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
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: riscv-registered-target
// RUN: %clang_cc1 -triple riscv64 -target-feature +f -target-feature +d -target-feature +experimental-v \
// RUN: -disable-O0-optnone -emit-llvm %s -o - | opt -S -mem2reg | FileCheck --check-prefix=CHECK-RV64 %s
#include <riscv_vector.h>
//
// CHECK-RV64-LABEL: @test_vfwredsum_vs_f32mf2_f64m1(
// CHECK-RV64-NEXT: entry:
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x double> @llvm.riscv.vfwredsum.nxv1f64.nxv1f32.i64(<vscale x 1 x double> [[DST:%.*]], <vscale x 1 x float> [[VECTOR:%.*]], <vscale x 1 x double> [[SCALAR:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: ret <vscale x 1 x double> [[TMP0]]
//
vfloat64m1_t test_vfwredsum_vs_f32mf2_f64m1(vfloat64m1_t dst,
vfloat32mf2_t vector,
vfloat64m1_t scalar, size_t vl) {
return vfwredsum_vs_f32mf2_f64m1(dst, vector, scalar, vl);
}
//
// CHECK-RV64-LABEL: @test_vfwredsum_vs_f32m1_f64m1(
// CHECK-RV64-NEXT: entry:
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x double> @llvm.riscv.vfwredsum.nxv1f64.nxv2f32.i64(<vscale x 1 x double> [[DST:%.*]], <vscale x 2 x float> [[VECTOR:%.*]], <vscale x 1 x double> [[SCALAR:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: ret <vscale x 1 x double> [[TMP0]]
//
vfloat64m1_t test_vfwredsum_vs_f32m1_f64m1(vfloat64m1_t dst,
vfloat32m1_t vector,
vfloat64m1_t scalar, size_t vl) {
return vfwredsum_vs_f32m1_f64m1(dst, vector, scalar, vl);
}
//
// CHECK-RV64-LABEL: @test_vfwredsum_vs_f32m2_f64m1(
// CHECK-RV64-NEXT: entry:
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x double> @llvm.riscv.vfwredsum.nxv1f64.nxv4f32.i64(<vscale x 1 x double> [[DST:%.*]], <vscale x 4 x float> [[VECTOR:%.*]], <vscale x 1 x double> [[SCALAR:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: ret <vscale x 1 x double> [[TMP0]]
//
vfloat64m1_t test_vfwredsum_vs_f32m2_f64m1(vfloat64m1_t dst,
vfloat32m2_t vector,
vfloat64m1_t scalar, size_t vl) {
return vfwredsum_vs_f32m2_f64m1(dst, vector, scalar, vl);
}
//
// CHECK-RV64-LABEL: @test_vfwredsum_vs_f32m4_f64m1(
// CHECK-RV64-NEXT: entry:
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x double> @llvm.riscv.vfwredsum.nxv1f64.nxv8f32.i64(<vscale x 1 x double> [[DST:%.*]], <vscale x 8 x float> [[VECTOR:%.*]], <vscale x 1 x double> [[SCALAR:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: ret <vscale x 1 x double> [[TMP0]]
//
vfloat64m1_t test_vfwredsum_vs_f32m4_f64m1(vfloat64m1_t dst,
vfloat32m4_t vector,
vfloat64m1_t scalar, size_t vl) {
return vfwredsum_vs_f32m4_f64m1(dst, vector, scalar, vl);
}
//
// CHECK-RV64-LABEL: @test_vfwredsum_vs_f32m8_f64m1(
// CHECK-RV64-NEXT: entry:
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x double> @llvm.riscv.vfwredsum.nxv1f64.nxv16f32.i64(<vscale x 1 x double> [[DST:%.*]], <vscale x 16 x float> [[VECTOR:%.*]], <vscale x 1 x double> [[SCALAR:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: ret <vscale x 1 x double> [[TMP0]]
//
vfloat64m1_t test_vfwredsum_vs_f32m8_f64m1(vfloat64m1_t dst,
vfloat32m8_t vector,
