workitem-intrinsics.ll
1.56 KB
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
32
33
34
35
36
37
38
39
40
41
42
43
44
45
; RUN: opt -mtriple amdgcn-unknown-amdhsa -analyze -divergence -use-gpu-divergence-analysis %s | FileCheck %s
declare i32 @llvm.amdgcn.workitem.id.x() #0
declare i32 @llvm.amdgcn.workitem.id.y() #0
declare i32 @llvm.amdgcn.workitem.id.z() #0
declare i32 @llvm.amdgcn.mbcnt.lo(i32, i32) #0
declare i32 @llvm.amdgcn.mbcnt.hi(i32, i32) #0
; CHECK: DIVERGENT: %id.x = call i32 @llvm.amdgcn.workitem.id.x()
define amdgpu_kernel void @workitem_id_x() #1 {
%id.x = call i32 @llvm.amdgcn.workitem.id.x()
store volatile i32 %id.x, i32 addrspace(1)* undef
ret void
}
; CHECK: DIVERGENT: %id.y = call i32 @llvm.amdgcn.workitem.id.y()
define amdgpu_kernel void @workitem_id_y() #1 {
%id.y = call i32 @llvm.amdgcn.workitem.id.y()
store volatile i32 %id.y, i32 addrspace(1)* undef
ret void
}
; CHECK: DIVERGENT: %id.z = call i32 @llvm.amdgcn.workitem.id.z()
define amdgpu_kernel void @workitem_id_z() #1 {
%id.z = call i32 @llvm.amdgcn.workitem.id.z()
store volatile i32 %id.z, i32 addrspace(1)* undef
ret void
}
; CHECK: DIVERGENT: %mbcnt.lo = call i32 @llvm.amdgcn.mbcnt.lo(i32 0, i32 0)
define amdgpu_kernel void @mbcnt_lo() #1 {
%mbcnt.lo = call i32 @llvm.amdgcn.mbcnt.lo(i32 0, i32 0)
store volatile i32 %mbcnt.lo, i32 addrspace(1)* undef
ret void
}
; CHECK: DIVERGENT: %mbcnt.hi = call i32 @llvm.amdgcn.mbcnt.hi(i32 0, i32 0)
define amdgpu_kernel void @mbcnt_hi() #1 {
%mbcnt.hi = call i32 @llvm.amdgcn.mbcnt.hi(i32 0, i32 0)
store volatile i32 %mbcnt.hi, i32 addrspace(1)* undef
ret void
}
attributes #0 = { nounwind readnone }
attributes #1 = { nounwind }