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
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
|
// RUN: %clang_cc1 -triple x86_64-apple-darwin %s -emit-llvm -disable-llvm-passes -o - | FileCheck %s
typedef float float4 __attribute__((ext_vector_type(4)));
typedef short int si8 __attribute__((ext_vector_type(8)));
typedef unsigned int u4 __attribute__((ext_vector_type(4)));
__attribute__((address_space(1))) int int_as_one;
typedef int bar;
bar b;
void test_builtin_elementwise_abs(float f1, float f2, double d1, double d2,
float4 vf1, float4 vf2, si8 vi1, si8 vi2,
long long int i1, long long int i2, short si) {
// CHECK-LABEL: define void @test_builtin_elementwise_abs(
// CHECK: [[F1:%.+]] = load float, float* %f1.addr, align 4
// CHECK-NEXT: call float @llvm.fabs.f32(float [[F1]])
f2 = __builtin_elementwise_abs(f1);
// CHECK: [[D1:%.+]] = load double, double* %d1.addr, align 8
// CHECK-NEXT: call double @llvm.fabs.f64(double [[D1]])
d2 = __builtin_elementwise_abs(d1);
// CHECK: [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
// CHECK-NEXT: call <4 x float> @llvm.fabs.v4f32(<4 x float> [[VF1]])
vf2 = __builtin_elementwise_abs(vf1);
// CHECK: [[I1:%.+]] = load i64, i64* %i1.addr, align 8
// CHECK-NEXT: call i64 @llvm.abs.i64(i64 [[I1]], i1 false)
i2 = __builtin_elementwise_abs(i1);
// CHECK: [[VI1:%.+]] = load <8 x i16>, <8 x i16>* %vi1.addr, align 16
// CHECK-NEXT: call <8 x i16> @llvm.abs.v8i16(<8 x i16> [[VI1]], i1 false)
vi2 = __builtin_elementwise_abs(vi1);
// CHECK: [[CVI2:%.+]] = load <8 x i16>, <8 x i16>* %cvi2, align 16
// CHECK-NEXT: call <8 x i16> @llvm.abs.v8i16(<8 x i16> [[CVI2]], i1 false)
const si8 cvi2 = vi2;
vi2 = __builtin_elementwise_abs(cvi2);
// CHECK: [[IA1:%.+]] = load i32, i32 addrspace(1)* @int_as_one, align 4
// CHECK-NEXT: call i32 @llvm.abs.i32(i32 [[IA1]], i1 false)
b = __builtin_elementwise_abs(int_as_one);
// CHECK: call i32 @llvm.abs.i32(i32 -10, i1 false)
b = __builtin_elementwise_abs(-10);
// CHECK: [[SI:%.+]] = load i16, i16* %si.addr, align 2
// CHECK-NEXT: [[SI_EXT:%.+]] = sext i16 [[SI]] to i32
// CHECK-NEXT: [[RES:%.+]] = call i32 @llvm.abs.i32(i32 [[SI_EXT]], i1 false)
// CHECK-NEXT: = trunc i32 [[RES]] to i16
si = __builtin_elementwise_abs(si);
}
void test_builtin_elementwise_max(float f1, float f2, double d1, double d2,
float4 vf1, float4 vf2, long long int i1,
long long int i2, si8 vi1, si8 vi2,
unsigned u1, unsigned u2, u4 vu1, u4 vu2) {
// CHECK-LABEL: define void @test_builtin_elementwise_max(
// CHECK: [[F1:%.+]] = load float, float* %f1.addr, align 4
// CHECK-NEXT: [[F2:%.+]] = load float, float* %f2.addr, align 4
// CHECK-NEXT: call float @llvm.maxnum.f32(float %0, float %1)
f1 = __builtin_elementwise_max(f1, f2);
// CHECK: [[D1:%.+]] = load double, double* %d1.addr, align 8
// CHECK-NEXT: [[D2:%.+]] = load double, double* %d2.addr, align 8
// CHECK-NEXT: call double @llvm.maxnum.f64(double [[D1]], double [[D2]])
