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
128
129
130
131
132
133
134
135
136
137
|
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 2
; RUN: llc --global-isel=1 -mtriple=amdgcn--amdpal -mcpu=gfx1100 -stop-after=irtranslator -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=GFX11
; RUN: llc --global-isel=1 -mtriple=amdgcn--amdpal -mcpu=gfx1030 -stop-after=irtranslator -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=GFX10
declare amdgpu_cs_chain void @callee(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
declare amdgpu_cs_chain_preserve void @callee_preserve(<3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 })
declare void @llvm.amdgcn.cs.chain(ptr, i32, <3 x i32> inreg, { i32, ptr addrspace(5), i32, i32 }, i32, ...) noreturn
define amdgpu_cs_chain void @chain_call(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
; GFX11-LABEL: name: chain_call
; GFX11: bb.1 (%ir-block.0):
; GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GFX11-NEXT: {{ $}}
; GFX11-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
; GFX11-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
; GFX11-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
; GFX11-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
; GFX11-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
; GFX11-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
; GFX11-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
; GFX11-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
; GFX11-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee
; GFX11-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
; GFX11-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; GFX11-NEXT: [[GV1:%[0-9]+]]:ccr_sgpr_64(p0) = G_GLOBAL_VALUE @callee
; GFX11-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
; GFX11-NEXT: [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV]](s32)
; GFX11-NEXT: $sgpr0 = COPY [[INTRINSIC_CONVERGENT]](s32)
; GFX11-NEXT: [[INTRINSIC_CONVERGENT1:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV1]](s32)
; GFX11-NEXT: $sgpr1 = COPY [[INTRINSIC_CONVERGENT1]](s32)
; GFX11-NEXT: [[INTRINSIC_CONVERGENT2:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV2]](s32)
; GFX11-NEXT: $sgpr2 = COPY [[INTRINSIC_CONVERGENT2]](s32)
; GFX11-NEXT: $vgpr8 = COPY [[COPY3]](s32)
; GFX11-NEXT: $vgpr9 = COPY [[COPY4]](p5)
; GFX11-NEXT: $vgpr10 = COPY [[COPY5]](s32)
; GFX11-NEXT: $vgpr11 = COPY [[COPY6]](s32)
; GFX11-NEXT: SI_CS_CHAIN_TC_W32 [[GV1]](p0), @callee, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; GFX10-LABEL: name: chain_call
; GFX10: bb.1 (%ir-block.0):
; GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
; GFX10-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
; GFX10-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
; GFX10-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
; GFX10-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
; GFX10-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
; GFX10-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
; GFX10-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
; GFX10-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee
; GFX10-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
; GFX10-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; GFX10-NEXT: [[GV1:%[0-9]+]]:ccr_sgpr_64(p0) = G_GLOBAL_VALUE @callee
; GFX10-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
; GFX10-NEXT: [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV]](s32)
; GFX10-NEXT: $sgpr0 = COPY [[INTRINSIC_CONVERGENT]](s32)
; GFX10-NEXT: [[INTRINSIC_CONVERGENT1:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV1]](s32)
; GFX10-NEXT: $sgpr1 = COPY [[INTRINSIC_CONVERGENT1]](s32)
; GFX10-NEXT: [[INTRINSIC_CONVERGENT2:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV2]](s32)
; GFX10-NEXT: $sgpr2 = COPY [[INTRINSIC_CONVERGENT2]](s32)
; GFX10-NEXT: $vgpr8 = COPY [[COPY3]](s32)
; GFX10-NEXT: $vgpr9 = COPY [[COPY4]](p5)
; GFX10-NEXT: $vgpr10 = COPY [[COPY5]](s32)
; GFX10-NEXT: $vgpr11 = COPY [[COPY6]](s32)
; GFX10-NEXT: [[COPY7:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]](<4 x s32>)
