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
|
; RUN: llc < %s -mtriple=i686-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck -check-prefix=X32 %s
; RUN: llc < %s -mtriple=i386-pc-win32 -mcpu=corei7-avx -mattr=+avx | FileCheck -check-prefix=X32 %s
; RUN: llc < %s -mtriple=x86_64-win32 -mcpu=corei7-avx -mattr=+avx | FileCheck -check-prefix=WIN64 %s
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck -check-prefix=X64 %s
declare <16 x float> @func_float16_ptr(<16 x float>, <16 x float> *)
declare <16 x float> @func_float16(<16 x float>, <16 x float>)
declare i32 @func_int(i32, i32)
; WIN64: testf16_inp
; WIN64: vaddps {{.*}}, {{%ymm[0-1]}}
; WIN64: vaddps {{.*}}, {{%ymm[0-1]}}
; WIN64: leaq {{.*}}(%rsp), %rcx
; WIN64: call
; WIN64: ret
; X32: testf16_inp
; X32: movl %eax, (%esp)
; X32: vaddps {{.*}}, {{%ymm[0-1]}}
; X32: vaddps {{.*}}, {{%ymm[0-1]}}
; X32: call
; X32: ret
; X64: testf16_inp
; X64: vaddps {{.*}}, {{%ymm[0-1]}}
; X64: vaddps {{.*}}, {{%ymm[0-1]}}
; X64: leaq {{.*}}(%rsp), %rdi
; X64: call
; X64: ret
;test calling conventions - input parameters
define <16 x float> @testf16_inp(<16 x float> %a, <16 x float> %b) nounwind {
%y = alloca <16 x float>, align 16
%x = fadd <16 x float> %a, %b
%1 = call intel_ocl_bicc <16 x float> @func_float16_ptr(<16 x float> %x, <16 x float>* %y)
%2 = load <16 x float>* %y, align 16
%3 = fadd <16 x float> %2, %1
ret <16 x float> %3
}
;test calling conventions - preserved registers
; preserved ymm6-ymm15
; WIN64: testf16_regs
; WIN64: call
; WIN64: vaddps {{%ymm[6-7]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
; WIN64: vaddps {{%ymm[6-7]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
; WIN64: ret
; preserved ymm8-ymm15
; X64: testf16_regs
; X64: call
; X64: vaddps {{%ymm[8-9]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
; X64: vaddps {{%ymm[8-9]}}, {{%ymm[0-1]}}, {{%ymm[0-1]}}
; X64: ret
define <16 x float> @testf16_regs(<16 x float> %a, <16 x float> %b) nounwind {
%y = alloca <16 x float>, align 16
%x = fadd <16 x float> %a, %b
%1 = call intel_ocl_bicc <16 x float> @func_float16_ptr(<16 x float> %x, <16 x float>* %y)
%2 = load <16 x float>* %y, align 16
%3 = fadd <16 x float> %1, %b
%4 = fadd <16 x float> %2, %3
ret <16 x float> %4
}
; test calling conventions - prolog and epilog
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: vmovaps {{%ymm([6-9]|1[0-5])}}, {{.*(%rsp).*}} # 32-byte Spill
; WIN64: call
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; WIN64: vmovaps {{.*(%rsp).*}}, {{%ymm([6-9]|1[0-5])}} # 32-byte Reload
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp) ## 32-byte Folded Spill
; X64: call
; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
define intel_ocl_bicc <16 x float> @test_prolog_epilog(<16 x float> %a, <16 x float> %b) nounwind {
%c = call <16 x float> @func_float16(<16 x float> %a, <16 x float> %b)
ret <16 x float> %c
}
; test functions with integer parameters
; pass parameters on stack for 32-bit platform
; X32: movl {{.*}}, 4(%esp)
; X32: movl {{.*}}, (%esp)
; X32: call
; X32: addl {{.*}}, %eax
; pass parameters in registers for 64-bit platform
; X64: leal {{.*}}, %edi
; X64: movl {{.*}}, %esi
; X64: call
; X64: addl {{.*}}, %eax
define i32 @test_int(i32 %a, i32 %b) nounwind {
%c1 = add i32 %a, %b
%c2 = call intel_ocl_bicc i32 @func_int(i32 %c1, i32 %a)
%c = add i32 %c2, %b
ret i32 %c
}
; WIN64: test_float4
; WIN64-NOT: vzeroupper
; WIN64: call
; WIN64-NOT: vzeroupper
; WIN64: call
; WIN64: ret
; X64: test_float4
; X64-NOT: vzeroupper
; X64: call
; X64-NOT: vzeroupper
; X64: call
; X64: ret
; X32: test_float4
; X32: vzeroupper
; X32: call
; X32: vzeroupper
; X32: call
; X32: ret
declare <4 x float> @func_float4(<4 x float>, <4 x float>, <4 x float>)
define <8 x float> @test_float4(<8 x float> %a, <8 x float> %b, <8 x float> %c) nounwind readnone {
entry:
%0 = shufflevector <8 x float> %a, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%1 = shufflevector <8 x float> %b, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%2 = shufflevector <8 x float> %c, <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%call.i = tail call intel_ocl_bicc <4 x float> @func_float4(<4 x float> %0, <4 x float> %1, <4 x float> %2) nounwind
%3 = shufflevector <4 x float> %call.i, <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
%4 = shufflevector <8 x float> %a, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%5 = shufflevector <8 x float> %b, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%6 = shufflevector <8 x float> %c, <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%call.i2 = tail call intel_ocl_bicc <4 x float> @func_float4(<4 x float> %4, <4 x float> %5, <4 x float> %6) nounwind
%7 = shufflevector <4 x float> %call.i2, <4 x float> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
%8 = shufflevector <8 x float> %3, <8 x float> %7, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
ret <8 x float> %8
}
|
