Lines Matching full:16
11 declare <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %d, <16 x i8> %k)
12 declare <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %d)
13 declare <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %d, <16 x i8> %k)
14 declare <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %d)
16 define void @aesea(<16 x i8>* %a0, <16 x i8>* %b0, <16 x i8>* %c0, <16 x i8> %d, <16 x i8> %e) {
17 %d0 = load <16 x i8>, <16 x i8>* %a0
18 %a1 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 1
19 %d1 = load <16 x i8>, <16 x i8>* %a1
20 %a2 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 2
21 %d2 = load <16 x i8>, <16 x i8>* %a2
22 %a3 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 3
23 %d3 = load <16 x i8>, <16 x i8>* %a3
24 %k0 = load <16 x i8>, <16 x i8>* %b0
25 %e00 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %d0, <16 x i8> %k0)
26 %f00 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e00)
27 %e01 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %d1, <16 x i8> %k0)
28 %f01 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e01)
29 %e02 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %d2, <16 x i8> %k0)
30 %f02 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e02)
31 %e03 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %d3, <16 x i8> %k0)
32 %f03 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e03)
33 %b1 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 1
34 %k1 = load <16 x i8>, <16 x i8>* %b1
35 %e10 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f00, <16 x i8> %k1)
36 %f10 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e00)
37 %e11 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f01, <16 x i8> %k1)
38 %f11 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e01)
39 %e12 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f02, <16 x i8> %k1)
40 %f12 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e02)
41 %e13 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f03, <16 x i8> %k1)
42 %f13 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e03)
43 %b2 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 2
44 %k2 = load <16 x i8>, <16 x i8>* %b2
45 %e20 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f10, <16 x i8> %k2)
46 %f20 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e10)
47 %e21 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f11, <16 x i8> %k2)
48 %f21 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e11)
49 %e22 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f12, <16 x i8> %k2)
50 %f22 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e12)
51 %e23 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f13, <16 x i8> %k2)
52 %f23 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e13)
53 %b3 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 3
54 %k3 = load <16 x i8>, <16 x i8>* %b3
55 %e30 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f20, <16 x i8> %k3)
56 %f30 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e20)
57 %e31 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f21, <16 x i8> %k3)
58 %f31 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e21)
59 %e32 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f22, <16 x i8> %k3)
60 %f32 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e22)
61 %e33 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f23, <16 x i8> %k3)
62 %f33 = call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %e23)
63 %g0 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f30, <16 x i8> %d)
64 %h0 = xor <16 x i8> %g0, %e
65 %g1 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f31, <16 x i8> %d)
66 %h1 = xor <16 x i8> %g1, %e
67 %g2 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f32, <16 x i8> %d)
68 %h2 = xor <16 x i8> %g2, %e
69 %g3 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %f33, <16 x i8> %d)
70 %h3 = xor <16 x i8> %g3, %e
71 store <16 x i8> %h0, <16 x i8>* %c0
72 %c1 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 1
73 store <16 x i8> %h1, <16 x i8>* %c1
74 %c2 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 2
75 store <16 x i8> %h2, <16 x i8>* %c2
76 %c3 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 3
77 store <16 x i8> %h3, <16 x i8>* %c3
81 ; CHECK: aese [[VA:v[0-7].16b]], {{v[0-7].16b}}
83 ; CHECK: aese [[VB:v[0-7].16b]], {{v[0-7].16b}}
85 ; CHECK: aese [[VC:v[0-7].16b]], {{v[0-7].16b}}
87 ; CHECK: aese [[VD:v[0-7].16b]], {{v[0-7].16b}}
89 ; CHECK: aese [[VE:v[0-7].16b]], {{v[0-7].16b}}
91 ; CHECK: aese [[VF:v[0-7].16b]], {{v[0-7].16b}}
93 ; CHECK: aese [[VG:v[0-7].16b]], {{v[0-7].16b}}
95 ; CHECK: aese [[VH:v[0-7].16b]], {{v[0-7].16b}}
100 define void @aesda(<16 x i8>* %a0, <16 x i8>* %b0, <16 x i8>* %c0, <16 x i8> %d, <16 x i8> %e) {
101 %d0 = load <16 x i8>, <16 x i8>* %a0
102 %a1 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 1
103 %d1 = load <16 x i8>, <16 x i8>* %a1
104 %a2 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 2
105 %d2 = load <16 x i8>, <16 x i8>* %a2
106 %a3 = getelementptr inbounds <16 x i8>, <16 x i8>* %a0, i64 3
