1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
| ; RUN: llc -mattr=+promote-alloca -verify-machineinstrs -march=amdgcn < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-PROMOTE %s
; RUN: llc -mattr=+promote-alloca,-flat-for-global -verify-machineinstrs -mtriple=amdgcn--amdhsa -mcpu=kaveri < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-PROMOTE -check-prefix=HSA %s
; RUN: llc -mattr=-promote-alloca -verify-machineinstrs -march=amdgcn < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-ALLOCA %s
; RUN: llc -mattr=-promote-alloca,-flat-for-global -verify-machineinstrs -mtriple=amdgcn-amdhsa -mcpu=kaveri < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-ALLOCA -check-prefix=HSA %s
; RUN: llc -mattr=+promote-alloca -verify-machineinstrs -march=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-PROMOTE %s
; RUN: llc -mattr=-promote-alloca -verify-machineinstrs -march=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-ALLOCA %s
declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
; Make sure we don't overwrite workitem information with private memory
; GCN-LABEL: {{^}}work_item_info:
; GCN-NOT: v0
; GCN: v_add_{{[iu]}}32_e32 [[RESULT:v[0-9]+]], vcc, v{{[0-9]+}}, v0
; GCN: buffer_store_dword [[RESULT]]
define amdgpu_kernel void @work_item_info(i32 addrspace(1)* %out, i32 %in) {
entry:
%0 = alloca [2 x i32], addrspace(5)
%1 = getelementptr [2 x i32], [2 x i32] addrspace(5)* %0, i32 0, i32 0
%2 = getelementptr [2 x i32], [2 x i32] addrspace(5)* %0, i32 0, i32 1
store i32 0, i32 addrspace(5)* %1
store i32 1, i32 addrspace(5)* %2
%3 = getelementptr [2 x i32], [2 x i32] addrspace(5)* %0, i32 0, i32 %in
%4 = load i32, i32 addrspace(5)* %3
%5 = call i32 @llvm.amdgcn.workitem.id.x()
%6 = add i32 %4, %5
store i32 %6, i32 addrspace(1)* %out
ret void
}
|