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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-unknown \
; RUN: < %s | FileCheck --check-prefix=CHECK-64 %s
; RUN: llc -verify-machineinstrs -mtriple=powerpc-unknown-unknown \
; RUN: < %s | FileCheck --check-prefix=CHECK-32 %s
define float @test_add(float* %ptr, float %incr) {
; CHECK-64-LABEL: test_add:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: sync
; CHECK-64-NEXT: lfs 0, 0(3)
; CHECK-64-NEXT: b .LBB0_3
; CHECK-64-NEXT: .LBB0_1: # %atomicrmw.start
; CHECK-64-NEXT: #
; CHECK-64-NEXT: stwcx. 5, 0, 3
; CHECK-64-NEXT: .LBB0_2: # %atomicrmw.start
; CHECK-64-NEXT: #
; CHECK-64-NEXT: stw 5, -4(1)
; CHECK-64-NEXT: cmplw 5, 4
; CHECK-64-NEXT: lfs 0, -4(1)
; CHECK-64-NEXT: beq 0, .LBB0_6
; CHECK-64-NEXT: .LBB0_3: # %atomicrmw.start
; CHECK-64-NEXT: # =>This Loop Header: Depth=1
; CHECK-64-NEXT: # Child Loop BB0_4 Depth 2
; CHECK-64-NEXT: fadds 2, 0, 1
; CHECK-64-NEXT: stfs 2, -8(1)
; CHECK-64-NEXT: stfs 0, -12(1)
; CHECK-64-NEXT: lwz 6, -8(1)
; CHECK-64-NEXT: lwz 4, -12(1)
; CHECK-64-NEXT: .LBB0_4: # %atomicrmw.start
; CHECK-64-NEXT: # Parent Loop BB0_3 Depth=1
; CHECK-64-NEXT: # => This Inner Loop Header: Depth=2
; CHECK-64-NEXT: lwarx 5, 0, 3
; CHECK-64-NEXT: cmpw 4, 5
; CHECK-64-NEXT: bne 0, .LBB0_1
; CHECK-64-NEXT: # %bb.5: # %atomicrmw.start
; CHECK-64-NEXT: #
; CHECK-64-NEXT: stwcx. 6, 0, 3
; CHECK-64-NEXT: bne 0, .LBB0_4
; CHECK-64-NEXT: b .LBB0_2
; CHECK-64-NEXT: .LBB0_6: # %atomicrmw.end
; CHECK-64-NEXT: fmr 1, 0
; CHECK-64-NEXT: lwsync
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: test_add:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: stwu 1, -32(1)
; CHECK-32-NEXT: .cfi_def_cfa_offset 32
; CHECK-32-NEXT: sync
; CHECK-32-NEXT: lfs 0, 0(3)
; CHECK-32-NEXT: b .LBB0_3
; CHECK-32-NEXT: .LBB0_1: # %atomicrmw.start
; CHECK-32-NEXT: #
; CHECK-32-NEXT: stwcx. 5, 0, 3
; CHECK-32-NEXT: .LBB0_2: # %atomicrmw.start
; CHECK-32-NEXT: #
; CHECK-32-NEXT: stw 5, 28(1)
; CHECK-32-NEXT: cmplw 5, 4
; CHECK-32-NEXT: lfs 0, 28(1)
; CHECK-32-NEXT: beq 0, .LBB0_6
; CHECK-32-NEXT: .LBB0_3: # %atomicrmw.start
; CHECK-32-NEXT: # =>This Loop Header: Depth=1
; CHECK-32-NEXT: # Child Loop BB0_4 Depth 2
; CHECK-32-NEXT: fadds 2, 0, 1
; CHECK-32-NEXT: stfs 2, 24(1)
; CHECK-32-NEXT: stfs 0, 20(1)
; CHECK-32-NEXT: lwz 6, 24(1)
; CHECK-32-NEXT: lwz 4, 20(1)
; CHECK-32-NEXT: .LBB0_4: # %atomicrmw.start
; CHECK-32-NEXT: # Parent Loop BB0_3 Depth=1
; CHECK-32-NEXT: # => This Inner Loop Header: Depth=2
; CHECK-32-NEXT: lwarx 5, 0, 3
; CHECK-32-NEXT: cmpw 4, 5
; CHECK-32-NEXT: bne 0, .LBB0_1
; CHECK-32-NEXT: # %bb.5: # %atomicrmw.start
; CHECK-32-NEXT: #
; CHECK-32-NEXT: stwcx. 6, 0, 3
; CHECK-32-NEXT: bne 0, .LBB0_4
; CHECK-32-NEXT: b .LBB0_2
; CHECK-32-NEXT: .LBB0_6: # %atomicrmw.end
; CHECK-32-NEXT: fmr 1, 0
; CHECK-32-NEXT: lwsync
; CHECK-32-NEXT: addi 1, 1, 32
; CHECK-32-NEXT: blr
entry:
%r = atomicrmw fadd float* %ptr, float %incr seq_cst
ret float %r
}
|
