llvm-project/Conversion at 890c4bece26e005cd9fa5511fe0efa7307794de5 - llvm-project - shylie's gitea

shylie/llvm-project

History

Manupa Karunaratne a6e72f9392

[MLIR][Vector] Add Lowering for vector.step (#113655 )

Currently, the lowering for vector.step lives
under a folder. This is not ideal if we want
to do transformation on it and defer the
 materizaliztion of the constants much later.

This commits adds a rewrite pattern that
could be used by using
`transform.structured.vectorize_children_and_apply_patterns`
transform dialect operation.

Moreover, the rewriter of vector.step is also
now used in -convert-vector-to-llvm pass where
it handles scalable and non-scalable types as
LLVM expects it.

As a consequence of removing the vector.step
lowering as its folder, linalg vectorization
will keep vector.step intact.

2024-11-01 16:38:36 +00:00

..

AffineToStandard

[mlir][affine] Enable ConvertAffineToStandard pass to handle affine.delinearize_index Op. (#82189 )

2024-02-28 18:58:53 +05:30

[mlir][AMDGPU] Support vector<2xbf16> packed atomic fadd (#113929 )

2024-10-31 10:52:53 -05:00

[MLIR][AMDGPU] Introduce fp16 packed arithmetic (#105688 )

2024-08-26 12:48:57 -05:00

[mlir][ArmSME] Rename slice move operations to insert/extract_tile_slice (#106755 )

2024-09-02 11:12:40 +01:00

[mlir] Support emit fp16 and bf16 type to cpp (#105803 )

2024-08-27 16:56:46 +08:00

[mlir][arith] Remove some e2e tests (#112012 )

2024-10-16 07:43:49 +01:00

[mlir][test] XFAIL little-endian-only tests on SPARC (#103726 )

2024-08-15 10:02:41 +02:00

[mlir][ArmSME] Rename slice move operations to insert/extract_tile_slice (#106755 )

2024-09-02 11:12:40 +01:00

[mlir][ArmSME] Rename slice move operations to insert/extract_tile_slice (#106755 )

2024-09-02 11:12:40 +01:00

[MLIR][AsyncToLLVM] Remove typed pointer support (#70731 )

2023-10-31 07:36:32 +01:00

BufferizationToMemRef

[mlir][bufferization] Unranked memref support for clone (#94757 )

2024-06-13 09:58:00 -04:00

[mlir][complex] Convert complex.tan to libm ctan call (#78250 )

2024-01-18 12:21:19 +09:00

[mlir][complex] Initial support for FastMath flag when converting to LLVM

2023-08-21 10:41:55 +09:00

[mlir][spirv][complex] Support convert complex.constant

2023-05-29 17:54:28 -07:00

ComplexToStandard

Fix complex abs with nnan/ninf. (#95080 )

2024-06-11 13:44:29 +02:00

ControlFlowToLLVM

[MLIR][ControlFlowToLLVM] Remove typed pointer support (#70733 )

2023-10-31 07:36:46 +01:00

ControlFlowToSCF

[mlir][cfg-to-scf] Fix invalid transformation when value is used in a subregion (#67544 )

2023-09-27 14:02:54 +02:00

ControlFlowToSPIRV

[mlir][spirv][cf] legalize block arguments when convert cf to spirv (#71288 )

2023-11-04 23:48:59 -04:00

[mlir][spirv] Integrate convert-to-spirv into mlir-vulkan-runner (#106082 )

2024-08-27 12:16:54 -04:00

[mlir][EmitC] Fix call ops with zero arguments in func to emitc conversion (#94936 )

2024-06-10 13:40:24 +02:00

[mlir] Rename memory attribute to memory_effects in llvmir dialect (#100108 )

2024-07-23 14:17:05 +02:00

[mlir][affine] Fix dim index out of bounds crash (#73266 )

2023-11-28 07:35:09 +01:00

[MLIR][AMDGPU] Add ability to do 16-bit Memset with HIP APIs (#108587 )

2024-09-20 09:53:41 -05:00

[MLIR][GPU-LLVM] Add in-pass signature update for opencl kernels (#105664 )

2024-10-10 14:04:52 +02:00

[mlir][GPU] gpu.printf: Do not emit duplicate format strings (#110504 )

2024-10-01 09:12:08 +02:00

[mlir][AMDGPU] Add support for AMD f16 math library calls (#108809 )

2024-09-23 12:52:00 -05:00

[mlir][spirv] Add gpu printf op lowering to spirv.CL.printf op (#78510 )

2024-09-30 15:39:13 -04:00

[MLIR][LaunchFuncToVulkan] Remove typed pointer support (#70865 )

2023-11-01 08:40:54 +01:00

[mlir][Transforms][NFC] Dialect Conversion: Resolve insertion point TODO (#95653 )

2024-06-17 19:56:40 +02:00

[mlir][Transforms][NFC] Dialect Conversion: Resolve insertion point TODO (#95653 )

2024-06-17 19:56:40 +02:00

[mlir] fix LLVM type converter for structs (#73231 )

