diff options
Diffstat (limited to 'test/CodeGen/AMDGPU/schedule-kernel-arg-loads.ll')
| -rw-r--r-- | test/CodeGen/AMDGPU/schedule-kernel-arg-loads.ll | 17 |
1 files changed, 8 insertions, 9 deletions
diff --git a/test/CodeGen/AMDGPU/schedule-kernel-arg-loads.ll b/test/CodeGen/AMDGPU/schedule-kernel-arg-loads.ll index 6b3e0814c3805..886d4a1dcb5c0 100644 --- a/test/CodeGen/AMDGPU/schedule-kernel-arg-loads.ll +++ b/test/CodeGen/AMDGPU/schedule-kernel-arg-loads.ll @@ -1,18 +1,17 @@ -; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=FUNC -check-prefix=SI --check-prefix=GCN %s -; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=FUNC -check-prefix=VI --check-prefix=GCN %s +; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=FUNC -check-prefix=SI -check-prefix=GCN %s +; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=FUNC -check-prefix=VI -check-prefix=GCN %s ; FUNC-LABEL: {{^}}cluster_arg_loads: +; FIXME: Due to changes in the load clustering heuristics. We no longer +; cluster all argument loads together on SI. +; SI: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0xd ; SI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x9 ; SI-NEXT: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0xb -; SI-NEXT: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0xd ; SI-NEXT: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0xe +; VI: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0x34 ; VI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x24 -; VI-NEXT: s_nop 0 -; VI-NEXT: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x2c -; VI-NEXT: s_nop 0 -; VI-NEXT: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0x34 -; VI-NEXT: s_nop 0 -; VI-NEXT: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0x38 +; VI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x2c +; VI: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0x38 define void @cluster_arg_loads(i32 addrspace(1)* %out0, i32 addrspace(1)* %out1, i32 %x, i32 %y) nounwind { store i32 %x, i32 addrspace(1)* %out0, align 4 store i32 %y, i32 addrspace(1)* %out1, align 4 |