diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2019-10-09 22:51:42 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2019-10-09 22:51:42 +0000 |
| commit | f8bf7d7f42f28fa18144091022236208e199f331 (patch) | |
| tree | 61c0d8ea5085aedf46ca3b329144cc94660867b7 /llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll | |
| parent | adc5043fa2749d2a38139e6429837651d4936569 (diff) | |
| download | bcm5719-llvm-f8bf7d7f42f28fa18144091022236208e199f331.tar.gz bcm5719-llvm-f8bf7d7f42f28fa18144091022236208e199f331.zip | |
AMDGPU: Don't fold copies to physregs
In a future patch, this will help cleanup m0 handling.
The register coalescer handles copies from a register that
materializes an immediate, but doesn't handle move immediates
itself. The virtual register uses will often be allocated to the same
register, so there end up being no real copy.
llvm-svn: 374257
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll b/llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll index 7a2085fa361..00ae166a6ce 100644 --- a/llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll +++ b/llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll @@ -14,8 +14,8 @@ define amdgpu_kernel void @kernel_background_evaluate(float addrspace(5)* %kg, < ; GCN-NEXT: s_mov_b64 s[0:1], s[36:37] ; GCN-NEXT: v_mov_b32_e32 v1, 0x2000 ; GCN-NEXT: v_mov_b32_e32 v2, 0x4000 -; GCN-NEXT: s_mov_b64 s[2:3], s[38:39] ; GCN-NEXT: v_mov_b32_e32 v3, 0 +; GCN-NEXT: s_mov_b64 s[2:3], s[38:39] ; GCN-NEXT: v_mov_b32_e32 v4, 0x400000 ; GCN-NEXT: s_add_u32 s32, s33, 0xc0000 ; GCN-NEXT: v_add_nc_u32_e64 v32, 4, 0x4000 |
