intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-01-26 12:26:52 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
889f4bf26406d22e24b7e85bb4f6a8eb57d04fb7
llvm/mlir/lib/Conversion
History
Giuseppe Rossini 4b3eaee270 [mlir][AMDGPU] Define wrappers for WMMA matrix ops 
Wave Matrix Multiply Accumulate (WMMA) is the instruction to accelerate
matrix multiplication on RDNA3 architectures.  LLVM already provides a
set of intrinsics to generate wmma instructions. This change uses those
intrinsics to enable the feature in MLIR.

Reviewed By: krzysz00

Differential Revision: https://reviews.llvm.org/D152451
2023-07-20 18:38:35 +00:00
..
AffineToStandard
…
AMDGPUToROCDL
[mlir][AMDGPU] Define wrappers for WMMA matrix ops
2023-07-20 18:38:35 +00:00
ArithCommon
…
ArithToLLVM
…
ArithToSPIRV
[mlir][spirv] Improve integer cast during type conversion
2023-07-12 14:38:11 -07:00
ArmNeon2dToIntr
…
AsyncToLLVM
…
BufferizationToMemRef
[mlir][bufferization] Add lowering of bufferization.dealloc to memref.dealloc
2023-07-19 14:28:01 +00:00
ComplexToLibm
…
ComplexToLLVM
…
ComplexToSPIRV
[mlir][spirv] Improve integer cast during type conversion
2023-07-12 14:38:11 -07:00
ComplexToStandard
…
ControlFlowToLLVM
…
ControlFlowToSPIRV
…
FuncToLLVM
[mlir][llvm] Add comdat attribute to functions
2023-06-27 07:26:59 +00:00
FuncToSPIRV
…
GPUCommon
[mlir][sparse][gpu] force 16-byte alignment on data structs for cuSparseLt
2023-07-13 10:45:15 -07:00
GPUToNVVM
[MLIR] Provide bare pointer memref lowering option on gpu-to-nvvm pass
2023-06-18 22:53:50 +05:30
GPUToROCDL
…
GPUToSPIRV
…
GPUToVulkan
…
IndexToLLVM
…
LinalgToLLVM
…
LinalgToStandard
…
LLVMCommon
[mlir][nfc] Clarify the limitation on scalable vectors
2023-07-19 07:00:35 +00:00
MathToFuncs
…
MathToLibm
…
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] Ensure immediate usage in intrinsics
2023-06-12 06:57:42 +00:00
MemRefToSPIRV
[mlir][spirv] Lower memref.reinterpret_cast
2023-07-13 15:54:21 +02:00
NVGPUToNVVM
[mlir][nvgpu] Add mbarrier.arrive.expect_tx and mbarrier.try_wait.parity
2023-07-20 13:48:30 +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
…
PDLToPDLInterp
…
ReconcileUnrealizedCasts
…
SCFToControlFlow
…
SCFToGPU
[mlir][NFC] Use getConstantIntValue instead of casting to ConstantIndexOp
2023-07-04 14:08:37 +02:00
SCFToOpenMP
…
SCFToSPIRV
…
ShapeToStandard
…
SPIRVCommon
…
SPIRVToLLVM
[mlir][llvm] Add branch weight op interface
2023-07-20 10:46:04 +00:00
TensorToLinalg
…
TensorToSPIRV
…
TosaToArith
…
TosaToLinalg
[mlir][linalg] Remove redundant dimension size helper functions
2023-07-03 09:07:18 +02:00
TosaToSCF
…
TosaToTensor
[MLIR] [TOSA]: Move reshape(reshape(x)) -> reshape(x) from canonicalization to fold
2023-07-17 10:14:37 +02:00
VectorToArmSME
[mlir][ArmSME] Introduce new lowering layer (Vector -> ArmSME)
2023-07-18 08:04:59 +00:00
VectorToGPU
[mlir][affine] More efficient makeComposedFolded... helpers
2023-06-22 10:47:38 +02:00
VectorToLLVM
[mlir][ArmSME] Introduce custom TypeConverter for ArmSME
2023-07-18 09:35:32 +00:00
VectorToSCF
[mlir][IR] Remove duplicate isLastMemrefDimUnitStride functions
2023-07-17 16:31:04 +02:00
VectorToSPIRV
[mlir][spirv] Improve integer cast during type conversion
2023-07-12 14:38:11 -07:00
CMakeLists.txt
[mlir][ArmSME] Introduce new lowering layer (Vector -> ArmSME)
2023-07-18 08:04:59 +00:00