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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt < %s -passes=msan -S | FileCheck %s
;
; Forked from llvm/test/CodeGen/X86/f16c-intrinsics.ll
;
; Handled by handleSSEVectorConvertIntrinsicByProp:
; - llvm.x86.vcvtps2ph.128/256
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
define <8 x i16> @test_x86_vcvtps2ph_128(<4 x float> %a0) #0 {
; CHECK-LABEL: define <8 x i16> @test_x86_vcvtps2ph_128(
; CHECK-SAME: <4 x float> [[A0:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <4 x i32> [[TMP1]], zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = sext <4 x i1> [[TMP2]] to <4 x i16>
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <4 x i16> [[TMP3]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[RES:%.*]] = call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[A0]], i32 0)
; CHECK-NEXT: store <8 x i16> [[TMP11]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i16> [[RES]]
;
%res = call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %a0, i32 0) ; <<8 x i16>> [#uses=1]
ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float>, i32) nounwind readonly
define <8 x i16> @test_x86_vcvtps2ph_256(<8 x float> %a0) #0 {
; CHECK-LABEL: define <8 x i16> @test_x86_vcvtps2ph_256(
; CHECK-SAME: <8 x float> [[A0:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i32>, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <8 x i32> [[TMP1]], zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = sext <8 x i1> [[TMP2]] to <8 x i16>
; CHECK-NEXT: [[RES:%.*]] = call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> [[A0]], i32 0)
; CHECK-NEXT: store <8 x i16> [[TMP3]], ptr @__msan_retval_tls, align 8
; CHECK-NEXT: ret <8 x i16> [[RES]]
;
%res = call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> %a0, i32 0) ; <<8 x i16>> [#uses=1]
ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float>, i32) nounwind readonly
define void @test_x86_vcvtps2ph_256_m(ptr nocapture %d, <8 x float> %a) nounwind #0 {
; CHECK-LABEL: define void @test_x86_vcvtps2ph_256_m(
; CHECK-SAME: ptr captures(none) [[D:%.*]], <8 x float> [[A:%.*]]) #[[ATTR2:[0-9]+]] {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[TMP17:%.*]] = load <8 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 8) to ptr), align 8
; CHECK-NEXT: [[TMP18:%.*]] = load i64, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP20:%.*]] = icmp ne <8 x i32> [[TMP17]], zeroinitializer
; CHECK-NEXT: [[TMP21:%.*]] = sext <8 x i1> [[TMP20]] to <8 x i16>
; CHECK-NEXT: [[TMP0:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> [[A]], i32 3)
; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i64 [[TMP18]], 0
; CHECK-NEXT: br i1 [[_MSCMP1]], label %[[BB5:.*]], label %[[BB6:.*]], !prof [[PROF1:![0-9]+]]
; CHECK: [[BB5]]:
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR4:[0-9]+]]
; CHECK-NEXT: unreachable
; CHECK: [[BB6]]:
; CHECK-NEXT: [[TMP1:%.*]] = ptrtoint ptr [[D]] to i64
; CHECK-NEXT: [[TMP2:%.*]] = xor i64 [[TMP1]], 87960930222080
; CHECK-NEXT: [[TMP3:%.*]] = inttoptr i64 [[TMP2]] to ptr
; CHECK-NEXT: store <8 x i16> [[TMP21]], ptr [[TMP3]], align 16
; CHECK-NEXT: store <8 x i16> [[TMP0]], ptr [[D]], align 16
; CHECK-NEXT: ret void
;
entry:
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.256(<8 x float> %a, i32 3)
store <8 x i16> %0, ptr %d, align 16
ret void
}
define void @test_x86_vcvtps2ph_128_m(ptr nocapture %d, <4 x float> %a) nounwind #0 {
; CHECK-LABEL: define void @test_x86_vcvtps2ph_128_m(
; CHECK-SAME: ptr captures(none) [[D:%.*]], <4 x float> [[A:%.*]]) #[[ATTR2]] {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[TMP9:%.*]] = load <4 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 8) to ptr), align 8
; CHECK-NEXT: [[TMP10:%.*]] = load i64, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP12:%.*]] = icmp ne <4 x i32> [[TMP9]], zeroinitializer
; CHECK-NEXT: [[TMP13:%.*]] = sext <4 x i1> [[TMP12]] to <4 x i16>
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <4 x i16> [[TMP13]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[TMP0:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[A]], i32 3)
; CHECK-NEXT: [[_MSPROP:%.*]] = shufflevector <8 x i16> [[TMP11]], <8 x i16> splat (i16 -1), <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i16> [[TMP0]], <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i64 [[TMP10]], 0
; CHECK-NEXT: br i1 [[_MSCMP1]], label %[[BB7:.*]], label %[[BB8:.*]], !prof [[PROF1]]
; CHECK: [[BB7]]:
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR4]]
