legalize-fmad.s64.mir
4.77 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
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -run-pass=legalizer %s -o - | FileCheck %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -run-pass=legalizer %s -o - | FileCheck %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -run-pass=legalizer %s -o - | FileCheck %s
---
name: test_fmad_s64_flush
machineFunctionInfo:
mode:
fp64-fp16-output-denormals: false
fp64-fp16-input-denormals: false
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5
; CHECK-LABEL: name: test_fmad_s64_flush
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY $vgpr4_vgpr5
; CHECK: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[COPY]], [[COPY1]]
; CHECK: [[FADD:%[0-9]+]]:_(s64) = G_FADD [[FMUL]], [[COPY2]]
; CHECK: $vgpr0_vgpr1 = COPY [[FADD]](s64)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(s64) = COPY $vgpr2_vgpr3
%2:_(s64) = COPY $vgpr4_vgpr5
%3:_(s64) = G_FMAD %0, %1, %2
$vgpr0_vgpr1 = COPY %3
...
---
name: test_fmad_v2s64_flush
machineFunctionInfo:
mode:
fp64-fp16-input-denormals: false
fp64-fp16-output-denormals: false
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7, $vgpr8_vgpr9_vgpr10_vgpr11
; CHECK-LABEL: name: test_fmad_v2s64_flush
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; CHECK: [[COPY2:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
; CHECK: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
; CHECK: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
; CHECK: [[UV4:%[0-9]+]]:_(s64), [[UV5:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY2]](<2 x s64>)
; CHECK: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[UV]], [[UV2]]
; CHECK: [[FADD:%[0-9]+]]:_(s64) = G_FADD [[FMUL]], [[UV4]]
; CHECK: [[FMUL1:%[0-9]+]]:_(s64) = G_FMUL [[UV1]], [[UV3]]
; CHECK: [[FADD1:%[0-9]+]]:_(s64) = G_FADD [[FMUL1]], [[UV5]]
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[FADD]](s64), [[FADD1]](s64)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
%0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
%2:_(<2 x s64>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
%3:_(<2 x s64>) = G_FMAD %0, %1, %2
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
...
---
name: test_fmad_s64_denorm
machineFunctionInfo:
mode:
fp64-fp16-input-denormals: true
fp64-fp16-output-denormals: true
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5
; CHECK-LABEL: name: test_fmad_s64_denorm
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY $vgpr4_vgpr5
; CHECK: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[COPY]], [[COPY1]]
; CHECK: [[FADD:%[0-9]+]]:_(s64) = G_FADD [[FMUL]], [[COPY2]]
; CHECK: $vgpr0_vgpr1 = COPY [[FADD]](s64)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(s64) = COPY $vgpr2_vgpr3
%2:_(s64) = COPY $vgpr4_vgpr5
%3:_(s64) = G_FMAD %0, %1, %2
$vgpr0_vgpr1 = COPY %3
...
---
name: test_fmad_v2s64_denorm
machineFunctionInfo:
mode:
fp64-fp16-input-denormals: true
fp64-fp16-output-denormals: true
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7, $vgpr8_vgpr9_vgpr10_vgpr11
; CHECK-LABEL: name: test_fmad_v2s64_denorm
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; CHECK: [[COPY2:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
; CHECK: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
; CHECK: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
; CHECK: [[UV4:%[0-9]+]]:_(s64), [[UV5:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY2]](<2 x s64>)
; CHECK: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[UV]], [[UV2]]
; CHECK: [[FADD:%[0-9]+]]:_(s64) = G_FADD [[FMUL]], [[UV4]]
; CHECK: [[FMUL1:%[0-9]+]]:_(s64) = G_FMUL [[UV1]], [[UV3]]
; CHECK: [[FADD1:%[0-9]+]]:_(s64) = G_FADD [[FMUL1]], [[UV5]]
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[FADD]](s64), [[FADD1]](s64)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
%0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
%2:_(<2 x s64>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
%3:_(<2 x s64>) = G_FMAD %0, %1, %2
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
...