shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
llvm-project/mlir/lib/Conversion
History
Erick Ochoa Lopez 9d19250610
[mlir][vector] Add vector.to_elements unrolling (#157142) 
This PR adds support for unrolling `vector.to_element`'s source operand.

It transforms

```mlir
%0:8 = vector.to_elements %v : vector<2x2x2xf32>
```

to

```mlir
%v0 = vector.extract %v[0] : vector<2x2xf32> from vector<2x2x2xf32>
%v1 = vector.extract %v[1] : vector<2x2xf32> from vector<2x2x2xf32>
%0:4 = vector.to_elements %v0 : vector<2x2xf32>
%1:4 = vector.to_elements %v1 : vector<2x2xf32>
// %0:8 = %0:4 - %1:4
```

This pattern will be applied until there are only 1-D vectors left.

---------

Signed-off-by: hanhanW <hanhan0912@gmail.com>
Co-authored-by: hanhanW <hanhan0912@gmail.com>
Co-authored-by: Jakub Kuderski <kubakuderski@gmail.com>
2025-09-11 13:56:57 -04:00
..
AffineToStandard
[mlir][NFC] update Conversion create APIs (4/n) (#149879)
2025-07-23 10:49:35 -05:00
AMDGPUToROCDL
[mlir][amdgpu] Promote gpu.shuffle to amdgpu.permlane_swap (#154933)
2025-08-24 12:41:09 +02:00
ArithCommon
…
ArithToAMDGPU
[mlir][ArithToAMDGPU] Use native packing support (#150342)
2025-07-24 12:26:03 -05:00
ArithToArmSME
[mlir][NFC] update Conversion create APIs (4/n) (#149879)
2025-07-23 10:49:35 -05:00
ArithToEmitC
[mlir][emitc] Isolate expressions from above (#155641)
2025-09-01 15:10:17 +03:00
ArithToLLVM
[mlir][LLVM] ArithToLLVM: Add 1:N support for arith.select lowering (#153944)
2025-08-18 09:42:37 +02:00
ArithToSPIRV
[mlir][spirv] Add pattern matching for arith.index_cast i1 to index for ArithToSPIRV (#155729)
2025-09-03 14:04:35 -04:00
ArmNeon2dToIntr
[mlir] Remove unused includes (NFC) (#150476)
2025-07-24 11:23:53 -07:00
ArmSMEToLLVM
[mlir][armsme][vector] Replace splat with broadcast (#148024)
2025-07-23 10:18:09 -07:00
ArmSMEToSCF
[mlir][sme] Use signed comparison in ArmSMEToSCF (#156834)
2025-09-05 08:58:52 +01:00
AsyncToLLVM
[mlir] Remove unused includes (NFC) (#150476)
2025-07-24 11:23:53 -07:00
BufferizationToMemRef
[mlir][NFC] update mlir create APIs (34/n) (#150660)
2025-07-25 12:36:54 -05:00
ComplexCommon
[mlir][NFC] update Conversion create APIs (5/n) (#149887)
2025-07-22 10:40:45 -04:00
ComplexToLibm
[mlir][NFC] update Conversion create APIs (5/n) (#149887)
2025-07-22 10:40:45 -04:00
ComplexToLLVM
[mlir][NFC] update Conversion create APIs (5/n) (#149887)
2025-07-22 10:40:45 -04:00
ComplexToROCDLLibraryCalls
[mlir] Use free op create functions. NFC. (#157374)
2025-09-07 22:13:20 -04:00
ComplexToSPIRV
[mlir] Remove unused includes (NFC) (#147101)
2025-07-04 13:30:21 -07:00
ComplexToStandard
[mlir] Remove unused includes (NFC) (#150476)
2025-07-24 11:23:53 -07:00
ControlFlowToLLVM
[mlir][LLVM] Fix build (#153947)
2025-08-16 13:06:58 +02:00
ControlFlowToSCF
[mlir][NFC] update mlir create APIs (34/n) (#150660)
2025-07-25 12:36:54 -05:00
ControlFlowToSPIRV
[mlir][spirv] Add 8-bit float type emulation (#148811)
2025-07-30 17:39:49 -05:00
ConvertToEmitC
[mlir] Remove unused includes (NFC) (#150476)
2025-07-24 11:23:53 -07:00
ConvertToLLVM