; CHECK-NEXT: unreachable
; CHECK: [[BB8]]:
; CHECK-NEXT: [[TMP2:%.*]] = ptrtoint ptr [[D]] to i64
; CHECK-NEXT: [[TMP3:%.*]] = xor i64 [[TMP2]], 87960930222080
; CHECK-NEXT: [[TMP4:%.*]] = inttoptr i64 [[TMP3]] to ptr
; CHECK-NEXT: store <4 x i16> [[_MSPROP]], ptr [[TMP4]], align 8
; CHECK-NEXT: store <4 x i16> [[TMP1]], ptr [[D]], align 8
; CHECK-NEXT: ret void
;
entry:
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %a, i32 3)
%1 = shufflevector <8 x i16> %0, <8 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
store <4 x i16> %1, ptr %d, align 8
ret void
}
define void @test_x86_vcvtps2ph_128_m2(ptr nocapture %hf4x16, <4 x float> %f4X86) #0 {
; CHECK-LABEL: define void @test_x86_vcvtps2ph_128_m2(
; CHECK-SAME: ptr captures(none) [[HF4X16:%.*]], <4 x float> [[F4X86:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[TMP0:%.*]] = load <4 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 8) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load i64, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <4 x i32> [[TMP0]], zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = sext <4 x i1> [[TMP2]] to <4 x i16>
; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <4 x i16> [[TMP3]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[TMP11:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[F4X86]], i32 3)
; CHECK-NEXT: [[TMP13:%.*]] = bitcast <8 x i16> [[TMP14]] to <2 x i64>
; CHECK-NEXT: [[TMP12:%.*]] = bitcast <8 x i16> [[TMP11]] to <2 x double>
; CHECK-NEXT: [[_MSPROP:%.*]] = extractelement <2 x i64> [[TMP13]], i32 0
; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <2 x double> [[TMP12]], i32 0
; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i64 [[TMP1]], 0
; CHECK-NEXT: br i1 [[_MSCMP1]], label %[[BB8:.*]], label %[[BB9:.*]], !prof [[PROF1]]
; CHECK: [[BB8]]:
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR4]]
; CHECK-NEXT: unreachable
; CHECK: [[BB9]]:
; CHECK-NEXT: [[TMP15:%.*]] = ptrtoint ptr [[HF4X16]] to i64
; CHECK-NEXT: [[TMP16:%.*]] = xor i64 [[TMP15]], 87960930222080
; CHECK-NEXT: [[TMP17:%.*]] = inttoptr i64 [[TMP16]] to ptr
; CHECK-NEXT: store i64 [[_MSPROP]], ptr [[TMP17]], align 8
; CHECK-NEXT: store double [[VECEXT]], ptr [[HF4X16]], align 8
; CHECK-NEXT: ret void
;
entry:
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %f4X86, i32 3)
%1 = bitcast <8 x i16> %0 to <2 x double>
%vecext = extractelement <2 x double> %1, i32 0
store double %vecext, ptr %hf4x16, align 8
ret void
}
define void @test_x86_vcvtps2ph_128_m3(ptr nocapture %hf4x16, <4 x float> %f4X86) #0 {
; CHECK-LABEL: define void @test_x86_vcvtps2ph_128_m3(
; CHECK-SAME: ptr captures(none) [[HF4X16:%.*]], <4 x float> [[F4X86:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[TMP0:%.*]] = load <4 x i32>, ptr inttoptr (i64 add (i64 ptrtoint (ptr @__msan_param_tls to i64), i64 8) to ptr), align 8
; CHECK-NEXT: [[TMP1:%.*]] = load i64, ptr @__msan_param_tls, align 8
; CHECK-NEXT: call void @llvm.donothing()
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <4 x i32> [[TMP0]], zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = sext <4 x i1> [[TMP2]] to <4 x i16>
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <4 x i16> [[TMP3]], <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[TMP11:%.*]] = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> [[F4X86]], i32 3)
; CHECK-NEXT: [[TMP12:%.*]] = bitcast <8 x i16> [[TMP13]] to <2 x i64>
; CHECK-NEXT: [[TMP14:%.*]] = bitcast <8 x i16> [[TMP11]] to <2 x i64>
; CHECK-NEXT: [[VECEXT:%.*]] = extractelement <2 x i64> [[TMP12]], i32 0
; CHECK-NEXT: [[VECEXT1:%.*]] = extractelement <2 x i64> [[TMP14]], i32 0
; CHECK-NEXT: [[_MSCMP1:%.*]] = icmp ne i64 [[TMP1]], 0
; CHECK-NEXT: br i1 [[_MSCMP1]], label %[[BB8:.*]], label %[[BB9:.*]], !prof [[PROF1]]
; CHECK: [[BB8]]:
; CHECK-NEXT: call void @__msan_warning_noreturn() #[[ATTR4]]
; CHECK-NEXT: unreachable
; CHECK: [[BB9]]:
; CHECK-NEXT: [[TMP15:%.*]] = ptrtoint ptr [[HF4X16]] to i64
; CHECK-NEXT: [[TMP16:%.*]] = xor i64 [[TMP15]], 87960930222080
; CHECK-NEXT: [[TMP17:%.*]] = inttoptr i64 [[TMP16]] to ptr
; CHECK-NEXT: store i64 [[VECEXT]], ptr [[TMP17]], align 8
; CHECK-NEXT: store i64 [[VECEXT1]], ptr [[HF4X16]], align 8
; CHECK-NEXT: ret void
;
entry:
%0 = tail call <8 x i16> @llvm.x86.vcvtps2ph.128(<4 x float> %f4X86, i32 3)
%1 = bitcast <8 x i16> %0 to <2 x i64>
%vecext = extractelement <2 x i64> %1, i32 0
store i64 %vecext, ptr %hf4x16, align 8
ret void
}
attributes #0 = { sanitize_memory }
|