107 %d3 = load <16 x i8>, <16 x i8>* %a3
108 %k0 = load <16 x i8>, <16 x i8>* %b0
109 %e00 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %d0, <16 x i8> %k0)
110 %f00 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e00)
111 %e01 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %d1, <16 x i8> %k0)
112 %f01 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e01)
113 %e02 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %d2, <16 x i8> %k0)
114 %f02 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e02)
115 %e03 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %d3, <16 x i8> %k0)
116 %f03 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e03)
117 %b1 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 1
118 %k1 = load <16 x i8>, <16 x i8>* %b1
119 %e10 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f00, <16 x i8> %k1)
120 %f10 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e00)
121 %e11 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f01, <16 x i8> %k1)
122 %f11 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e01)
123 %e12 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f02, <16 x i8> %k1)
124 %f12 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e02)
125 %e13 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f03, <16 x i8> %k1)
126 %f13 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e03)
127 %b2 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 2
128 %k2 = load <16 x i8>, <16 x i8>* %b2
129 %e20 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f10, <16 x i8> %k2)
130 %f20 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e10)
131 %e21 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f11, <16 x i8> %k2)
132 %f21 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e11)
133 %e22 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f12, <16 x i8> %k2)
134 %f22 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e12)
135 %e23 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f13, <16 x i8> %k2)
136 %f23 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e13)
137 %b3 = getelementptr inbounds <16 x i8>, <16 x i8>* %b0, i64 3
138 %k3 = load <16 x i8>, <16 x i8>* %b3
139 %e30 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f20, <16 x i8> %k3)
140 %f30 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e20)
141 %e31 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f21, <16 x i8> %k3)
142 %f31 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e21)
143 %e32 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f22, <16 x i8> %k3)
144 %f32 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e22)
145 %e33 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f23, <16 x i8> %k3)
146 %f33 = call <16 x i8> @llvm.aarch64.crypto.aesimc(<16 x i8> %e23)
147 %g0 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f30, <16 x i8> %d)
148 %h0 = xor <16 x i8> %g0, %e
149 %g1 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f31, <16 x i8> %d)
150 %h1 = xor <16 x i8> %g1, %e
151 %g2 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f32, <16 x i8> %d)
152 %h2 = xor <16 x i8> %g2, %e
153 %g3 = call <16 x i8> @llvm.aarch64.crypto.aesd(<16 x i8> %f33, <16 x i8> %d)
154 %h3 = xor <16 x i8> %g3, %e
155 store <16 x i8> %h0, <16 x i8>* %c0
156 %c1 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 1
157 store <16 x i8> %h1, <16 x i8>* %c1
158 %c2 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 2
159 store <16 x i8> %h2, <16 x i8>* %c2
160 %c3 = getelementptr inbounds <16 x i8>, <16 x i8>* %c0, i64 3
161 store <16 x i8> %h3, <16 x i8>* %c3
165 ; CHECK: aesd [[VA:v[0-7].16b]], {{v[0-7].16b}}
167 ; CHECK: aesd [[VB:v[0-7].16b]], {{v[0-7].16b}}
169 ; CHECK: aesd [[VC:v[0-7].16b]], {{v[0-7].16b}}
171 ; CHECK: aesd [[VD:v[0-7].16b]], {{v[0-7].16b}}
173 ; CHECK: aesd [[VE:v[0-7].16b]], {{v[0-7].16b}}
175 ; CHECK: aesd [[VF:v[0-7].16b]], {{v[0-7].16b}}
177 ; CHECK: aesd [[VG:v[0-7].16b]], {{v[0-7].16b}}
179 ; CHECK: aesd [[VH:v[0-7].16b]], {{v[0-7].16b}}
184 define void @aes_load_store(<16 x i8> *%p1, <16 x i8> *%p2 , <16 x i8> *%p3) {
186 %x1 = alloca <16 x i8>, align 16
187 %x2 = alloca <16 x i8>, align 16
188 %x3 = alloca <16 x i8>, align 16
189 %x4 = alloca <16 x i8>, align 16
190 %x5 = alloca <16 x i8>, align 16
191 %in1 = load <16 x i8>, <16 x i8>* %p1, align 16
192 store <16 x i8> %in1, <16 x i8>* %x1, align 16
193 %aese1 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %in1, <16 x i8> %in1) #2
194 %in2 = load <16 x i8>, <16 x i8>* %p2, align 16
195 %aesmc1= call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %aese1) #2
196 %aese2 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %in1, <16 x i8> %in2) #2
197 store <16 x i8> %aesmc1, <16 x i8>* %x3, align 16
198 %in3 = load <16 x i8>, <16 x i8>* %p3, align 16
199 %aesmc2= call <16 x i8> @llvm.aarch64.crypto.aesmc(<16 x i8> %aese2) #2
200 %aese3 = call <16 x i8> @llvm.aarch64.crypto.aese(<16 x i8> %aesmc2, <16 x i8> %in3) #2
201 store <16 x i8> %aese3, <16 x i8>* %x5, align 16
205 ; CHECK: aese [[VA:v[0-7].16b]], {{v[0-7].16b}}
209 ; CHECK: aese [[VB:v[0-7].16b]], {{v[0-7].16b}}