d1 = __builtin_elementwise_max(d1, d2);
// CHECK: [[D2:%.+]] = load double, double* %d2.addr, align 8
// CHECK-NEXT: call double @llvm.maxnum.f64(double 2.000000e+01, double [[D2]])
d1 = __builtin_elementwise_max(20.0, d2);
// CHECK: [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
// CHECK-NEXT: [[VF2:%.+]] = load <4 x float>, <4 x float>* %vf2.addr, align 16
// CHECK-NEXT: call <4 x float> @llvm.maxnum.v4f32(<4 x float> [[VF1]], <4 x float> [[VF2]])
vf1 = __builtin_elementwise_max(vf1, vf2);
// CHECK: [[I1:%.+]] = load i64, i64* %i1.addr, align 8
// CHECK-NEXT: [[I2:%.+]] = load i64, i64* %i2.addr, align 8
// CHECK-NEXT: call i64 @llvm.smax.i64(i64 [[I1]], i64 [[I2]])
i1 = __builtin_elementwise_max(i1, i2);
// CHECK: [[I1:%.+]] = load i64, i64* %i1.addr, align 8
// CHECK-NEXT: call i64 @llvm.smax.i64(i64 [[I1]], i64 10)
i1 = __builtin_elementwise_max(i1, 10);
// CHECK: [[VI1:%.+]] = load <8 x i16>, <8 x i16>* %vi1.addr, align 16
// CHECK-NEXT: [[VI2:%.+]] = load <8 x i16>, <8 x i16>* %vi2.addr, align 16
// CHECK-NEXT: call <8 x i16> @llvm.smax.v8i16(<8 x i16> [[VI1]], <8 x i16> [[VI2]])
vi1 = __builtin_elementwise_max(vi1, vi2);
// CHECK: [[U1:%.+]] = load i32, i32* %u1.addr, align 4
// CHECK-NEXT: [[U2:%.+]] = load i32, i32* %u2.addr, align 4
// CHECK-NEXT: call i32 @llvm.umax.i32(i32 [[U1]], i32 [[U2]])
u1 = __builtin_elementwise_max(u1, u2);
// CHECK: [[VU1:%.+]] = load <4 x i32>, <4 x i32>* %vu1.addr, align 16
// CHECK-NEXT: [[VU2:%.+]] = load <4 x i32>, <4 x i32>* %vu2.addr, align 16
// CHECK-NEXT: call <4 x i32> @llvm.umax.v4i32(<4 x i32> [[VU1]], <4 x i32> [[VU2]])
vu1 = __builtin_elementwise_max(vu1, vu2);
// CHECK: [[CVF1:%.+]] = load <4 x float>, <4 x float>* %cvf1, align 16
// CHECK-NEXT: [[VF2:%.+]] = load <4 x float>, <4 x float>* %vf2.addr, align 16
// CHECK-NEXT: call <4 x float> @llvm.maxnum.v4f32(<4 x float> [[CVF1]], <4 x float> [[VF2]])
const float4 cvf1 = vf1;
vf1 = __builtin_elementwise_max(cvf1, vf2);
// CHECK: [[VF2:%.+]] = load <4 x float>, <4 x float>* %vf2.addr, align 16
// CHECK-NEXT: [[CVF1:%.+]] = load <4 x float>, <4 x float>* %cvf1, align 16
// CHECK-NEXT: call <4 x float> @llvm.maxnum.v4f32(<4 x float> [[VF2]], <4 x float> [[CVF1]])
vf1 = __builtin_elementwise_max(vf2, cvf1);
// CHECK: [[IAS1:%.+]] = load i32, i32 addrspace(1)* @int_as_one, align 4
// CHECK-NEXT: [[B:%.+]] = load i32, i32* @b, align 4
// CHECK-NEXT: call i32 @llvm.smax.i32(i32 [[IAS1]], i32 [[B]])
int_as_one = __builtin_elementwise_max(int_as_one, b);
// CHECK: call i32 @llvm.smax.i32(i32 1, i32 97)
i1 = __builtin_elementwise_max(1, 'a');
}
void test_builtin_elementwise_min(float f1, float f2, double d1, double d2,
float4 vf1, float4 vf2, long long int i1,
long long int i2, si8 vi1, si8 vi2,
unsigned u1, unsigned u2, u4 vu1, u4 vu2) {
// CHECK-LABEL: define void @test_builtin_elementwise_min(
// CHECK: [[F1:%.+]] = load float, float* %f1.addr, align 4
