llvm-project/mlir/lib/Conversion
Alex Zinenko a776942ba1 [mlir] squash LLVM_AVX512 dialect into AVX512
The dialect separation was introduced to demarkate ops operating in different
type systems. This is no longer the case after the LLVM dialect has migrated to
using built-in vector types, so the original reason for separation is no longer
valid. Squash the two dialects into one.

The code size decrease isn't quite large: the ops originally in LLVM_AVX512 are
preserved because they match LLVM IR intrinsics specialized for vector element
bitwidth. However, it is still conceptually beneficial to have only one
dialect. I originally considered to use Tablegen multiclasses to define both
the type-polymorphic op and its two intrinsic-related instantiations, but
decided against it given both the complexity of the required Tablegen input and
its dissimilarity with the rest of ODS-defined ops, both potentially resulting
in very poor maintainability.

Depends On D98327

Reviewed By: nicolasvasilache, springerm

Differential Revision: https://reviews.llvm.org/D98328
2021-03-10 13:07:26 +01:00
..
AffineToStandard Revert "[MLIR] Create memref dialect and move several dialect-specific ops from std." 2021-02-18 12:49:52 +01:00
ArmSVEToLLVM [mlir] make vector to llvm conversion truly partial 2021-02-04 11:33:24 +01:00
AsyncToLLVM [mlir] Delay adding the __resume function 2021-02-02 20:02:54 +01:00
ComplexToLLVM Move LLVM::FMFAttr definition to TableGen (NFC) 2021-03-09 05:29:54 +00:00
GPUCommon [mlir] Add base class for GpuKernelToBlobPass 2021-03-10 12:14:43 +01:00
GPUToNVVM [mlir][NFC] Rename `MemRefType::getMemorySpace` to `getMemorySpaceAsInt` 2021-03-02 11:08:54 +03:00
GPUToROCDL Lower math.expm1 to intrinsics in the GPUToNVVM and GPUToROCDL conversions. 2021-02-16 10:23:42 +01:00
GPUToSPIRV [mlir] Silence some deprecation warnings after dffc487b07 2021-02-26 15:15:56 +01:00
GPUToVulkan Revert "Revert "Reorder MLIRContext location in BuiltinAttributes.h"" 2021-02-08 10:39:58 +01:00
LinalgToLLVM [mlir] Turn Linalg to LLVM into a partial conversion 2021-02-05 14:31:19 +01:00
LinalgToSPIRV [mlir][spirv] Replace SPIRVOpLowering with OpConversionPattern 2021-01-09 08:04:53 -05:00
LinalgToStandard Revert "[MLIR] Create memref dialect and move several dialect-specific ops from std." 2021-02-18 12:49:52 +01:00
OpenMPToLLVM [mlir] Replace deprecated 'getAttrs' 2021-02-26 14:52:40 +01:00
PDLToPDLInterp [mlir][pdl][NFC] Rename InputOp to OperandOp 2021-03-03 15:48:00 -08:00
SCFToGPU [mlir] Replace deprecated 'getAttrs' 2021-02-26 14:52:40 +01:00
SCFToOpenMP [mlir] Use mlir::OpState::operator->() to get to methods of mlir::Operation. This is a preparation step to remove the corresponding methods from OpState. 2020-12-09 12:11:32 +01:00
SCFToSPIRV [MLIR][SPIRV] Rename `spv.selection` to `spv.mlir.selection`. 2021-03-06 16:05:31 +01:00
SCFToStandard [mlir] Avoid cloning ops in SCF parallel conversion to CFG 2020-11-23 14:01:22 +01:00
SPIRVToLLVM Move LLVM::FMFAttr definition to TableGen (NFC) 2021-03-09 05:29:54 +00:00
ShapeToStandard [mlir][Shape] Allow shape.split_at to return extent tensors and lower it to std.subtensor 2021-03-08 16:48:05 +01:00
StandardToLLVM Move LLVM::FMFAttr definition to TableGen (NFC) 2021-03-09 05:29:54 +00:00
StandardToSPIRV [mlir][spirv] Convert tensor.extract for very small tensors 2021-03-06 08:03:36 -05:00
TosaToLinalg [MLIR][TOSA] Added lowerings for Reduce operations to Linalg 2021-03-08 10:57:19 -08:00
TosaToSCF [MLIR][TOSA] Resubmit Tosa to Standard/SCF Lowerings (const, if, while)" 2021-02-26 17:44:12 -08:00
TosaToStandard [MLIR][TOSA] Resubmit Tosa to Standard/SCF Lowerings (const, if, while)" 2021-02-26 17:44:12 -08:00
VectorToLLVM [mlir] squash LLVM_AVX512 dialect into AVX512 2021-03-10 13:07:26 +01:00
VectorToROCDL [mlir][NFC] Rename `MemRefType::getMemorySpace` to `getMemorySpaceAsInt` 2021-03-02 11:08:54 +03:00
VectorToSCF [mlir][NFC] Rename `MemRefType::getMemorySpace` to `getMemorySpaceAsInt` 2021-03-02 11:08:54 +03:00
VectorToSPIRV [mlir][lldb] Fix several gcc warnings in mlir and lldb 2021-03-01 13:48:22 -08:00
CMakeLists.txt [mlir] squash LLVM_AVX512 dialect into AVX512 2021-03-10 13:07:26 +01:00
PassDetail.h [mlir] Squash LLVM_ArmNeon dialect into ArmNeon 2021-03-05 23:33:32 +01:00