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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+zdinx,+zilsd -verify-machineinstrs \
; RUN: -code-model=medium < %s | FileCheck %s
@g_0 = global double 0.0
define double @load_g_0() nounwind {
; CHECK-LABEL: load_g_0:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: .Lpcrel_hi0:
; CHECK-NEXT: auipc a0, %pcrel_hi(g_0)
; CHECK-NEXT: ld a0, %pcrel_lo(.Lpcrel_hi0)(a0)
; CHECK-NEXT: ret
entry:
%0 = load double, ptr @g_0
ret double %0
}
define void @store_g_0() nounwind {
; CHECK-LABEL: store_g_0:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: .Lpcrel_hi1:
; CHECK-NEXT: auipc a0, %pcrel_hi(g_0)
; CHECK-NEXT: sd zero, %pcrel_lo(.Lpcrel_hi1)(a0)
; CHECK-NEXT: ret
entry:
store double 0.0, ptr @g_0
ret void
}
%struct.S = type { double, double }
define double @fold_addi_from_different_bb(i32 %k, i32 %n, ptr %a) nounwind {
; CHECK-LABEL: fold_addi_from_different_bb:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi sp, sp, -32
; CHECK-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
; CHECK-NEXT: blez a1, .LBB2_3
; CHECK-NEXT: # %bb.1: # %for.body.lr.ph
; CHECK-NEXT: mv s2, a2
; CHECK-NEXT: mv s3, a1
; CHECK-NEXT: li s0, 0
; CHECK-NEXT: li s1, 0
; CHECK-NEXT: slli a0, a0, 4
; CHECK-NEXT: add s4, a2, a0
; CHECK-NEXT: .LBB2_2: # %for.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: mv a0, s2
; CHECK-NEXT: call f
; CHECK-NEXT: ld a0, 8(s4)
; CHECK-NEXT: addi s3, s3, -1
; CHECK-NEXT: fadd.d s0, a0, s0
; CHECK-NEXT: bnez s3, .LBB2_2
; CHECK-NEXT: j .LBB2_4
; CHECK-NEXT: .LBB2_3:
; CHECK-NEXT: li s0, 0
; CHECK-NEXT: li s1, 0
; CHECK-NEXT: .LBB2_4: # %for.cond.cleanup
; CHECK-NEXT: mv a0, s0
; CHECK-NEXT: mv a1, s1
; CHECK-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 32
; CHECK-NEXT: ret
entry:
%cmp4 = icmp sgt i32 %n, 0
br i1 %cmp4, label %for.body.lr.ph, label %for.cond.cleanup
for.body.lr.ph: ; preds = %entry
%y = getelementptr inbounds %struct.S, ptr %a, i32 %k, i32 1
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
%s.0.lcssa = phi double [ 0.0, %entry ], [ %add, %for.body ]
ret double %s.0.lcssa
for.body: ; preds = %for.body.lr.ph, %for.body
%i.06 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
%s.05 = phi double [ 0.0, %for.body.lr.ph ], [ %add, %for.body ]
call void @f(ptr %a)
%0 = load double, ptr %y, align 8
%add = fadd double %0, %s.05
%inc = add nuw nsw i32 %i.06, 1
%exitcond.not = icmp eq i32 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
declare void @f(ptr)
define void @split_offset(ptr %dest, double %x) {
; CHECK-LABEL: split_offset:
; CHECK: # %bb.0:
; CHECK-NEXT: mv a3, a2
; CHECK-NEXT: addi a0, a0, 2047
; CHECK-NEXT: mv a2, a1
; CHECK-NEXT: sd a2, 1(a0)
; CHECK-NEXT: sd a2, 9(a0)
; CHECK-NEXT: sd a2, 17(a0)
; CHECK-NEXT: sd a2, 25(a0)
; CHECK-NEXT: ret
%p1 = getelementptr double, ptr %dest, i32 256
store double %x, ptr %p1
%p2 = getelementptr double, ptr %dest, i32 257
store double %x, ptr %p2
%p3 = getelementptr double, ptr %dest, i32 258
store double %x, ptr %p3
%p4 = getelementptr double, ptr %dest, i32 259
store double %x, ptr %p4
ret void
}
|
