[mlir][GPU] Move amdgpu target-specific transforms out of generic GPU dialect transforms

[Muzammiluddin-Syed-ECE]

AMDGPU-specific lowerings of gpu data movement ops do not belong under the GPU dialect.

Relocate the amdgpu-specific patterns within these files to somewhere more appropriate under AMDGPU/transforms:

• https://github.com/llvm/llvm-project/blob/c8fd662bfa83b3cfa1c7a37ffaec8fac9bb36ccf/mlir/lib/Dialect/GPU/Transforms/SubgroupReduceLowering.cpp
• https://github.com/llvm/llvm-project/blob/c8fd662bfa83b3cfa1c7a37ffaec8fac9bb36ccf/mlir/lib/Dialect/GPU/Transforms/PromoteShuffleToAMDGPU.cpp

[llvmbot]

@llvm/issue-subscribers-mlir

Author: Muzammil (Muzammiluddin-Syed-ECE)

Lowerings of generic gpu data movement ops from GPU to AMDGPU have persisted under the GPU dialect.

Relocate the amdgpu-specific patterns within these files to somewhere more appropriate under AMDGPU/transforms:

• https://github.com/llvm/llvm-project/blob/c8fd662bfa83b3cfa1c7a37ffaec8fac9bb36ccf/mlir/lib/Dialect/GPU/Transforms/SubgroupReduceLowering.cpp
• https://github.com/llvm/llvm-project/blob/c8fd662bfa83b3cfa1c7a37ffaec8fac9bb36ccf/mlir/lib/Dialect/GPU/Transforms/PromoteShuffleToAMDGPU.cpp

[llvmbot]

@llvm/issue-subscribers-mlir-gpu

Author: Muzammil (Muzammiluddin-Syed-ECE)

Lowerings of generic gpu data movement ops from GPU to AMDGPU have persisted under the GPU dialect.

Relocate the amdgpu-specific patterns within these files to somewhere more appropriate under AMDGPU/transforms:

• https://github.com/llvm/llvm-project/blob/c8fd662bfa83b3cfa1c7a37ffaec8fac9bb36ccf/mlir/lib/Dialect/GPU/Transforms/SubgroupReduceLowering.cpp
• https://github.com/llvm/llvm-project/blob/c8fd662bfa83b3cfa1c7a37ffaec8fac9bb36ccf/mlir/lib/Dialect/GPU/Transforms/PromoteShuffleToAMDGPU.cpp