[mlir][ToLLVM] Fix the index bitwidth handling for the dynamic case of convert-to-llvm (#156557)
2025-09-03 08:07:18 -04:00
FuncToEmitC
[mlir][NFC] update Conversion create APIs (5/n) (#149887)
2025-07-22 10:40:45 -04:00
FuncToLLVM
[mlir][Transforms] Add support for ConversionPatternRewriter::replaceAllUsesWith (#155244)
2025-09-06 11:17:55 +02:00
FuncToSPIRV
[mlir][spirv] Add 8-bit float type emulation (#148811)
2025-07-30 17:39:49 -05:00
GPUCommon
[mlir][vector] fix: unroll vector.from_elements in gpu pipelines (#154774)
2025-08-21 21:46:06 -05:00
GPUToLLVMSPV
[mlir][NFC] update Conversion create APIs (5/n) (#149887)
2025-07-22 10:40:45 -04:00
GPUToNVVM
[MLIR] Apply clang-tidy fixes for llvm-qualified-auto in LowerGpuOpsToNVVMOps.cpp (NFC)
2025-08-27 12:18:04 -07:00
GPUToROCDL
[mlir][gpu] Refactor GpuOpsToROCDLOps pass interface (NFC) (#157402)
2025-09-10 09:04:34 +02:00
GPUToSPIRV
[mlir][spirv] Fix lookup logic spirv.target_env for gpu.module (#147262)
2025-08-01 06:54:04 -04:00
IndexToLLVM
[mlir][NFC] update Conversion create APIs (6/n) (#149888)
2025-07-22 08:16:53 -04:00
IndexToSPIRV
[mlir][NFC] update Conversion create APIs (6/n) (#149888)
2025-07-22 08:16:53 -04:00
LinalgToStandard
[mlir][NFC] update Conversion create APIs (6/n) (#149888)
2025-07-22 08:16:53 -04:00
LLVMCommon
[mlir][LLVM] FuncToLLVM: Add 1:N type conversion support (#153823)
2025-08-16 09:45:08 +02:00
MathToEmitC
[mlir][EmitC] Add MathToEmitC pass for math function lowering to EmitC (#113799)
2025-01-20 09:26:41 +01:00
MathToFuncs
[MLIR] Migrate some conversion passes and dialects to LDBG() macro (NFC) (#151349)
2025-07-30 17:58:54 +02:00
MathToLibm
[mlir][NFC] update Conversion create APIs (6/n) (#149888)
2025-07-22 08:16:53 -04:00
MathToLLVM
[mlir][NFC] update Conversion create APIs (6/n) (#149888)
2025-07-22 08:16:53 -04:00
MathToROCDL
[MLIR] Migrate some conversion passes and dialects to LDBG() macro (NFC) (#151349)
2025-07-30 17:58:54 +02:00
MathToSPIRV
[MLIR][SPIRV] Add spirv.IsFinite and lower math.{isfinite,isinf,isnan} to spirv. (#151552)
2025-07-31 13:54:14 -04:00
MemRefToEmitC
[mlir] Update builders to use new form. (#154132)
2025-08-18 15:19:34 +00:00
MemRefToLLVM
[mlir][LLVM][NFC] Simplify computeSizes function (#153588)
2025-08-14 17:00:03 +02:00
MemRefToSPIRV
[mlir] MemRefToSPIRV propagate alignment attributes from MemRef ops. (#151723)
2025-08-07 12:18:23 -04:00
MPIToLLVM
[mlir] Fix possible null dereference during error logging (#157455)
2025-09-10 09:10:11 +08:00
NVGPUToNVVM
[MLIR][NVVM][NVGPU] Combine prefetch and prefetch.tensormap (#153134)
2025-09-01 15:56:31 +05:30
NVVMToLLVM
[MLIR][NVVM] Support packed registers in inline_ptx (#154904)
2025-09-02 14:15:55 +02:00
OpenACCToSCF
[mlir][NFC] update Conversion create APIs (6/n) (#149888)
2025-07-22 08:16:53 -04:00
OpenMPToLLVM
[mlir][NFC] update Conversion create APIs (6/n) (#149888)
2025-07-22 08:16:53 -04:00
PDLToPDLInterp
[MLIR] Apply clang-tidy fixes for misc-use-internal-linkage in PredicateTree.cpp (NFC)
2025-08-27 03:17:18 -07:00
PtrToLLVM
[MLIR] fix LLVM::InsertValueOp::create
2025-09-07 22:23:12 -04:00
ReconcileUnrealizedCasts
