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
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=riscv64 | FileCheck %s
; Make sure we don't emit a pair of shift for the zext in the preheader. We
; can tell that bit 31 is 0 in the preheader and rely on %n already being
; sign extended without adding zeros explicitly.
define void @test1(ptr nocapture noundef %a, i32 noundef signext %n) {
; CHECK-LABEL: test1:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: blez a1, .LBB0_2
; CHECK-NEXT: .LBB0_1: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: lw a2, 0(a0)
; CHECK-NEXT: addiw a2, a2, 4
; CHECK-NEXT: sw a2, 0(a0)
; CHECK-NEXT: addi a1, a1, -1
; CHECK-NEXT: addi a0, a0, 4
; CHECK-NEXT: bnez a1, .LBB0_1
; CHECK-NEXT: .LBB0_2: # %for.cond.cleanup
; CHECK-NEXT: ret
entry:
%cmp3 = icmp sgt i32 %n, 0
br i1 %cmp3, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%wide.trip.count = zext i32 %n to i64
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
ret void
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
%0 = load i32, ptr %arrayidx, align 4
%add = add nsw i32 %0, 4
store i32 %add, ptr %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
; Make sure we convert the 4294967294 in for.body.preheader.new to -2 based on
; the upper 33 bits being zero by the dominating condition %cmp3.
define void @test2(ptr nocapture noundef %a, i32 noundef signext %n) {
; CHECK-LABEL: test2:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: blez a1, .LBB1_7
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: li a3, 1
; CHECK-NEXT: andi a2, a1, 1
; CHECK-NEXT: bne a1, a3, .LBB1_3
; CHECK-NEXT: # %bb.2:
; CHECK-NEXT: li a3, 0
; CHECK-NEXT: j .LBB1_5
; CHECK-NEXT: .LBB1_3: # %for.body.preheader.new
; CHECK-NEXT: li a3, 0
; CHECK-NEXT: andi a1, a1, -2
; CHECK-NEXT: addi a4, a0, 4
; CHECK-NEXT: .LBB1_4: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: lw a5, -4(a4)
; CHECK-NEXT: lw a6, 0(a4)
; CHECK-NEXT: addiw a5, a5, 4
; CHECK-NEXT: sw a5, -4(a4)
; CHECK-NEXT: addiw a6, a6, 4
; CHECK-NEXT: sw a6, 0(a4)
; CHECK-NEXT: addi a3, a3, 2
; CHECK-NEXT: addi a4, a4, 8
; CHECK-NEXT: bne a1, a3, .LBB1_4
; CHECK-NEXT: .LBB1_5: # %for.cond.cleanup.loopexit.unr-lcssa
; CHECK-NEXT: beqz a2, .LBB1_7
; CHECK-NEXT: # %bb.6: # %for.body.epil
; CHECK-NEXT: slli a3, a3, 2
; CHECK-NEXT: add a0, a0, a3
; CHECK-NEXT: lw a1, 0(a0)
; CHECK-NEXT: addiw a1, a1, 4
; CHECK-NEXT: sw a1, 0(a0)
; CHECK-NEXT: .LBB1_7: # %for.cond.cleanup
; CHECK-NEXT: ret
entry:
%cmp3 = icmp sgt i32 %n, 0
br i1 %cmp3, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%wide.trip.count = zext i32 %n to i64
%xtraiter = and i64 %wide.trip.count, 1
%0 = icmp eq i32 %n, 1
br i1 %0, label %for.cond.cleanup.loopexit.unr-lcssa, label %for.body.preheader.new
for.body.preheader.new: ; preds = %for.body.preheader
%unroll_iter = and i64 %wide.trip.count, 4294967294
br label %for.body
for.cond.cleanup.loopexit.unr-lcssa: ; preds = %for.body, %for.body.preheader
%indvars.iv.unr = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next.1, %for.body ]
%lcmp.mod.not = icmp eq i64 %xtraiter, 0
br i1 %lcmp.mod.not, label %for.cond.cleanup, label %for.body.epil
for.body.epil: ; preds = %for.cond.cleanup.loopexit.unr-lcssa
%arrayidx.epil = getelementptr inbounds i32, ptr %a, i64 %indvars.iv.unr
%1 = load i32, ptr %arrayidx.epil, align 4
%add.epil = add nsw i32 %1, 4
store i32 %add.epil, ptr %arrayidx.epil, align 4
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.body.epil, %for.cond.cleanup.loopexit.unr-lcssa, %entry
ret void
for.body: ; preds = %for.body, %for.body.preheader.new
%indvars.iv = phi i64 [ 0, %for.body.preheader.new ], [ %indvars.iv.next.1, %for.body ]
%niter = phi i64 [ 0, %for.body.preheader.new ], [ %niter.next.1, %for.body ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
%2 = load i32, ptr %arrayidx, align 4
%add = add nsw i32 %2, 4
store i32 %add, ptr %arrayidx, align 4
%indvars.iv.next = or i64 %indvars.iv, 1
%arrayidx.1 = getelementptr inbounds i32, ptr %a, i64 %indvars.iv.next
%3 = load i32, ptr %arrayidx.1, align 4
%add.1 = add nsw i32 %3, 4
store i32 %add.1, ptr %arrayidx.1, align 4
%indvars.iv.next.1 = add nuw nsw i64 %indvars.iv, 2
%niter.next.1 = add i64 %niter, 2
%niter.ncmp.1 = icmp eq i64 %niter.next.1, %unroll_iter
br i1 %niter.ncmp.1, label %for.cond.cleanup.loopexit.unr-lcssa, label %for.body
}
|