2023-11-23 22:21:39 +01:00

[mlir][MathToFuncs] MathToFuncs only support integer type (#113693 )

2024-10-28 09:54:51 +08:00

[MLIR][MathDialect] fix fp32 promotion crash when encounters scf.if (#104451 )

2024-08-21 10:08:56 +08:00

[mlir][math] Propagate scalability in convert-math-to-llvm (#82635 )

2024-02-23 09:48:58 +00:00

[mlir][GPU] Add FunctionOpInterface check for OpToFuncCallLowering (#113449 )

2024-10-26 11:22:08 +08:00

[mlir][spirv] Update math.powf lowering (#111388 )

2024-10-09 09:04:31 +01:00

[MLIR][VCIX] Support VCIX intrinsics in LLVMIR dialect (#75875 )

2024-02-07 15:23:28 -05:00

[mlir][EmitC] memref-to-emitc: insert conversion_casts (#114204 )

2024-10-30 15:27:23 +01:00

[mlir] [memref] add more checks to the memref.reinterpret_cast (#112669 )

2024-10-26 08:07:51 +08:00

[MLIR][SPIRV] Update cast from IntN to Bool (#113329 )

2024-10-23 09:47:33 +01:00

[mlir][Transforms] Dialect conversion: Make materializations optional (#107109 )

2024-09-05 19:40:58 +02:00

[MLIR][NVVM] Update the elect.sync Op to use intrinsics (#113757 )

2024-10-27 22:24:31 +05:30

OneToNTypeConversion

[mlir] Implement one-to-n structural conversion for ForOp

2023-07-07 15:50:54 +00:00

[mlir][openacc] Cleanup acc.exit_data from old data clause operands

2023-05-09 11:36:48 -07:00

[MLIR][OpenMP] Remove terminators from loop wrappers (#112229 )

2024-10-15 11:28:39 +01:00

[mlir] Fix test expectation.

2024-05-24 10:00:36 +00:00

ReconcileUnrealizedCasts

[mlir][Conversion] Generalize and fix crash in reconcile-unrealized-casts (#95700 )

2024-06-19 16:23:27 +02:00

SCFToControlFlow

Enable attaching LLVM loop annotations to scf.for (#102562 )

2024-08-12 18:25:13 +02:00

[mlir][EmitC] Model lvalues as a type in EmitC (#91475 )

2024-08-20 11:52:16 +02:00

[mlir][gpu] Add Support for Cluster of Thread Blocks in gpu.launch (#76924 )

2024-01-06 11:17:01 +01:00

[MLIR][OpenMP] Remove terminators from loop wrappers (#112229 )

2024-10-15 11:28:39 +01:00

[mlir][spirv] Improve folding of MemRef to SPIRV Lowering (#85433 )

2024-03-21 08:49:27 -07:00

ShapeToStandard

[mlir] Use arith max or min ops instead of cmp + select (#82178 )

2024-02-21 12:28:05 -08:00

[mlir][SPIRVToLLVM] Erase empty spirv.mlir.loop in LoopPattern (#113527 )

2024-10-26 11:22:57 +08:00

[mlir][tensor] Make getMixedPadImpl return static values when possible. (#85016 )

2024-03-13 08:52:05 -07:00

[mlir][TensorToSPIRV] Add type check for tensor.extract in TensorToSPIRV (#107110 )

2024-09-04 10:21:27 +08:00

[mlir][tosa]Create a check for i64 input in apply_scale lowering in TosaToArith

2023-09-07 11:08:52 -07:00

[mlir][TosaToLinalg] RescaleConverter only support integer type (#114239 )

2024-10-31 11:32:19 +00:00

TosaToMLProgram

[TOSA] Add TosaToMLProgram conversion (#69787 )

2023-11-10 10:54:51 -08:00

[mlir][tosa] operation printing syntax prettification

2023-08-15 18:16:37 +00:00

TosaToTensor: Support reshape on tensors of unsigned integer (#91734 )

2024-05-28 17:59:23 +02:00

[mlir][UBToLLVM] Do not arbitrarily restrict input types

2023-08-28 17:16:21 +02:00

[mlir][spirv] Convert ub.poison to spirv.undef

2023-07-25 00:23:09 +02:00

[mlir][ArmSME] Rename slice move operations to insert/extract_tile_slice (#106755 )

2024-09-02 11:12:40 +01:00

[mlir][vector] Fix a crash in VectorToGPU (#113454 )

2024-10-24 20:28:42 +08:00

[MLIR][Vector] Add Lowering for vector.step (#113655 )

2024-11-01 16:38:36 +00:00

[mlir][Vector] Support 0-d vectors natively in TransferOpReduceRank (#112907 )

2024-10-22 15:50:16 +01:00

[mlir][SPIRV] Make test case more robust (#108388 )

2024-09-12 15:34:59 +02:00

[mlir][xegpu] Allow out-of-bounds writes (#110811 )

2024-10-09 18:59:14 +02:00