; GFX10-NEXT: SI_CS_CHAIN_TC_W32 [[GV1]](p0), @callee, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
unreachable
}
define amdgpu_cs_chain void @chain_preserve_call(<3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr) {
; GFX11-LABEL: name: chain_preserve_call
; GFX11: bb.1 (%ir-block.0):
; GFX11-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GFX11-NEXT: {{ $}}
; GFX11-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
; GFX11-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
; GFX11-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
; GFX11-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
; GFX11-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
; GFX11-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
; GFX11-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
; GFX11-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
; GFX11-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee_preserve
; GFX11-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
; GFX11-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; GFX11-NEXT: [[GV1:%[0-9]+]]:ccr_sgpr_64(p0) = G_GLOBAL_VALUE @callee_preserve
; GFX11-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
; GFX11-NEXT: [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV]](s32)
; GFX11-NEXT: $sgpr0 = COPY [[INTRINSIC_CONVERGENT]](s32)
; GFX11-NEXT: [[INTRINSIC_CONVERGENT1:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV1]](s32)
; GFX11-NEXT: $sgpr1 = COPY [[INTRINSIC_CONVERGENT1]](s32)
; GFX11-NEXT: [[INTRINSIC_CONVERGENT2:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV2]](s32)
; GFX11-NEXT: $sgpr2 = COPY [[INTRINSIC_CONVERGENT2]](s32)
; GFX11-NEXT: $vgpr8 = COPY [[COPY3]](s32)
; GFX11-NEXT: $vgpr9 = COPY [[COPY4]](p5)
; GFX11-NEXT: $vgpr10 = COPY [[COPY5]](s32)
; GFX11-NEXT: $vgpr11 = COPY [[COPY6]](s32)
; GFX11-NEXT: SI_CS_CHAIN_TC_W32 [[GV1]](p0), @callee_preserve, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11
;
; GFX10-LABEL: name: chain_preserve_call
; GFX10: bb.1 (%ir-block.0):
; GFX10-NEXT: liveins: $sgpr0, $sgpr1, $sgpr2, $vgpr8, $vgpr9, $vgpr10, $vgpr11
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $sgpr0
; GFX10-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $sgpr1
; GFX10-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $sgpr2
; GFX10-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
; GFX10-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr8
; GFX10-NEXT: [[COPY4:%[0-9]+]]:_(p5) = COPY $vgpr9
; GFX10-NEXT: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr10
; GFX10-NEXT: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr11
; GFX10-NEXT: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @callee_preserve
; GFX10-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
; GFX10-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; GFX10-NEXT: [[GV1:%[0-9]+]]:ccr_sgpr_64(p0) = G_GLOBAL_VALUE @callee_preserve
; GFX10-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<3 x s32>)
; GFX10-NEXT: [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV]](s32)
; GFX10-NEXT: $sgpr0 = COPY [[INTRINSIC_CONVERGENT]](s32)
; GFX10-NEXT: [[INTRINSIC_CONVERGENT1:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV1]](s32)
; GFX10-NEXT: $sgpr1 = COPY [[INTRINSIC_CONVERGENT1]](s32)
; GFX10-NEXT: [[INTRINSIC_CONVERGENT2:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[UV2]](s32)
; GFX10-NEXT: $sgpr2 = COPY [[INTRINSIC_CONVERGENT2]](s32)
; GFX10-NEXT: $vgpr8 = COPY [[COPY3]](s32)
; GFX10-NEXT: $vgpr9 = COPY [[COPY4]](p5)
; GFX10-NEXT: $vgpr10 = COPY [[COPY5]](s32)
; GFX10-NEXT: $vgpr11 = COPY [[COPY6]](s32)
; GFX10-NEXT: [[COPY7:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr48_sgpr49_sgpr50_sgpr51
; GFX10-NEXT: $sgpr48_sgpr49_sgpr50_sgpr51 = COPY [[COPY7]](<4 x s32>)
; GFX10-NEXT: SI_CS_CHAIN_TC_W32 [[GV1]](p0), @callee_preserve, 0, -1, amdgpu_allvgprs, implicit $sgpr0, implicit $sgpr1, implicit $sgpr2, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $sgpr48_sgpr49_sgpr50_sgpr51
call void(ptr, i32, <3 x i32>, { i32, ptr addrspace(5), i32, i32 }, i32, ...) @llvm.amdgcn.cs.chain(ptr @callee_preserve, i32 -1, <3 x i32> inreg %sgpr, { i32, ptr addrspace(5), i32, i32 } %vgpr, i32 0)
unreachable
}
|
