diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/reduce-load-width-alignment.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/reduce-load-width-alignment.ll | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/reduce-load-width-alignment.ll b/llvm/test/CodeGen/AMDGPU/reduce-load-width-alignment.ll index dd67dc488db..ecb513cd80b 100644 --- a/llvm/test/CodeGen/AMDGPU/reduce-load-width-alignment.ll +++ b/llvm/test/CodeGen/AMDGPU/reduce-load-width-alignment.ll @@ -6,7 +6,7 @@ ; GCN: buffer_load_dword [[VAL:v[0-9]+]] ; GCN: v_and_b32_e32 v{{[0-9]+}}, 0x12d687, [[VAL]] ; GCN: buffer_store_dwordx2 -define void @reduce_i64_load_align_4_width_to_i32(i64 addrspace(1)* %out, i64 addrspace(1)* %in) #0 { +define amdgpu_kernel void @reduce_i64_load_align_4_width_to_i32(i64 addrspace(1)* %out, i64 addrspace(1)* %in) #0 { %a = load i64, i64 addrspace(1)* %in, align 4 %and = and i64 %a, 1234567 store i64 %and, i64 addrspace(1)* %out, align 8 @@ -16,7 +16,7 @@ define void @reduce_i64_load_align_4_width_to_i32(i64 addrspace(1)* %out, i64 ad ; GCN-LABEL: {{^}}reduce_i64_align_4_bitcast_v2i32_elt0: ; GCN: buffer_load_dword [[VAL:v[0-9]+]] ; GCN: buffer_store_dword [[VAL]] -define void @reduce_i64_align_4_bitcast_v2i32_elt0(i32 addrspace(1)* %out, i64 addrspace(1)* %in) #0 { +define amdgpu_kernel void @reduce_i64_align_4_bitcast_v2i32_elt0(i32 addrspace(1)* %out, i64 addrspace(1)* %in) #0 { %a = load i64, i64 addrspace(1)* %in, align 4 %vec = bitcast i64 %a to <2 x i32> %elt0 = extractelement <2 x i32> %vec, i32 0 @@ -27,7 +27,7 @@ define void @reduce_i64_align_4_bitcast_v2i32_elt0(i32 addrspace(1)* %out, i64 a ; GCN-LABEL: {{^}}reduce_i64_align_4_bitcast_v2i32_elt1: ; GCN: buffer_load_dword [[VAL:v[0-9]+]], off, s{{\[[0-9]+:[0-9]+\]}}, 0 offset:4 ; GCN: buffer_store_dword [[VAL]] -define void @reduce_i64_align_4_bitcast_v2i32_elt1(i32 addrspace(1)* %out, i64 addrspace(1)* %in) #0 { +define amdgpu_kernel void @reduce_i64_align_4_bitcast_v2i32_elt1(i32 addrspace(1)* %out, i64 addrspace(1)* %in) #0 { %a = load i64, i64 addrspace(1)* %in, align 4 %vec = bitcast i64 %a to <2 x i32> %elt0 = extractelement <2 x i32> %vec, i32 1 |
