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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -O1 -mtriple=x86_64-unknown-unknown -o - | FileCheck %s
; We used to assert on widening the SMULFIX/UMULFIX/SMULFIXSAT node result,
; so primiary goal with the test is to see that we support legalization for
; such vectors.
declare <4 x i16> @llvm.smul.fix.v4i16(<4 x i16>, <4 x i16>, i32 immarg)
declare <4 x i16> @llvm.umul.fix.v4i16(<4 x i16>, <4 x i16>, i32 immarg)
declare <4 x i16> @llvm.smul.fix.sat.v4i16(<4 x i16>, <4 x i16>, i32 immarg)
declare <4 x i16> @llvm.umul.fix.sat.v4i16(<4 x i16>, <4 x i16>, i32 immarg)
define <4 x i16> @smulfix(<4 x i16> %a) {
; CHECK-LABEL: smulfix:
; CHECK: # %bb.0:
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = <1,2,3,4,u,u,u,u>
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: pmullw %xmm1, %xmm2
; CHECK-NEXT: psrlw $15, %xmm2
; CHECK-NEXT: pmulhw %xmm1, %xmm0
; CHECK-NEXT: paddw %xmm0, %xmm0
; CHECK-NEXT: por %xmm2, %xmm0
; CHECK-NEXT: retq
%t = call <4 x i16> @llvm.smul.fix.v4i16(<4 x i16> <i16 1, i16 2, i16 3, i16 4>, <4 x i16> %a, i32 15)
ret <4 x i16> %t
}
define <4 x i16> @umulfix(<4 x i16> %a) {
; CHECK-LABEL: umulfix:
; CHECK: # %bb.0:
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = <1,2,3,4,u,u,u,u>
; CHECK-NEXT: movdqa %xmm0, %xmm2
; CHECK-NEXT: pmullw %xmm1, %xmm2
; CHECK-NEXT: psrlw $15, %xmm2
; CHECK-NEXT: pmulhuw %xmm1, %xmm0
; CHECK-NEXT: paddw %xmm0, %xmm0
; CHECK-NEXT: por %xmm2, %xmm0
; CHECK-NEXT: retq
%t = call <4 x i16> @llvm.umul.fix.v4i16(<4 x i16> <i16 1, i16 2, i16 3, i16 4>, <4 x i16> %a, i32 15)
ret <4 x i16> %t
}
define <4 x i16> @smulfixsat(<4 x i16> %a) {
; CHECK-LABEL: smulfixsat:
; CHECK: # %bb.0:
; CHECK-NEXT: pextrw $2, %xmm0, %eax
; CHECK-NEXT: cwtl
; CHECK-NEXT: leal (%rax,%rax,2), %ecx
; CHECK-NEXT: movl %ecx, %edx
; CHECK-NEXT: shrl $16, %edx
; CHECK-NEXT: shldw $1, %cx, %dx
; CHECK-NEXT: sarl $16, %ecx
; CHECK-NEXT: cmpl $16384, %ecx # imm = 0x4000
; CHECK-NEXT: movl $32767, %eax # imm = 0x7FFF
; CHECK-NEXT: cmovgel %eax, %edx
; CHECK-NEXT: cmpl $-16384, %ecx # imm = 0xC000
; CHECK-NEXT: movl $32768, %ecx # imm = 0x8000
; CHECK-NEXT: cmovll %ecx, %edx
; CHECK-NEXT: pextrw $1, %xmm0, %esi
; CHECK-NEXT: leal (%rsi,%rsi), %edi
; CHECK-NEXT: movswl %si, %r8d
; CHECK-NEXT: movl %r8d, %esi
; CHECK-NEXT: shrl $16, %esi
; CHECK-NEXT: shldw $1, %di, %si
; CHECK-NEXT: sarl $16, %r8d
; CHECK-NEXT: cmpl $16384, %r8d # imm = 0x4000
; CHECK-NEXT: cmovgel %eax, %esi
; CHECK-NEXT: cmpl $-16384, %r8d # imm = 0xC000
; CHECK-NEXT: cmovll %ecx, %esi
