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
|
; RUN: opt %loadPolly -polly-codegen \
; RUN: -S < %s | FileCheck %s
define void @foo(float* %A, i1 %cond0, i1 %cond1) {
entry:
br label %loop
loop:
%indvar = phi i64 [0, %entry], [%indvar.next, %backedge]
%val0 = fadd float 1.0, 2.0
%val1 = fadd float 1.0, 2.0
br i1 %cond0, label %branch1, label %backedge
; CHECK-LABEL: polly.stmt.loop:
; CHECK-NEXT: %polly.subregion.iv = phi i32 [ 0, %polly.stmt.loop.entry ]
; CHECK-NEXT: %p_val0 = fadd float 1.000000e+00, 2.000000e+00
; CHECK-NEXT: %p_val1 = fadd float 1.000000e+00, 2.000000e+00
; CHECK-NEXT: %polly.subregion.iv.inc = add i32 %polly.subregion.iv, 1
; CHECK-NEXT: store float %p_val0, float* %merge.phiops
; CHECK-NEXT: br i1
; The interesting instruction here is %val2, which does not dominate the exit of
; the non-affine region. Care needs to be taken when code-generating this write.
; Specifically, at some point we modeled this scalar write, which we tried to
; code generate in the exit block of the non-affine region.
branch1:
%val2 = fadd float 1.0, 2.0
br i1 %cond1, label %branch2, label %backedge
; CHECK-LABEL: polly.stmt.branch1:
; CHECK-NEXT: %p_val2 = fadd float 1.000000e+00, 2.000000e+00
; CHECK-NEXT: store float %p_val1, float* %merge.phiops
; CHECK-NEXT: br i1
branch2:
br label %backedge
; CHECK-LABEL: polly.stmt.branch2:
; CHECK-NEXT: store float %p_val2, float* %merge.phiops
; CHECK-NEXT: br label
backedge:
%merge = phi float [%val0, %loop], [%val1, %branch1], [%val2, %branch2]
%indvar.next = add i64 %indvar, 1
store float %merge, float* %A
%cmp = icmp sle i64 %indvar.next, 100
br i1 %cmp, label %loop, label %exit
exit:
ret void
}
|
