uniform-loop-inside-nonuniform.ll
1.63 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
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
; RUN: llc -march=amdgcn -mcpu=verde < %s | FileCheck %s
; Test a simple uniform loop that lives inside non-uniform control flow.
; CHECK-LABEL: {{^}}test1:
; CHECK: v_cmp_ne_u32_e32 vcc, 0
; CHECK: s_and_saveexec_b64
; CHECK-NEXT: s_cbranch_execz BB{{[0-9]+_[0-9]+}}
; CHECK: [[LOOP_BODY_LABEL:BB[0-9]+_[0-9]+]]: ; %loop_body
; CHECK: s_cbranch_scc1 [[LOOP_BODY_LABEL]]
; CHECK: s_endpgm
define amdgpu_ps void @test1(<8 x i32> inreg %rsrc, <2 x i32> %addr.base, i32 %y, i32 %p) {
main_body:
%cc = icmp eq i32 %p, 0
br i1 %cc, label %out, label %loop_body
loop_body:
%counter = phi i32 [ 0, %main_body ], [ %incr, %loop_body ]
; Prevent the loop from being optimized out
call void asm sideeffect "", "" ()
%incr = add i32 %counter, 1
%lc = icmp sge i32 %incr, 1000
br i1 %lc, label %out, label %loop_body
out:
ret void
}
; CHECK-LABEL: {{^}}test2:
; CHECK: s_and_saveexec_b64
; CHECK-NEXT: s_cbranch_execz
define amdgpu_kernel void @test2(i32 addrspace(1)* %out, i32 %a, i32 %b) {
main_body:
%tid = call i32 @llvm.amdgcn.workitem.id.x() #1
%cc = icmp eq i32 %tid, 0
br i1 %cc, label %done1, label %if
if:
%cmp = icmp eq i32 %a, 0
br i1 %cmp, label %done0, label %loop_body
loop_body:
%counter = phi i32 [ 0, %if ], [0, %done0], [ %incr, %loop_body ]
; Prevent the loop from being optimized out
call void asm sideeffect "", "" ()
%incr = add i32 %counter, 1
%lc = icmp sge i32 %incr, 1000
br i1 %lc, label %done1, label %loop_body
done0:
%cmp0 = icmp eq i32 %b, 0
br i1 %cmp0, label %done1, label %loop_body
done1:
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #1
attributes #1 = { nounwind readonly }