; CHECK-NEXT: movd %xmm0, %edi
; CHECK-NEXT: movswl %di, %edi
; CHECK-NEXT: movl %edi, %r8d
; CHECK-NEXT: shrl $16, %r8d
; CHECK-NEXT: shldw $1, %di, %r8w
; CHECK-NEXT: sarl $16, %edi
; CHECK-NEXT: cmpl $16384, %edi # imm = 0x4000
; CHECK-NEXT: cmovgel %eax, %r8d
; CHECK-NEXT: cmpl $-16384, %edi # imm = 0xC000
; CHECK-NEXT: cmovll %ecx, %r8d
; CHECK-NEXT: movzwl %r8w, %edi
; CHECK-NEXT: movd %edi, %xmm1
; CHECK-NEXT: pinsrw $1, %esi, %xmm1
; CHECK-NEXT: pinsrw $2, %edx, %xmm1
; CHECK-NEXT: pextrw $3, %xmm0, %edx
; CHECK-NEXT: movswl %dx, %edx
; CHECK-NEXT: leal (,%rdx,4), %esi
; CHECK-NEXT: movl %esi, %edi
; CHECK-NEXT: shrl $16, %edi
; CHECK-NEXT: shldw $1, %si, %di
; CHECK-NEXT: sarl $14, %edx
; CHECK-NEXT: cmpl $16384, %edx # imm = 0x4000
; CHECK-NEXT: cmovgel %eax, %edi
; CHECK-NEXT: cmpl $-16384, %edx # imm = 0xC000
; CHECK-NEXT: cmovll %ecx, %edi
; CHECK-NEXT: pinsrw $3, %edi, %xmm1
; CHECK-NEXT: movdqa %xmm1, %xmm0
; CHECK-NEXT: retq
%t = call <4 x i16> @llvm.smul.fix.sat.v4i16(<4 x i16> <i16 1, i16 2, i16 3, i16 4>, <4 x i16> %a, i32 15)
ret <4 x i16> %t
}
define <4 x i16> @umulfixsat(<4 x i16> %a) {
; CHECK-LABEL: umulfixsat:
; CHECK: # %bb.0:
; CHECK-NEXT: pextrw $2, %xmm0, %eax
; CHECK-NEXT: leal (%rax,%rax,2), %eax
; CHECK-NEXT: movl %eax, %edx
; CHECK-NEXT: shrl $16, %edx
; CHECK-NEXT: movl %edx, %ecx
; CHECK-NEXT: shldw $1, %ax, %cx
; CHECK-NEXT: cmpl $32768, %edx # imm = 0x8000
; CHECK-NEXT: movl $65535, %eax # imm = 0xFFFF
; CHECK-NEXT: cmovael %eax, %ecx
; CHECK-NEXT: pextrw $1, %xmm0, %edx
; CHECK-NEXT: addl %edx, %edx
; CHECK-NEXT: movl %edx, %esi
; CHECK-NEXT: shrl $16, %esi
; CHECK-NEXT: movl %esi, %edi
; CHECK-NEXT: shldw $1, %dx, %di
; CHECK-NEXT: cmpl $32768, %esi # imm = 0x8000
; CHECK-NEXT: cmovael %eax, %edi
; CHECK-NEXT: movd %xmm0, %edx
; CHECK-NEXT: xorl %esi, %esi
; CHECK-NEXT: shldw $1, %dx, %si
; CHECK-NEXT: movl $32768, %edx # imm = 0x8000
; CHECK-NEXT: negl %edx
; CHECK-NEXT: cmovael %eax, %esi
; CHECK-NEXT: movzwl %si, %edx
; CHECK-NEXT: movd %edx, %xmm1
; CHECK-NEXT: pinsrw $1, %edi, %xmm1
; CHECK-NEXT: pinsrw $2, %ecx, %xmm1
; CHECK-NEXT: pextrw $3, %xmm0, %ecx
; CHECK-NEXT: shll $2, %ecx
; CHECK-NEXT: movl %ecx, %edx
; CHECK-NEXT: shrl $16, %edx
; CHECK-NEXT: movl %edx, %esi
; CHECK-NEXT: shldw $1, %cx, %si
; CHECK-NEXT: cmpl $32768, %edx # imm = 0x8000
; CHECK-NEXT: cmovael %eax, %esi
; CHECK-NEXT: pinsrw $3, %esi, %xmm1
; CHECK-NEXT: movdqa %xmm1, %xmm0
; CHECK-NEXT: retq
%t = call <4 x i16> @llvm.umul.fix.sat.v4i16(<4 x i16> <i16 1, i16 2, i16 3, i16 4>, <4 x i16> %a, i32 15)
ret <4 x i16> %t
}
|
