Luke Hutton d4570ea813

[mlir][tosa] Disallow invalid datatype combinations in the validation pass (#131595) ...

This commit checks if the operands/results of an operator can be found
in the profile compliance mapping, if it isn't the operator is
considered invalid. As a result, operator datatype combinations that are
not listed under the "Supported Data Types" of the TOSA specification
are disallowed and the validation pass results in failure.

Signed-off-by: Luke Hutton <luke.hutton@arm.com>

2025-03-25 10:05:39 +00:00

..

AffineToStandard

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

AMDGPUToROCDL

[AMD][ROCDL] Add packed conversions fp8/bf8->bf16 and fp8/bf8->fp32 in ROCDL dialect (#131850)

2025-03-21 14:49:50 +00:00

ArithCommon

[mlir][llvm] Port overflowFlags to a native operation property (RELAND) (#89410)

2024-04-19 09:23:00 -07:00

ArithToAMDGPU

[AMD][ROCDL] Add packed conversions fp8/bf8->bf16 and fp8/bf8->fp32 in ROCDL dialect (#131850)

2025-03-21 14:49:50 +00:00

ArithToArmSME

[mlir] Enable decoupling two kinds of greedy behavior. (#104649)

2024-12-20 08:15:48 -08:00

ArithToEmitC

[mlir][emitc] Support convert arith.extf and arith.truncf to emitc (#121184)

2025-01-16 14:57:43 +08:00

ArithToLLVM

Reland [mlir] ArithToLLVM: fix memref bitcast lowering (#125148) (#126939)

2025-02-12 20:32:13 +03:00

ArithToSPIRV

[mlir] Use getSingleElement/hasSingleElement in various places (#131460)

2025-03-17 07:43:18 +01:00

ArmNeon2dToIntr

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

ArmSMEToLLVM

[mlir][LLVM] Switch undef for poison for uninitialized values (#125629)

2025-02-06 12:49:30 -06:00

ArmSMEToSCF

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

AsyncToLLVM

[mlir] Fix conflict of user defined reserved functions with internal prototypes (#123378)

2025-01-28 14:40:47 +01:00

BufferizationToMemRef

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

ComplexCommon

[mlir] Fix a warning

2025-02-13 08:36:07 -08:00

ComplexToLibm

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

ComplexToLLVM

[mlir][complex] Add complex-range option and select complex division … (#127010)

2025-02-13 13:06:04 +01:00

ComplexToSPIRV

[mlir][NFC] Mark type converter in populate... functions as const (#111250)

2024-10-05 21:32:40 +02:00

ComplexToStandard

[MLIR][NFC] Use base alias for constructor inheritance (#127756)

2025-02-19 16:05:25 +01:00

ControlFlowToLLVM

[mlir] Fix conflict of user defined reserved functions with internal prototypes (#123378)

2025-01-28 14:40:47 +01:00

ControlFlowToSCF

[MLIR] Remove unneeded LLVMDialect.h include in ControlFlowToSCF.cpp (#113560)

2024-10-25 15:41:39 +01:00

ControlFlowToSPIRV

[MLIR][NFC] Use base alias for constructor inheritance (#127756)

2025-02-19 16:05:25 +01:00

ConvertToLLVM

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

FuncToEmitC

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

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

FuncToLLVM

[mlir][LLVM] Switch undef for poison for uninitialized values (#125629)

2025-02-06 12:49:30 -06:00

FuncToSPIRV

[MLIR][NFC] Use base alias for constructor inheritance (#127756)

2025-02-19 16:05:25 +01:00

GPUCommon

[mlir][Transforms] Dialect Conversion: Add 1:N support to remapInput (#131454)

2025-03-15 18:33:06 +01:00

GPUToLLVMSPV

[MLIR][GPU] Support bf16 and i1 gpu::shuffles to LLVMSPIRV conversion (#119675)

2025-01-09 13:16:18 +01:00

GPUToNVVM

[MLIR][GPUToNVVM] Support 32-bit isfinite (#131699)

2025-03-18 02:11:38 +01:00

GPUToROCDL

[mlir][gpu] GPUToROCDL/NVVM: use generic llvm conversion interface instead of hardcoded conversions. (#124439)

2025-02-13 17:53:12 +03:00

GPUToSPIRV

[mlir] Use getSingleElement/hasSingleElement in various places (#131460)

2025-03-17 07:43:18 +01:00

IndexToLLVM

[mlir][NFC] Mark type converter in populate... functions as const (#111250)

2024-10-05 21:32:40 +02:00

IndexToSPIRV

eliminating g++ warnings (#105520)

2024-10-18 21:20:47 +01:00

LinalgToStandard

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

LLVMCommon

Revert "[mlir] ArithToLLVM: fix memref bitcast lowering" (#126895)

