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
46
47
48
49
50
|
; RUN: llc -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
declare i32 @llvm.amdgcn.workitem.id.x() #0
; GCN-LABEL: {{^}}convergent_inlineasm:
; GCN: %bb.0:
; GCN: v_cmp_ne_u32_e64
; GCN: s_cbranch_execz
; GCN: ; %bb.{{[0-9]+}}:
define amdgpu_kernel void @convergent_inlineasm(ptr addrspace(1) nocapture %arg) {
bb:
%tmp = call i32 @llvm.amdgcn.workitem.id.x()
%tmp1 = tail call i64 asm "v_cmp_ne_u32_e64 $0, 0, $1", "=s,v"(i32 1) #1
%tmp2 = icmp eq i32 %tmp, 8
br i1 %tmp2, label %bb3, label %bb5
bb3: ; preds = %bb
%tmp4 = getelementptr i64, ptr addrspace(1) %arg, i32 %tmp
store i64 %tmp1, ptr addrspace(1) %arg, align 8
br label %bb5
bb5: ; preds = %bb3, %bb
ret void
}
; GCN-LABEL: {{^}}nonconvergent_inlineasm:
; GCN: s_cbranch_execz
; GCN: ; %bb.{{[0-9]+}}:
; GCN: v_cmp_ne_u32_e64
; GCN: BB{{[0-9]+_[0-9]+}}:
define amdgpu_kernel void @nonconvergent_inlineasm(ptr addrspace(1) nocapture %arg) {
bb:
%tmp = call i32 @llvm.amdgcn.workitem.id.x()
%tmp1 = tail call i64 asm "v_cmp_ne_u32_e64 $0, 0, $1", "=s,v"(i32 1)
%tmp2 = icmp eq i32 %tmp, 8
br i1 %tmp2, label %bb3, label %bb5
bb3: ; preds = %bb
%tmp4 = getelementptr i64, ptr addrspace(1) %arg, i32 %tmp
store i64 %tmp1, ptr addrspace(1) %arg, align 8
br label %bb5
bb5: ; preds = %bb3, %bb
ret void
}
attributes #0 = { nounwind readnone }
attributes #1 = { convergent nounwind readnone }
|
