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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -verify-machineinstrs -mtriple=aarch64-none-linux-gnu -mattr=+sve2,+lut,+bf16 | FileCheck %s
define <vscale x 16 x i8> @test_luti2_lane_i8(<vscale x 16 x i8> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti2_lane_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: luti2 z0.b, { z0.b }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti2.lane.nxv16i8(<vscale x 16 x i8> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 16 x i8> %res
}
define <vscale x 8 x i16> @test_luti2_lane_i16(<vscale x 8 x i16> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti2_lane_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: luti2 z0.h, { z0.h }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti2.lane.nxv8i16(<vscale x 8 x i16> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 8 x i16> %res
}
define <vscale x 8 x half> @test_luti2_lane_f16(<vscale x 8 x half> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti2_lane_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: luti2 z0.h, { z0.h }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 8 x half> @llvm.aarch64.sve.luti2.lane.nxv8f16(<vscale x 8 x half> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 8 x half> %res
}
define <vscale x 8 x bfloat> @test_luti2_lane_bf16(<vscale x 8 x bfloat> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti2_lane_bf16:
; CHECK: // %bb.0:
; CHECK-NEXT: luti2 z0.h, { z0.h }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti2.lane.nxv8bf16(<vscale x 8 x bfloat> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 8 x bfloat> %res
}
define <vscale x 16 x i8> @test_luti4_lane_i8(<vscale x 16 x i8> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti4_lane_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: luti4 z0.b, { z0.b }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 16 x i8> @llvm.aarch64.sve.luti4.lane.nxv16i8(<vscale x 16 x i8> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 16 x i8> %res
}
define <vscale x 8 x i16> @test_luti4_lane_i16(<vscale x 8 x i16> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti4_lane_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: luti4 z0.h, { z0.h }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.nxv8i16(<vscale x 8 x i16> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 8 x i16> %res
}
define <vscale x 8 x half> @test_luti4_lane_f16(<vscale x 8 x half> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti4_lane_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: luti4 z0.h, { z0.h }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.lane.nxv8f16(<vscale x 8 x half> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 8 x half> %res
}
define <vscale x 8 x bfloat> @test_luti4_lane_bf16(<vscale x 8 x bfloat> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti4_lane_bf16:
; CHECK: // %bb.0:
; CHECK-NEXT: luti4 z0.h, { z0.h }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.lane.nxv8bf16(<vscale x 8 x bfloat> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 8 x bfloat> %res
}
define <vscale x 8 x i16> @test_luti4_lane_i16_x2(<vscale x 8 x i16> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti4_lane_i16_x2:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z2.d, z0.d
; CHECK-NEXT: mov z3.d, z2.d
; CHECK-NEXT: luti4 z0.h, { z2.h, z3.h }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 8 x i16> @llvm.aarch64.sve.luti4.lane.x2.nxv8i16(<vscale x 8 x i16> %table, <vscale x 8 x i16> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 8 x i16> %res
}
define <vscale x 8 x half> @test_luti4_lane_f16_x2(<vscale x 8 x half> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti4_lane_f16_x2:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z2.d, z0.d
; CHECK-NEXT: mov z3.d, z2.d
; CHECK-NEXT: luti4 z0.h, { z2.h, z3.h }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 8 x half> @llvm.aarch64.sve.luti4.lane.x2.nxv8f16(<vscale x 8 x half> %table, <vscale x 8 x half> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 8 x half> %res
}
define <vscale x 8 x bfloat> @test_luti4_lane_bf16_x2(<vscale x 8 x bfloat> %table, <vscale x 16 x i8> %indices){
; CHECK-LABEL: test_luti4_lane_bf16_x2:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z2.d, z0.d
; CHECK-NEXT: mov z3.d, z2.d
; CHECK-NEXT: luti4 z0.h, { z2.h, z3.h }, z1[0]
; CHECK-NEXT: ret
%res= tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.luti4.lane.x2.nxv8bf16(<vscale x 8 x bfloat> %table, <vscale x 8 x bfloat> %table, <vscale x 16 x i8> %indices, i32 0)
ret <vscale x 8 x bfloat> %res
}
|
