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
|
; RUN: opt --verify %s
define void @test_vp_int(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n) {
%r0 = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r1 = call <8 x i32> @llvm.vp.sub.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r2 = call <8 x i32> @llvm.vp.mul.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r3 = call <8 x i32> @llvm.vp.sdiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r4 = call <8 x i32> @llvm.vp.srem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r5 = call <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r6 = call <8 x i32> @llvm.vp.urem.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r7 = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r8 = call <8 x i32> @llvm.vp.or.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%r9 = call <8 x i32> @llvm.vp.xor.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rA = call <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rB = call <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
%rC = call <8 x i32> @llvm.vp.shl.v8i32(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %n)
ret void
}
define void @test_vp_fp(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n) {
%r0 = call <8 x double> @llvm.vp.fadd.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)
%r1 = call <8 x double> @llvm.vp.fsub.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)
%r2 = call <8 x double> @llvm.vp.fmul.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)
%r3 = call <8 x double> @llvm.vp.fdiv.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)
%r4 = call <8 x double> @llvm.vp.frem.v8f64(<8 x double> %f0, <8 x double> %f1, <8 x i1> %m, i32 %n)
ret void
}
; TODO: test_vp_constrained_fp
define void @test_vp_reduction(i32 %x, <8 x i32> %vi, <8 x float> %vf, float %f, <8 x i1> %m, i32 %n) {
%r0 = call i32 @llvm.vp.reduce.add.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
%r1 = call i32 @llvm.vp.reduce.mul.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
%r2 = call i32 @llvm.vp.reduce.and.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
%r3 = call i32 @llvm.vp.reduce.or.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
%r4 = call i32 @llvm.vp.reduce.xor.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
%r5 = call i32 @llvm.vp.reduce.smax.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
%r6 = call i32 @llvm.vp.reduce.smin.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
%r7 = call i32 @llvm.vp.reduce.umax.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
%r8 = call i32 @llvm.vp.reduce.umin.v8i32(i32 %x, <8 x i32> %vi, <8 x i1> %m, i32 %n)
%r9 = call float @llvm.vp.reduce.fmin.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)
%rA = call float @llvm.vp.reduce.fmax.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)
%rB = call float @llvm.vp.reduce.fadd.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)
%rC = call float @llvm.vp.reduce.fmul.v8f32(float %f, <8 x float> %vf, <8 x i1> %m, i32 %n)
ret void
}
define void @test_vp_splice0(<8 x i32> %i0, <8 x i32> %i1, <8 x i1> %m, i32 %l0, i32 %l1) {
%r0 = call <8 x i32> @llvm.experimental.vp.splice.v8i32(<8 x i32> %i0, <8 x i32> %i1, i32 2, <8 x i1> %m, i32 %l0, i32 %l1)
ret void
}
define void @test_vp_splice1(<vscale x 8 x i32> %i0, <vscale x 8 x i32> %i1, <vscale x 8 x i1> %m, i32 %l0, i32 %l1) {
%r0 = call <vscale x 8 x i32> @llvm.experimental.vp.splice.nxv8i32(<vscale x 8 x i32> %i0, <vscale x 8 x i32> %i1, i32 -1, <vscale x 8 x i1> %m, i32 %l0, i32 %l1)
ret void
}
; integer arith
declare <8 x i32> @llvm.vp.add.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.sub.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.mul.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.sdiv.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.srem.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.udiv.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.urem.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
; bit arith
declare <8 x i32> @llvm.vp.and.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.or.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.xor.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.ashr.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.lshr.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
declare <8 x i32> @llvm.vp.shl.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)
; fp arith
declare <8 x double> @llvm.vp.fadd.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)
declare <8 x double> @llvm.vp.fsub.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)
declare <8 x double> @llvm.vp.fmul.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)
declare <8 x double> @llvm.vp.fdiv.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)
declare <8 x double> @llvm.vp.frem.v8f64(<8 x double>, <8 x double>, <8 x i1>, i32)
; reductions
declare i32 @llvm.vp.reduce.add.v8i32(i32, <8 x i32>, <8 x i1>, i32)
declare i32 @llvm.vp.reduce.mul.v8i32(i32, <8 x i32>, <8 x i1>, i32)
declare i32 @llvm.vp.reduce.and.v8i32(i32, <8 x i32>, <8 x i1>, i32)
declare i32 @llvm.vp.reduce.or.v8i32(i32, <8 x i32>, <8 x i1>, i32)
declare i32 @llvm.vp.reduce.xor.v8i32(i32, <8 x i32>, <8 x i1>, i32)
declare i32 @llvm.vp.reduce.smax.v8i32(i32, <8 x i32>, <8 x i1>, i32)
declare i32 @llvm.vp.reduce.smin.v8i32(i32, <8 x i32>, <8 x i1>, i32)
declare i32 @llvm.vp.reduce.umax.v8i32(i32, <8 x i32>, <8 x i1>, i32)
declare i32 @llvm.vp.reduce.umin.v8i32(i32, <8 x i32>, <8 x i1>, i32)
declare float @llvm.vp.reduce.fmin.v8f32(float, <8 x float>, <8 x i1>, i32)
declare float @llvm.vp.reduce.fmax.v8f32(float, <8 x float>, <8 x i1>, i32)
declare float @llvm.vp.reduce.fadd.v8f32(float, <8 x float>, <8 x i1>, i32)
declare float @llvm.vp.reduce.fmul.v8f32(float, <8 x float>, <8 x i1>, i32)
; shuffles
declare <8 x i32> @llvm.experimental.vp.splice.v8i32(<8 x i32>, <8 x i32>, i32, <8 x i1>, i32, i32)
declare <vscale x 8 x i32> @llvm.experimental.vp.splice.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>, i32, <vscale x 8 x i1>, i32, i32)
|
