diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/local-memory-two-objects.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/local-memory-two-objects.ll | 37 |
1 files changed, 28 insertions, 9 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/local-memory-two-objects.ll b/llvm/test/CodeGen/AMDGPU/local-memory-two-objects.ll index 969769bea6f..cec334f7df6 100644 --- a/llvm/test/CodeGen/AMDGPU/local-memory-two-objects.ll +++ b/llvm/test/CodeGen/AMDGPU/local-memory-two-objects.ll @@ -1,6 +1,6 @@ -; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG %s -; RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=GCN --check-prefix=SI %s -; RUN: llc < %s -march=amdgcn -mcpu=bonaire -verify-machineinstrs | FileCheck --check-prefix=GCN --check-prefix=CI %s +; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=FUNC %s +; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s +; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s @local_memory_two_objects.local_mem0 = internal unnamed_addr addrspace(3) global [4 x i32] undef, align 4 @local_memory_two_objects.local_mem1 = internal unnamed_addr addrspace(3) global [4 x i32] undef, align 4 @@ -12,15 +12,14 @@ ; GCN: .long 47180 ; GCN-NEXT: .long 32900 -; EG: {{^}}local_memory_two_objects: + +; FUNC-LABEL: {{^}}local_memory_two_objects: ; We would like to check the lds writes are using different ; addresses, but due to variations in the scheduler, we can't do ; this consistently on evergreen GPUs. ; EG: LDS_WRITE ; EG: LDS_WRITE -; GCN: ds_write_b32 {{v[0-9]*}}, v[[ADDRW:[0-9]*]] -; GCN-NOT: ds_write_b32 {{v[0-9]*}}, v[[ADDRW]] ; GROUP_BARRIER must be the last instruction in a clause ; EG: GROUP_BARRIER @@ -30,9 +29,29 @@ ; constant offsets. ; EG: LDS_READ_RET {{[*]*}} OQAP, {{PV|T}}[[ADDRR:[0-9]*\.[XYZW]]] ; EG-NOT: LDS_READ_RET {{[*]*}} OQAP, T[[ADDRR]] -; SI: v_add_i32_e32 [[SIPTR:v[0-9]+]], vcc, 16, v{{[0-9]+}} -; SI: ds_read_b32 {{v[0-9]+}}, [[SIPTR]] -; CI: ds_read2_b32 {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}} offset1:4 + + +; GCN: v_lshlrev_b32_e32 [[ADDRW:v[0-9]+]], 2, v0 +; CI-DAG: ds_write_b32 [[ADDRW]], {{v[0-9]*}} offset:16 +; CI-DAG: ds_write_b32 [[ADDRW]], {{v[0-9]*$}} + + +; SI: v_add_i32_e32 [[ADDRW_OFF:v[0-9]+]], vcc, 16, [[ADDRW]] + +; SI-DAG: ds_write_b32 [[ADDRW]], +; SI-DAG: ds_write_b32 [[ADDRW_OFF]], + +; GCN: s_barrier + +; SI-DAG: v_sub_i32_e32 [[SUB0:v[0-9]+]], vcc, 28, [[ADDRW]] +; SI-DAG: v_sub_i32_e32 [[SUB1:v[0-9]+]], vcc, 12, [[ADDRW]] + +; SI-DAG: ds_read_b32 v{{[0-9]+}}, [[SUB0]] +; SI-DAG: ds_read_b32 v{{[0-9]+}}, [[SUB1]] + +; CI: v_sub_i32_e32 [[SUB:v[0-9]+]], vcc, 0, [[ADDRW]] +; CI: ds_read2_b32 {{v\[[0-9]+:[0-9]+\]}}, [[SUB]] offset0:3 offset1:7 + define void @local_memory_two_objects(i32 addrspace(1)* %out) { entry: %x.i = call i32 @llvm.r600.read.tidig.x() #0 |