2025-02-12 14:34:16 +03:00

MathToEmitC

[mlir][EmitC] Add MathToEmitC pass for math function lowering to EmitC (#113799)

2025-01-20 09:26:41 +01:00

MathToFuncs

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

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

MathToLibm

[MLIR][Math] Add erfc to math dialect (#126439)

2025-02-18 10:51:37 -05:00

MathToLLVM

[MLIR][Math] Add lowering for isnan and isfinite (#128125)

2025-02-20 23:40:35 -06:00

MathToROCDL

[MLIR][ROCDL] Add conversion of math.erfc to AMD GPU library calls (#128899)

2025-02-27 14:32:25 -05:00

MathToSPIRV

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

MemRefToEmitC

[mlir][SCFToEmitC] Don't convert unsupported types in EmitC (#131786)

2025-03-19 14:18:51 +08:00

MemRefToLLVM

[mlir][IR] Deprecate match and rewrite functions (#130031)

2025-03-07 08:43:01 +01:00

MemRefToSPIRV

[MLIR][NFC] Use base alias for constructor inheritance (#127756)

2025-02-19 16:05:25 +01:00

MeshToMPI

[mlir] Use getSingleElement/hasSingleElement in various places (#131460)

2025-03-17 07:43:18 +01:00

MPIToLLVM

[mlir] Apply ClangTidy finding (NFC)

2025-03-04 12:20:35 +00:00

NVGPUToNVVM

[mlir][LLVM] Switch undef for poison for uninitialized values (#125629)

2025-02-06 12:49:30 -06:00

NVVMToLLVM

mlir/LogicalResult: move into llvm (#97309)

2024-07-02 10:42:33 +01:00

OpenACCToSCF

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

OpenMPToLLVM

[MLIR][OpenMP] Simplify OpenMP to LLVM dialect conversion (#132009)

2025-03-20 14:41:27 +00:00

PDLToPDLInterp

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

ReconcileUnrealizedCasts

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

SCFToControlFlow

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

SCFToEmitC

[mlir][SCFToEmitC] Don't convert unsupported types in EmitC (#131786)

2025-03-19 14:18:51 +08:00

SCFToGPU

[MLIR][NFC] Use base alias for constructor inheritance (#127756)

2025-02-19 16:05:25 +01:00

SCFToOpenMP

[mlir][OpenMP] inscan reduction modifier and scan op mlir support (#114737)

2025-01-22 09:53:54 -08:00

SCFToSPIRV

[mlir][NFC] Mark type converter in populate... functions as const (#111250)

2024-10-05 21:32:40 +02:00

ShapeToStandard

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

SPIRVCommon

[MLIR][GPU-LLVM] Convert gpu.func to llvm.func (#101664)

2024-08-09 16:09:11 +02:00

SPIRVToLLVM

[mlir][LLVM] Switch undef for poison for uninitialized values (#125629)

2025-02-06 12:49:30 -06:00

TensorToLinalg

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

TensorToSPIRV

[MLIR][NFC] Use base alias for constructor inheritance (#127756)

2025-02-19 16:05:25 +01:00

TosaToArith

[mlir][tosa] Add support for EXT-DOUBLEROUND and EXT-INEXACTROUND (#130337)

2025-03-10 19:32:30 +00:00

TosaToLinalg

[mlir][tosa] Disallow invalid datatype combinations in the validation pass (#131595)

2025-03-25 10:05:39 +00:00

TosaToMLProgram

[TOSA] Add TosaToMLProgram conversion (#69787)

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

TosaToSCF

[mlir][tosa] Update ControlFlow variable names to match with TOSA v1.0 spec (#129790)

2025-03-05 01:17:42 +00:00

TosaToTensor

[mlir][tosa] Update value to values for ConstOp and ConstShapeOp (#129943)

2025-03-06 14:55:50 -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

VectorToArmSME

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

VectorToGPU

[mlir] Use *Set::insert_range (NFC) (#132326)

2025-03-20 22:24:17 -07:00

VectorToLLVM

[mlir][vector] Allow multi dim vectors in vector.scatter (#132217)

2025-03-24 12:52:46 +00:00

VectorToSCF

[mlir][vector][nfc] Replace failure() with notifyMatchFailure() (#129278)

2025-03-06 18:22:46 +00:00

VectorToSPIRV

[MLIR][NFC] Retire let constructor for passes in Conversion directory (part1) (#127403)

2025-02-17 10:55:27 +01:00

VectorToXeGPU

[mlir][xegpu] Convert Vector contraction to XeGPU (#122115)

2025-03-13 19:41:53 +01:00

CMakeLists.txt

[mlir][mpi] Lowering Mpi To LLVM (#127053)

2025-02-21 18:03:04 +01:00