AMDGPU: Fix splitting wide f32 s.buffer.load intrinsics
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Sat, 1 Feb 2020 16:35:15 +0000 (11:35 -0500)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 3 Feb 2020 20:28:08 +0000 (12:28 -0800)
commit726446a00964f0be5521a5ad2b21752b8571cb9a
tree2cee3ecd8c12b6619b74f956a7b8dd99ca4fa8d2
parent80e63c17c0a4f02a730b8d00a426fcf0e018f9bb
AMDGPU: Fix splitting wide f32 s.buffer.load intrinsics

This would witch f32 to i32, and produce an invald concat_vectors from
i32 pieces to an f32 vector.
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
llvm/test/CodeGen/AMDGPU/smrd.ll