arm64/lib/xor-neon.c

16 	uint64_t *dp1 = (uint64_t *)p1;
24 		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
25 		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
26 		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
27 		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
30 		vst1q_u64(dp1 +  0, v0);
31 		vst1q_u64(dp1 +  2, v1);
32 		vst1q_u64(dp1 +  4, v2);
33 		vst1q_u64(dp1 +  6, v3);
35 		dp1 += 8;
44 	uint64_t *dp1 = (uint64_t *)p1;
53 		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
54 		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
55 		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
56 		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
65 		vst1q_u64(dp1 +  0, v0);
66 		vst1q_u64(dp1 +  2, v1);
67 		vst1q_u64(dp1 +  4, v2);
68 		vst1q_u64(dp1 +  6, v3);
70 		dp1 += 8;
81 	uint64_t *dp1 = (uint64_t *)p1;
91 		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
92 		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
93 		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
94 		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
109 		vst1q_u64(dp1 +  0, v0);
110 		vst1q_u64(dp1 +  2, v1);
111 		vst1q_u64(dp1 +  4, v2);
112 		vst1q_u64(dp1 +  6, v3);
114 		dp1 += 8;
127 	uint64_t *dp1 = (uint64_t *)p1;
138 		v0 = veorq_u64(vld1q_u64(dp1 +  0), vld1q_u64(dp2 +  0));
139 		v1 = veorq_u64(vld1q_u64(dp1 +  2), vld1q_u64(dp2 +  2));
140 		v2 = veorq_u64(vld1q_u64(dp1 +  4), vld1q_u64(dp2 +  4));
141 		v3 = veorq_u64(vld1q_u64(dp1 +  6), vld1q_u64(dp2 +  6));
162 		vst1q_u64(dp1 +  0, v0);
163 		vst1q_u64(dp1 +  2, v1);
164 		vst1q_u64(dp1 +  4, v2);
165 		vst1q_u64(dp1 +  6, v3);
167 		dp1 += 8;
199 	uint64_t *dp1 = (uint64_t *)p1;
208 		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
210 		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
212 		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
214 		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
218 		vst1q_u64(dp1 + 0, v0);
219 		vst1q_u64(dp1 + 2, v1);
220 		vst1q_u64(dp1 + 4, v2);
221 		vst1q_u64(dp1 + 6, v3);
223 		dp1 += 8;
235 	uint64_t *dp1 = (uint64_t *)p1;
245 		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
247 		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
249 		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
251 		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
261 		vst1q_u64(dp1 + 0, v0);
262 		vst1q_u64(dp1 + 2, v1);
263 		vst1q_u64(dp1 + 4, v2);
264 		vst1q_u64(dp1 + 6, v3);
266 		dp1 += 8;
280 	uint64_t *dp1 = (uint64_t *)p1;
291 		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
293 		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
295 		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
297 		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
307 		vst1q_u64(dp1 + 0, v0);
308 		vst1q_u64(dp1 + 2, v1);
309 		vst1q_u64(dp1 + 4, v2);
310 		vst1q_u64(dp1 + 6, v3);
312 		dp1 += 8;