55:48 +01:00
ArithToArmSME
…
ArithToEmitC
…
ArithToLLVM
[mlir][arith] Fix arith.cmpf lowering with unsupported FP types (#166684)
2025-11-28 03:01:14 +00:00
ArithToSPIRV
…
ArmNeon2dToIntr
…
ArmSMEToLLVM
…
ArmSMEToSCF
…
AsyncToLLVM
…
BufferizationToMemRef
…
ComplexCommon
…
ComplexToLibm
…
ComplexToLLVM
Add 'exact' flag to arith.shrui/shrsi/divsi/divui operations (#165923)
2025-11-17 09:46:39 -08:00
ComplexToROCDLLibraryCalls
…
ComplexToSPIRV
…
ComplexToStandard
…
ControlFlowToLLVM
…
ControlFlowToSCF
…
ControlFlowToSPIRV
…
ConvertToEmitC
…
ConvertToLLVM
…
FuncToEmitC
…
FuncToLLVM
[mlir][LLVM] Resync memory effect attribute with LLVM IR (#168568)
2025-11-19 11:56:04 -05:00
FuncToSPIRV
…
GPUCommon
…
GPUToLLVMSPV
[mlir][LLVM] Resync memory effect attribute with LLVM IR (#168568)
2025-11-19 11:56:04 -05:00
GPUToNVVM
[MLIR][GPU] subgroup_mma fp64 extension - take 2 (#169061)
2025-12-01 07:39:59 -05:00
GPUToROCDL
…
GPUToSPIRV
…
IndexToLLVM
…
IndexToSPIRV
[MLIR] Apply clang-tidy fixes for readability-identifier-naming in IndexToSPIRV.cpp (NFC)
2025-12-04 05:01:03 -08:00
LinalgToStandard
…
LLVMCommon
[mlir][arith] Fix arith.cmpf lowering with unsupported FP types (#166684)
2025-11-28 03:01:14 +00:00
MathToEmitC
…
MathToFuncs
…
MathToLibm
…
MathToLLVM
…
MathToROCDL
…
MathToSPIRV
…
MathToXeVM
…
MemRefToEmitC
[mlir][emitc] Add address-of and dereference ops (#72569)
2025-12-03 12:41:29 +02:00
MemRefToLLVM
…
MemRefToSPIRV
…
MPIToLLVM
[MLIR] Apply clang-tidy fixes for readability-avoid-const-params-in-decls in MPIToLLVM.cpp (NFC)
2025-11-28 05:35:44 -08:00
NVGPUToNVVM
[MLIR][NVVM] Update mbarrier.arrive.expect_tx Op (#169922)
2025-12-01 22:19:34 +05:30
NVVMToLLVM
…
OpenACCToSCF
…
OpenMPToLLVM
[mlir][OpenMP] Fix crash in MapInfoOp conversion when type conversion fails (#171045)
2025-12-08 17:30:22 +01:00
PDLToPDLInterp
…
PtrToLLVM
…
ReconcileUnrealizedCasts
…
SCFToControlFlow
[mlir][SCF] Add pass option to deactivate pattern rollback (#168481)
2025-11-18 16:08:27 +08:00
SCFToEmitC
…
SCFToGPU
[MLIR][SCFToGPU] Guard operands before AffineApplyOp::create to avoid crash (#167959)
2025-11-20 22:20:34 +08:00
SCFToOpenMP
[OpenMP][flang] Add initial support for by-ref reductions on the GPU (#165714)
2025-11-26 11:59:22 +01:00
SCFToSPIRV
…
ShapeToStandard
…
ShardToMPI
…
SPIRVCommon
…
SPIRVToLLVM
[MLIR][SPIRV] Lower SPIR-V Tan/Tanh ops to LLVM intrinsics (#168419)
2025-11-18 06:31:46 -05:00
TensorToLinalg
…
TensorToSPIRV
…
TosaToArith
…
TosaToLinalg
…
TosaToMLProgram
…
TosaToSCF
…
TosaToTensor
…
UBToLLVM
[mlir][UB] Add ub.unreachable operation (#169872)
2025-11-28 10:35:18 +00:00
UBToSPIRV
[mlir][UB] Add ub.unreachable operation (#169872)
2025-11-28 10:35:18 +00:00
VectorToAMX
…
VectorToArmSME
…
VectorToGPU
…
VectorToLLVM
…
VectorToSCF
…
VectorToSPIRV
…
VectorToXeGPU
[MLIR][XeGPU] Retain anchor op layouts for XeGPU nD ops (#170934)
2025-12-05 21:49:13 -08:00
XeGPUToXeVM
[MLIR][XeGPU][Conversion] Add 2D block op support for sub byte types (#169099)
2025-12-08 09:23:07 -08:00
XeVMToLLVM
[MLIR] Apply clang-tidy fixes for llvm-qualified-auto in XeVMToLLVM.cpp (NFC)
2025-12-05 05:20:52 -08:00
CMakeLists.txt
…