// CHECK-NEXT: [[F2:%.+]] = load float, float* %f2.addr, align 4
// CHECK-NEXT: call float @llvm.minnum.f32(float %0, float %1)
f1 = __builtin_elementwise_min(f1, f2);
// CHECK: [[D1:%.+]] = load double, double* %d1.addr, align 8
// CHECK-NEXT: [[D2:%.+]] = load double, double* %d2.addr, align 8
// CHECK-NEXT: call double @llvm.minnum.f64(double [[D1]], double [[D2]])
d1 = __builtin_elementwise_min(d1, d2);
// CHECK: [[D1:%.+]] = load double, double* %d1.addr, align 8
// CHECK-NEXT: call double @llvm.minnum.f64(double [[D1]], double 2.000000e+00)
d1 = __builtin_elementwise_min(d1, 2.0);
// CHECK: [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
// CHECK-NEXT: [[VF2:%.+]] = load <4 x float>, <4 x float>* %vf2.addr, align 16
// CHECK-NEXT: call <4 x float> @llvm.minnum.v4f32(<4 x float> [[VF1]], <4 x float> [[VF2]])
vf1 = __builtin_elementwise_min(vf1, vf2);
// CHECK: [[I1:%.+]] = load i64, i64* %i1.addr, align 8
// CHECK-NEXT: [[I2:%.+]] = load i64, i64* %i2.addr, align 8
// CHECK-NEXT: call i64 @llvm.smin.i64(i64 [[I1]], i64 [[I2]])
i1 = __builtin_elementwise_min(i1, i2);
// CHECK: [[I2:%.+]] = load i64, i64* %i2.addr, align 8
// CHECK-NEXT: call i64 @llvm.smin.i64(i64 -11, i64 [[I2]])
i1 = __builtin_elementwise_min(-11, i2);
// CHECK: [[VI1:%.+]] = load <8 x i16>, <8 x i16>* %vi1.addr, align 16
// CHECK-NEXT: [[VI2:%.+]] = load <8 x i16>, <8 x i16>* %vi2.addr, align 16
// CHECK-NEXT: call <8 x i16> @llvm.smin.v8i16(<8 x i16> [[VI1]], <8 x i16> [[VI2]])
vi1 = __builtin_elementwise_min(vi1, vi2);
// CHECK: [[U1:%.+]] = load i32, i32* %u1.addr, align 4
// CHECK-NEXT: [[U2:%.+]] = load i32, i32* %u2.addr, align 4
// CHECK-NEXT: call i32 @llvm.umin.i32(i32 [[U1]], i32 [[U2]])
u1 = __builtin_elementwise_min(u1, u2);
// CHECK: [[U1:%.+]] = load i32, i32* %u1.addr, align 4
// CHECK-NEXT: [[ZEXT_U1:%.+]] = zext i32 [[U1]] to i64
// CHECK-NEXT: [[I2:%.+]] = load i64, i64* %i2.addr, align 8
// CHECK-NEXT: call i64 @llvm.smin.i64(i64 [[ZEXT_U1]], i64 [[I2]])
u1 = __builtin_elementwise_min(u1, i2);
// CHECK: [[VU1:%.+]] = load <4 x i32>, <4 x i32>* %vu1.addr, align 16
// CHECK-NEXT: [[VU2:%.+]] = load <4 x i32>, <4 x i32>* %vu2.addr, align 16
// CHECK-NEXT: call <4 x i32> @llvm.umin.v4i32(<4 x i32> [[VU1]], <4 x i32> [[VU2]])
vu1 = __builtin_elementwise_min(vu1, vu2);
// CHECK: [[CVF1:%.+]] = load <4 x float>, <4 x float>* %cvf1, align 16
// CHECK-NEXT: [[VF2:%.+]] = load <4 x float>, <4 x float>* %vf2.addr, align 16
// CHECK-NEXT: call <4 x float> @llvm.minnum.v4f32(<4 x float> [[CVF1]], <4 x float> [[VF2]])
const float4 cvf1 = vf1;
vf1 = __builtin_elementwise_min(cvf1, vf2);
// CHECK: [[VF2:%.+]] = load <4 x float>, <4 x float>* %vf2.addr, align 16
// CHECK-NEXT: [[CVF1:%.+]] = load <4 x float>, <4 x float>* %cvf1, align 16
// CHECK-NEXT: call <4 x float> @llvm.minnum.v4f32(<4 x float> [[VF2]], <4 x float> [[CVF1]])
vf1 = __builtin_elementwise_min(vf2, cvf1);
