Files
clang-p2996/llvm/lib/Target/AMDGPU/AMDGPUPostLegalizerCombiner.cpp
Konstantina Mitropoulou 944f429b21 [AMDGPU] Improve the lowering of raw_buffer_load_{i8,i16} and struct_buffer_load_{i8,i16} intrinsics
Currently, raw_buffer_load_{i8,i16} and struct_buffer_load_{i8,i16}
intrinsics are lowered as buffer_load_{u8,u16}. This patch combines
buffer_load_{u8,u16} and sign extension instructions in order to
generate buffer_load_{i8,i16} instructions.

Reviewed By: foad

Differential Revision: https://reviews.llvm.org/D144313
2023-02-22 09:01:33 -08:00

17 KiB