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
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -O3 -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=+sha < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-unknown"
; Stack reload folding tests.
;
; By including a nop call with sideeffects we can force a partial register spill of the
; relevant registers and check that the reload is correctly folded into the instruction.
define <4 x i32> @stack_fold_sha1msg1(<4 x i32> %a0, <4 x i32> %a1) {
; CHECK-LABEL: stack_fold_sha1msg1:
; CHECK: # %bb.0:
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: #APP
; CHECK-NEXT: nop
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: sha1msg1 {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: retq
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
%2 = tail call <4 x i32> @llvm.x86.sha1msg1(<4 x i32> %a0, <4 x i32> %a1)
ret <4 x i32> %2
}
declare <4 x i32> @llvm.x86.sha1msg1(<4 x i32>, <4 x i32>) nounwind readnone
define <4 x i32> @stack_fold_sha1msg2(<4 x i32> %a0, <4 x i32> %a1) {
; CHECK-LABEL: stack_fold_sha1msg2:
; CHECK: # %bb.0:
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: #APP
; CHECK-NEXT: nop
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: sha1msg2 {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: retq
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
%2 = tail call <4 x i32> @llvm.x86.sha1msg2(<4 x i32> %a0, <4 x i32> %a1)
ret <4 x i32> %2
}
declare <4 x i32> @llvm.x86.sha1msg2(<4 x i32>, <4 x i32>) nounwind readnone
define <4 x i32> @stack_fold_sha1nexte(<4 x i32> %a0, <4 x i32> %a1) {
; CHECK-LABEL: stack_fold_sha1nexte:
; CHECK: # %bb.0:
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: #APP
; CHECK-NEXT: nop
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: sha1nexte {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: retq
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
%2 = tail call <4 x i32> @llvm.x86.sha1nexte(<4 x i32> %a0, <4 x i32> %a1)
ret <4 x i32> %2
}
declare <4 x i32> @llvm.x86.sha1nexte(<4 x i32>, <4 x i32>) nounwind readnone
define <4 x i32> @stack_fold_sha1rnds4(<4 x i32> %a0, <4 x i32> %a1) {
; CHECK-LABEL: stack_fold_sha1rnds4:
; CHECK: # %bb.0:
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: #APP
; CHECK-NEXT: nop
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: sha1rnds4 $3, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: retq
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
%2 = tail call <4 x i32> @llvm.x86.sha1rnds4(<4 x i32> %a0, <4 x i32> %a1, i8 3)
ret <4 x i32> %2
}
declare <4 x i32> @llvm.x86.sha1rnds4(<4 x i32>, <4 x i32>, i8) nounwind readnone
define <4 x i32> @stack_fold_sha256msg1(<4 x i32> %a0, <4 x i32> %a1) {
; CHECK-LABEL: stack_fold_sha256msg1:
; CHECK: # %bb.0:
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: #APP
; CHECK-NEXT: nop
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: sha256msg1 {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: retq
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
%2 = tail call <4 x i32> @llvm.x86.sha256msg1(<4 x i32> %a0, <4 x i32> %a1)
ret <4 x i32> %2
}
declare <4 x i32> @llvm.x86.sha256msg1(<4 x i32>, <4 x i32>) nounwind readnone
define <4 x i32> @stack_fold_sha256msg2(<4 x i32> %a0, <4 x i32> %a1) {
; CHECK-LABEL: stack_fold_sha256msg2:
; CHECK: # %bb.0:
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: #APP
; CHECK-NEXT: nop
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: sha256msg2 {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: retq
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
%2 = tail call <4 x i32> @llvm.x86.sha256msg2(<4 x i32> %a0, <4 x i32> %a1)
ret <4 x i32> %2
}
declare <4 x i32> @llvm.x86.sha256msg2(<4 x i32>, <4 x i32>) nounwind readnone
define <4 x i32> @stack_fold_sha256rnds2(<4 x i32> %a0, <4 x i32> %a1, <4 x i32> %a2) {
; CHECK-LABEL: stack_fold_sha256rnds2:
; CHECK: # %bb.0:
; CHECK-NEXT: movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: #APP
; CHECK-NEXT: nop
; CHECK-NEXT: #NO_APP
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
; CHECK-NEXT: sha256rnds2 %xmm0, {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retq
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
%2 = tail call <4 x i32> @llvm.x86.sha256rnds2(<4 x i32> %a0, <4 x i32> %a1, <4 x i32> %a2)
ret <4 x i32> %2
}
declare <4 x i32> @llvm.x86.sha256rnds2(<4 x i32>, <4 x i32>, <4 x i32>) nounwind readnone
|