atomic_optimizations_raw_buffer.ll
7.72 KB
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
138
139
140
141
142
143
144
145
146
147
148
149
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN64,GFX7LESS %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN64,GFX8MORE,GFX8MORE64,DPPCOMB %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN64,GFX8MORE,GFX8MORE64,DPPCOMB %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN64,GFX8MORE,GFX8MORE64 %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN32,GFX8MORE,GFX8MORE32 %s
declare i32 @llvm.amdgcn.workitem.id.x()
declare i32 @llvm.amdgcn.raw.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32)
declare i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i32)
; Show what the atomic optimization pass will do for raw buffers.
; GCN-LABEL: add_i32_constant:
; GCN32: s_mov_b32 s[[exec_lo:[0-9]+]], exec_lo
; GCN64: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt:[0-9]+]], s[[exec_lo]], 0
; GCN64: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt]], s[[exec_hi]], v[[mbcnt]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc{{(_lo)?}}, 0, v[[mbcnt]]
; GCN: s_and_saveexec_b{{32|64}} s[[exec:\[?[0-9:]+\]?]], vcc
; GCN32: s_bcnt1_i32_b32 s[[popcount:[0-9]+]], s[[exec_lo]]
; GCN64: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
; GCN: buffer_atomic_add v[[value]]
define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
entry:
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: add_i32_uniform:
; GCN32: s_mov_b32 s[[exec_lo:[0-9]+]], exec_lo
; GCN64: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt:[0-9]+]], s[[exec_lo]], 0
; GCN64: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt]], s[[exec_hi]], v[[mbcnt]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc{{(_lo)?}}, 0, v[[mbcnt]]
; GCN: s_and_saveexec_b{{32|64}} s[[exec:\[?[0-9:]+\]?]], vcc
; GCN32: s_bcnt1_i32_b32 s[[popcount:[0-9]+]], s[[exec_lo]]
; GCN64: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
; GCN: buffer_atomic_add v[[value]]
define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %additive) {
entry:
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: add_i32_varying_vdata:
; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
; GFX7LESS-NOT: s_bcnt1_i32_b64
; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
; DPPCOMB: v_add_u32_dpp
; DPPCOMB: v_add_u32_dpp
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
; GFX8MORE64: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
; GFX8MORE: buffer_atomic_add v[[value]]
define amdgpu_kernel void @add_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
entry:
%lane = call i32 @llvm.amdgcn.workitem.id.x()
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: add_i32_varying_offset:
; GCN-NOT: v_mbcnt_lo_u32_b32
; GCN-NOT: v_mbcnt_hi_u32_b32
; GCN-NOT: s_bcnt1_i32_b64
; GCN: buffer_atomic_add v{{[0-9]+}}
define amdgpu_kernel void @add_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
entry:
%lane = call i32 @llvm.amdgcn.workitem.id.x()
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i32_constant:
; GCN32: s_mov_b32 s[[exec_lo:[0-9]+]], exec_lo
; GCN64: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt:[0-9]+]], s[[exec_lo]], 0
; GCN64: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt]], s[[exec_hi]], v[[mbcnt]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc{{(_lo)?}}, 0, v[[mbcnt]]
; GCN: s_and_saveexec_b{{32|64}} s[[exec:\[?[0-9:]+\]?]], vcc
; GCN32: s_bcnt1_i32_b32 s[[popcount:[0-9]+]], s[[exec_lo]]
; GCN64: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: v_mul_u32_u24{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[popcount]], 5
; GCN: buffer_atomic_sub v[[value]]
define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
entry:
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i32_uniform:
; GCN32: s_mov_b32 s[[exec_lo:[0-9]+]], exec_lo
; GCN64: s_mov_b64 s{{\[}}[[exec_lo:[0-9]+]]:[[exec_hi:[0-9]+]]{{\]}}, exec
; GCN: v_mbcnt_lo_u32_b32{{(_e[0-9]+)?}} v[[mbcnt:[0-9]+]], s[[exec_lo]], 0
; GCN64: v_mbcnt_hi_u32_b32{{(_e[0-9]+)?}} v[[mbcnt]], s[[exec_hi]], v[[mbcnt]]
; GCN: v_cmp_eq_u32{{(_e[0-9]+)?}} vcc{{(_lo)?}}, 0, v[[mbcnt]]
; GCN: s_and_saveexec_b{{32|64}} s[[exec:\[?[0-9:]+\]?]], vcc
; GCN32: s_bcnt1_i32_b32 s[[popcount:[0-9]+]], s[[exec_lo]]
; GCN64: s_bcnt1_i32_b64 s[[popcount:[0-9]+]], s{{\[}}[[exec_lo]]:[[exec_hi]]{{\]}}
; GCN: s_mul_i32 s[[scalar_value:[0-9]+]], s{{[0-9]+}}, s[[popcount]]
; GCN: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
; GCN: buffer_atomic_sub v[[value]]
define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %subitive) {
entry:
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i32_varying_vdata:
; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
; GFX7LESS-NOT: s_bcnt1_i32_b64
; GFX7LESS: buffer_atomic_sub v{{[0-9]+}}
; DPPCOMB: v_add_u32_dpp
; DPPCOMB: v_add_u32_dpp
; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
; GFX8MORE64: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
; GFX8MORE: buffer_atomic_sub v[[value]]
define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
entry:
%lane = call i32 @llvm.amdgcn.workitem.id.x()
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: sub_i32_varying_offset:
; GCN-NOT: v_mbcnt_lo_u32_b32
; GCN-NOT: v_mbcnt_hi_u32_b32
; GCN-NOT: s_bcnt1_i32_b64
; GCN: buffer_atomic_sub v{{[0-9]+}}
define amdgpu_kernel void @sub_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
entry:
%lane = call i32 @llvm.amdgcn.workitem.id.x()
%old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0)
store i32 %old, i32 addrspace(1)* %out
ret void
}