Lines Matching +full:8 +full:a
24 // This software is available to you under a choice of one of two
49 // IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
69 .arch armv8-a+crypto
116 movi perm4.8b, #8
119 ushr perm2.2d, perm1.2d, #8
136 ext t4.8b, ad.8b, ad.8b, #1 // A1
137 ext t5.8b, ad.8b, ad.8b, #2 // A2
138 ext t6.8b, ad.8b, ad.8b, #3 // A3
140 pmull t4.8h, t4.8b, fold_consts.8b // F = A1*B
141 pmull t8.8h, ad.8b, bd1.8b // E = A*B1
142 pmull t5.8h, t5.8b, fold_consts.8b // H = A2*B
143 pmull t7.8h, ad.8b, bd2.8b // G = A*B2
144 pmull t6.8h, t6.8b, fold_consts.8b // J = A3*B
145 pmull t9.8h, ad.8b, bd3.8b // I = A*B3
146 pmull t3.8h, ad.8b, bd4.8b // K = A*B4
154 pmull2 t4.8h, t4.16b, fold_consts.16b // F = A1*B
155 pmull2 t8.8h, ad.16b, bd1.16b // E = A*B1
156 pmull2 t5.8h, t5.16b, fold_consts.16b // H = A2*B
157 pmull2 t7.8h, ad.16b, bd2.16b // G = A*B2
158 pmull2 t6.8h, t6.16b, fold_consts.16b // J = A3*B
159 pmull2 t9.8h, ad.16b, bd3.16b // I = A*B3
160 pmull2 t3.8h, ad.16b, bd4.16b // K = A*B4
171 // t4 = (L) (P0 + P1) << 8
205 pmull \rq\().8h, \ad\().8b, \bd\().8b // D = A*B
207 pmull2 \rq\().8h, \ad\().16b, \bd\().16b // D = A*B
230 CPU_LE( ext v11.16b, v11.16b, v11.16b, #8 )
231 CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
262 // For sizes less than 256 bytes, we can't fold 128 bytes at a time.
283 CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
284 CPU_LE( ext v1.16b, v1.16b, v1.16b, #8 )
285 CPU_LE( ext v2.16b, v2.16b, v2.16b, #8 )
286 CPU_LE( ext v3.16b, v3.16b, v3.16b, #8 )
287 CPU_LE( ext v4.16b, v4.16b, v4.16b, #8 )
288 CPU_LE( ext v5.16b, v5.16b, v5.16b, #8 )
289 CPU_LE( ext v6.16b, v6.16b, v6.16b, #8 )
290 CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
347 CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
361 // do this without needing a fold constant for each possible 'len',
362 // redivide the bytes into a first chunk of 'len' bytes and a second
369 CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
382 // Convert to 8-bit masks: 'len' 0x00 bytes, then '16-len' 0xff bytes.
405 // x^64. This produces a 128-bit value congruent to x^64 * M(x) and
407 ext v0.16b, v2.16b, v7.16b, #8
411 // Fold the high 32 bits into the low 96 bits. This produces a 96-bit
437 // Checksumming a buffer of length 16...255 bytes
444 CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
483 .section ".rodata", "a"
487 // G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0
489 .quad 0x0000000000006123 // x^(8*128) mod G(x)
490 .quad 0x0000000000002295 // x^(8*128+64) mod G(x)