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
|
; RUN: llc < %s -mtriple=i386-pc-win32 -mattr=+avx | FileCheck -check-prefix=WIN32 %s
; RUN: llc < %s -mtriple=x86_64-win32 -mattr=+avx | FileCheck -check-prefix=WIN64 %s
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx | FileCheck -check-prefix=NOT_WIN %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>)
; WIN64: testf16_inp
; WIN64: vaddps {{.*}}, {{%ymm[0-1]}}
; WIN64: vaddps {{.*}}, {{%ymm[0-1]}}
; WIN64: leaq {{.*}}(%rsp), %rcx
; WIN64: call
; WIN64: ret
; WIN32: testf16_inp
; WIN32: movl %eax, (%esp)
; WIN32: vaddps {{.*}}, {{%ymm[0-1]}}
; WIN32: vaddps {{.*}}, {{%ymm[0-1]}}
; WIN32: call
; WIN32: ret
; NOT_WIN: testf16_inp
; NOT_WIN: vaddps {{.*}}, {{%ymm[0-1]}}
; NOT_WIN: vaddps {{.*}}, {{%ymm[0-1]}}
; NOT_WIN: leaq {{.*}}(%rsp), %rdi
; NOT_WIN: call
; NOT_WIN: 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]}}, %ymm0, %ymm0
; WIN64: vaddps {{%ymm[6-7]}}, %ymm1, %ymm1
; WIN64: ret
; preserved ymm8-ymm15
; NOT_WIN: testf16_regs
; NOT_WIN: call
; NOT_WIN: vaddps {{%ymm[8-9]}}, %ymm0, %ymm0
; NOT_WIN: vaddps {{%ymm[8-9]}}, %ymm1, %ymm1
; NOT_WIN: 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
; NOT_WIN: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp) ## 32-byte Spill
; NOT_WIN: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp) ## 32-byte Spill
; NOT_WIN: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp) ## 32-byte Spill
; NOT_WIN: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp) ## 32-byte Spill
; NOT_WIN: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp) ## 32-byte Spill
; NOT_WIN: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp) ## 32-byte Spill
; NOT_WIN: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp) ## 32-byte Spill
; NOT_WIN: vmovaps {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rbp) ## 32-byte Spill
; NOT_WIN: call
; NOT_WIN: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
; NOT_WIN: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
; NOT_WIN: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
; NOT_WIN: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
; NOT_WIN: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
; NOT_WIN: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
; NOT_WIN: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
; NOT_WIN: vmovaps {{.*}}(%rbp), {{%ymm([8-9]|1[0-5])}} ## 32-byte 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
}
|