// CHECK: [[IAS1:%.+]] = load i32, i32 addrspace(1)* @int_as_one, align 4
// CHECK-NEXT: [[B:%.+]] = load i32, i32* @b, align 4
// CHECK-NEXT: call i32 @llvm.smin.i32(i32 [[IAS1]], i32 [[B]])
int_as_one = __builtin_elementwise_min(int_as_one, b);
}
void test_builtin_elementwise_ceil(float f1, float f2, double d1, double d2,
float4 vf1, float4 vf2) {
// CHECK-LABEL: define void @test_builtin_elementwise_ceil(
// CHECK: [[F1:%.+]] = load float, float* %f1.addr, align 4
// CHECK-NEXT: call float @llvm.ceil.f32(float [[F1]])
f2 = __builtin_elementwise_ceil(f1);
// CHECK: [[D1:%.+]] = load double, double* %d1.addr, align 8
// CHECK-NEXT: call double @llvm.ceil.f64(double [[D1]])
d2 = __builtin_elementwise_ceil(d1);
// CHECK: [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
// CHECK-NEXT: call <4 x float> @llvm.ceil.v4f32(<4 x float> [[VF1]])
vf2 = __builtin_elementwise_ceil(vf1);
}
void test_builtin_elementwise_floor(float f1, float f2, double d1, double d2,
float4 vf1, float4 vf2) {
// CHECK-LABEL: define void @test_builtin_elementwise_floor(
// CHECK: [[F1:%.+]] = load float, float* %f1.addr, align 4
// CHECK-NEXT: call float @llvm.floor.f32(float [[F1]])
f2 = __builtin_elementwise_floor(f1);
// CHECK: [[D1:%.+]] = load double, double* %d1.addr, align 8
// CHECK-NEXT: call double @llvm.floor.f64(double [[D1]])
d2 = __builtin_elementwise_floor(d1);
// CHECK: [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
// CHECK-NEXT: call <4 x float> @llvm.floor.v4f32(<4 x float> [[VF1]])
vf2 = __builtin_elementwise_floor(vf1);
}
void test_builtin_elementwise_roundeven(float f1, float f2, double d1, double d2,
float4 vf1, float4 vf2) {
// CHECK-LABEL: define void @test_builtin_elementwise_roundeven(
// CHECK: [[F1:%.+]] = load float, float* %f1.addr, align 4
// CHECK-NEXT: call float @llvm.roundeven.f32(float [[F1]])
f2 = __builtin_elementwise_roundeven(f1);
// CHECK: [[D1:%.+]] = load double, double* %d1.addr, align 8
// CHECK-NEXT: call double @llvm.roundeven.f64(double [[D1]])
d2 = __builtin_elementwise_roundeven(d1);
// CHECK: [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
// CHECK-NEXT: call <4 x float> @llvm.roundeven.v4f32(<4 x float> [[VF1]])
vf2 = __builtin_elementwise_roundeven(vf1);
}
void test_builtin_elementwise_trunc(float f1, float f2, double d1, double d2,
float4 vf1, float4 vf2) {
// CHECK-LABEL: define void @test_builtin_elementwise_trunc(
// CHECK: [[F1:%.+]] = load float, float* %f1.addr, align 4
// CHECK-NEXT: call float @llvm.trunc.f32(float [[F1]])
f2 = __builtin_elementwise_trunc(f1);
// CHECK: [[D1:%.+]] = load double, double* %d1.addr, align 8
// CHECK-NEXT: call double @llvm.trunc.f64(double [[D1]])
d2 = __builtin_elementwise_trunc(d1);
// CHECK: [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
// CHECK-NEXT: call <4 x float> @llvm.trunc.v4f32(<4 x float> [[VF1]])
vf2 = __builtin_elementwise_trunc(vf1);
}
|