[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)
2025-02-17 10:55:27 +01:00
SCFToControlFlow
[mlir][SCF] scf.for: Add support for unsigned integer comparison (#153379)
2025-08-15 10:59:14 +02:00
SCFToEmitC
[mlir][SCF] scf.for: Add support for unsigned integer comparison (#153379)
2025-08-15 10:59:14 +02:00
SCFToGPU
[MLIR] Add missing include to SCFToGPU.cpp (NFC)
2025-08-23 04:55:33 -07:00
SCFToOpenMP
[flang][OpenMP] Enable tiling (#143715)
2025-09-10 09:25:40 -04:00
SCFToSPIRV
[mlir][SCF] scf.for: Add support for unsigned integer comparison (#153379)
2025-08-15 10:59:14 +02:00
ShapeToStandard
[mlir] Remove unused includes (NFC) (#150476)
2025-07-24 11:23:53 -07:00
ShardToMPI
[MLIR] Apply clang-tidy fixes for llvm-qualified-auto in ShardToMPI.cpp (NFC)
2025-08-27 14:39:23 -07:00
SPIRVCommon
[MLIR][GPU-LLVM] Convert gpu.func to llvm.func (#101664)
2024-08-09 16:09:11 +02:00
SPIRVToLLVM
[mlir][NFC] update mlir create APIs (34/n) (#150660)
2025-07-25 12:36:54 -05:00
TensorToLinalg
[mlir] Remove unused includes (NFC) (#147101)
2025-07-04 13:30:21 -07:00
TensorToSPIRV
[mlir][spirv] Add 8-bit float type emulation (#148811)
2025-07-30 17:39:49 -05:00
TosaToArith
[mlir][tosa] Convert TOSA enumerations from StringBasedAttr to Tosa_I32EnumAttr (#152856)
2025-08-29 15:13:17 +01:00
TosaToLinalg
[mlir] Use free op create functions. NFC. (#157374)
2025-09-07 22:13:20 -04:00
TosaToMLProgram
[mlir] Remove unused includes (NFC) (#150476)
2025-07-24 11:23:53 -07:00
TosaToSCF
[mlir][NFC] update Conversion create APIs (7/n) (#149889)
2025-07-22 10:41:06 -04:00
TosaToTensor
[mlir][tosa] Use typeConverter->convertType<T> (#150578)
2025-08-04 17:28:31 +08:00
UBToLLVM
[mlir][NFC] Mark type converter in populate... functions as const (#111250)
2024-10-05 21:32:40 +02:00
UBToSPIRV
[mlir][spirv] Fix some issues related to converting ub.poison to SPIR-V (#125905)
2025-02-06 19:07:34 +01:00
VectorToAMX
[mlir][amx] Direct AMX data transfers (#154114)
2025-08-27 08:54:54 +02:00
VectorToArmSME
[mlir][armsme][vector] Replace splat with broadcast (#148024)
2025-07-23 10:18:09 -07:00
VectorToGPU
[MLIR] Migrate some conversion passes and dialects to LDBG() macro (NFC) (#151349)
2025-07-30 17:58:54 +02:00
VectorToLLVM
[mlir][vector] Add vector.to_elements unrolling (#157142)
2025-09-11 13:56:57 -04:00
VectorToSCF
[mlir][Vector] Remove vector.extractelement and vector.insertelement ops (#149603)
2025-07-28 11:01:14 -07:00
VectorToSPIRV
[mlir][spirv][vector] Use adaptor.getElements() in FromElements lowering. (#156972)
2025-09-04 16:06:33 -07:00
VectorToXeGPU
[MLIR][XeGPU] Add lowering from transfer_read/transfer_write to load_gather/store_scatter (#152429)
2025-08-14 11:27:07 -07:00
XeGPUToXeVM
[MLIR][Conversion] Convert XeGPU to XeVM pass: Remove lowering support for tensor descriptor with offsets. (#157550)
2025-09-10 15:43:03 -07:00
XeVMToLLVM
[MLIR][XeVM] Add lowering for llvm load store ops with XeVM cache control (#156768)
2025-09-09 09:12:16 -07:00
CMakeLists.txt
[mlir][ptr] Add conversion to LLVM for all existing ptr ops (#156053)
2025-08-29 16:57:48 +00:00