vfloat64m1_t scalar, size_t vl) {
return vfwredsum_vs_f32m8_f64m1(dst, vector, scalar, vl);
}
//
// CHECK-RV64-LABEL: @test_vfwredsum_vs_f32mf2_f64m1_m(
// CHECK-RV64-NEXT: entry:
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x double> @llvm.riscv.vfwredsum.mask.nxv1f64.nxv1f32.i64(<vscale x 1 x double> [[DST:%.*]], <vscale x 1 x float> [[VECTOR:%.*]], <vscale x 1 x double> [[SCALAR:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: ret <vscale x 1 x double> [[TMP0]]
//
vfloat64m1_t test_vfwredsum_vs_f32mf2_f64m1_m(vbool64_t mask, vfloat64m1_t dst,
vfloat32mf2_t vector,
vfloat64m1_t scalar, size_t vl) {
return vfwredsum_vs_f32mf2_f64m1_m(mask, dst, vector, scalar, vl);
}
//
// CHECK-RV64-LABEL: @test_vfwredsum_vs_f32m1_f64m1_m(
// CHECK-RV64-NEXT: entry:
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x double> @llvm.riscv.vfwredsum.mask.nxv1f64.nxv2f32.i64(<vscale x 1 x double> [[DST:%.*]], <vscale x 2 x float> [[VECTOR:%.*]], <vscale x 1 x double> [[SCALAR:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: ret <vscale x 1 x double> [[TMP0]]
//
vfloat64m1_t test_vfwredsum_vs_f32m1_f64m1_m(vbool32_t mask, vfloat64m1_t dst,
vfloat32m1_t vector,
vfloat64m1_t scalar, size_t vl) {
return vfwredsum_vs_f32m1_f64m1_m(mask, dst, vector, scalar, vl);
}
//
// CHECK-RV64-LABEL: @test_vfwredsum_vs_f32m2_f64m1_m(
// CHECK-RV64-NEXT: entry:
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x double> @llvm.riscv.vfwredsum.mask.nxv1f64.nxv4f32.i64(<vscale x 1 x double> [[DST:%.*]], <vscale x 4 x float> [[VECTOR:%.*]], <vscale x 1 x double> [[SCALAR:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: ret <vscale x 1 x double> [[TMP0]]
//
vfloat64m1_t test_vfwredsum_vs_f32m2_f64m1_m(vbool16_t mask, vfloat64m1_t dst,
vfloat32m2_t vector,
vfloat64m1_t scalar, size_t vl) {
return vfwredsum_vs_f32m2_f64m1_m(mask, dst, vector, scalar, vl);
}
//
// CHECK-RV64-LABEL: @test_vfwredsum_vs_f32m4_f64m1_m(
// CHECK-RV64-NEXT: entry:
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x double> @llvm.riscv.vfwredsum.mask.nxv1f64.nxv8f32.i64(<vscale x 1 x double> [[DST:%.*]], <vscale x 8 x float> [[VECTOR:%.*]], <vscale x 1 x double> [[SCALAR:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: ret <vscale x 1 x double> [[TMP0]]
//
vfloat64m1_t test_vfwredsum_vs_f32m4_f64m1_m(vbool8_t mask, vfloat64m1_t dst,
vfloat32m4_t vector,
vfloat64m1_t scalar, size_t vl) {
return vfwredsum_vs_f32m4_f64m1_m(mask, dst, vector, scalar, vl);
}
//
// CHECK-RV64-LABEL: @test_vfwredsum_vs_f32m8_f64m1_m(
// CHECK-RV64-NEXT: entry:
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x double> @llvm.riscv.vfwredsum.mask.nxv1f64.nxv16f32.i64(<vscale x 1 x double> [[DST:%.*]], <vscale x 16 x float> [[VECTOR:%.*]], <vscale x 1 x double> [[SCALAR:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: ret <vscale x 1 x double> [[TMP0]]
//
vfloat64m1_t test_vfwredsum_vs_f32m8_f64m1_m(vbool4_t mask, vfloat64m1_t dst,
vfloat32m8_t vector,
vfloat64m1_t scalar, size_t vl) {
return vfwredsum_vs_f32m8_f64m1_m(mask, dst, vector, scalar, vl);
}
|
