Convert Arm NEON structured ops to intrinsics

Convert top-level AffineFor Ops to GPU kernels

Convert AMDGPU dialect to ROCDL dialect

Convert Arith dialect to LLVM dialect

Convert Arith dialect to SPIR-V dialect

Convert the operations from the async dialect into the LLVM dialect

Convert operations from the Bufferization dialect to the MemRef dialect

Convert ControlFlow operations to the LLVM dialect

Convert ControlFlow dialect to SPIR-V dialect

Convert Complex dialect to libm calls

Convert Complex dialect to LLVM dialect

Convert Complex dialect to standard dialect

Convert from the Func dialect to the LLVM dialect

Convert Func dialect to SPIR-V dialect

Convert gpu.launch_func to vulkanLaunch external call

Generate NVVM operations for gpu operations

Generate ROCDL operations for gpu operations

Convert GPU dialect to SPIR-V dialect

Lower the index dialect to the llvm dialect.

Convert the operations from the linalg dialect into the LLVM dialect

Convert the operations from the linalg dialect into the Standard dialect

Convert Math operations to calls of outlined implementations.

Convert Math dialect to libm calls

Convert Math dialect to LLVM dialect

Convert Math dialect to SPIR-V dialect

Convert MemRef dialect to SPIR-V dialect

Convert NVGPU dialect to NVVM dialect

Convert the OpenACC ops to LLVM dialect

Convert the OpenACC ops to OpenACC with SCF dialect

Convert the OpenMP ops to OpenMP ops with LLVM dialect

Convert mapped scf.parallel ops to gpu launch operations

Convert PDL ops to PDL interpreter ops

Convert SCF dialect to ControlFlow dialect, replacing structured control flow with a CFG

Convert SCF parallel loop to OpenMP parallel + workshare constructs.

Convert SCF dialect to SPIR-V dialect.

Convert shape constraint operations to the standard dialect

Convert operations from the shape dialect into the standard dialect

Convert SPIR-V dialect to LLVM dialect

Convert some Tensor dialect ops to Linalg dialect

Convert Tensor dialect to SPIR-V dialect

Lower the operations from the vector dialect into the GPU dialect

Lower the operations from the vector dialect into the LLVM dialect

Lower the operations from the vector dialect into the SCF dialect

Convert Vector dialect to SPIR-V dialect

Finalize MemRef dialect to LLVM dialect conversion

Convert GPU dialect to LLVM dialect with GPU runtime calls

Convert vulkanLaunch external call to Vulkan runtime external calls

Lower Affine operations to a combination of Standard and SCF operations

Lowers the host module code and gpu.launch_func to LLVM

Map numeric MemRef memory spaces to SPIR-V storage classes

Simplify and eliminate unrealized conversion casts

Lower TOSA to the Arith dialect

Lower TOSA to LinAlg on tensors

Lower TOSA to LinAlg named operations

Lower TOSA to the SCF dialect

Lower TOSA to the Tensor dialect