Lines Matching refs:b
116 movi perm4.8b, #8
118 eor perm1.16b, perm1.16b, perm4.16b
128 tbl bd1.16b, {\bd\().16b}, perm1.16b
129 tbl bd2.16b, {\bd\().16b}, perm2.16b
130 tbl bd3.16b, {\bd\().16b}, perm3.16b
131 tbl bd4.16b, {\bd\().16b}, perm4.16b
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
147 b 0f
150 tbl t4.16b, {ad.16b}, perm1.16b // A1
151 tbl t5.16b, {ad.16b}, perm2.16b // A2
152 tbl t6.16b, {ad.16b}, perm3.16b // A3
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
162 0: eor t4.16b, t4.16b, t8.16b // L = E + F
163 eor t5.16b, t5.16b, t7.16b // M = G + H
164 eor t6.16b, t6.16b, t9.16b // N = I + J
173 eor t8.16b, t8.16b, t4.16b
174 and t4.16b, t4.16b, k32_48.16b
178 eor t7.16b, t7.16b, t6.16b
179 and t6.16b, t6.16b, k00_16.16b
181 eor t8.16b, t8.16b, t4.16b
182 eor t7.16b, t7.16b, t6.16b
189 ext t4.16b, t4.16b, t4.16b, #15
190 ext t5.16b, t5.16b, t5.16b, #14
191 ext t6.16b, t6.16b, t6.16b, #13
192 ext t3.16b, t3.16b, t3.16b, #12
194 eor t4.16b, t4.16b, t5.16b
195 eor t6.16b, t6.16b, t3.16b
203 mov ad.16b, \ad\().16b
205 pmull \rq\().8h, \ad\().8b, \bd\().8b // D = A*B
207 pmull2 \rq\().8h, \ad\().16b, \bd\().16b // D = A*B
212 eor \rq\().16b, \rq\().16b, t4.16b
213 eor \rq\().16b, \rq\().16b, t6.16b
224 CPU_LE( rev64 v11.16b, v11.16b )
225 CPU_LE( rev64 v12.16b, v12.16b )
230 CPU_LE( ext v11.16b, v11.16b, v11.16b, #8 )
231 CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
233 eor \reg1\().16b, \reg1\().16b, v8.16b
234 eor \reg2\().16b, \reg2\().16b, v9.16b
235 eor \reg1\().16b, \reg1\().16b, v11.16b
236 eor \reg2\().16b, \reg2\().16b, v12.16b
247 eor \dst_reg\().16b, \dst_reg\().16b, v8.16b
248 eor \dst_reg\().16b, \dst_reg\().16b, \src_reg\().16b
270 b.lt .Lless_than_256_bytes_\@
281 CPU_LE( rev64 v0.16b, v0.16b )
282 CPU_LE( rev64 v1.16b, v1.16b )
283 CPU_LE( rev64 v2.16b, v2.16b )
284 CPU_LE( rev64 v3.16b, v3.16b )
285 CPU_LE( rev64 v4.16b, v4.16b )
286 CPU_LE( rev64 v5.16b, v5.16b )
287 CPU_LE( rev64 v6.16b, v6.16b )
288 CPU_LE( rev64 v7.16b, v7.16b )
289 CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
290 CPU_LE( ext v1.16b, v1.16b, v1.16b, #8 )
291 CPU_LE( ext v2.16b, v2.16b, v2.16b, #8 )
292 CPU_LE( ext v3.16b, v3.16b, v3.16b, #8 )
293 CPU_LE( ext v4.16b, v4.16b, v4.16b, #8 )
294 CPU_LE( ext v5.16b, v5.16b, v5.16b, #8 )
295 CPU_LE( ext v6.16b, v6.16b, v6.16b, #8 )
296 CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
299 movi v8.16b, #0
301 eor v0.16b, v0.16b, v8.16b
320 b.lt .Lfold_128_bytes_loop_done_\@
337 b .Lfold_128_bytes_loop_\@
365 b.lt .Lfold_16_bytes_loop_done_\@
369 eor v7.16b, v7.16b, v8.16b
371 CPU_LE( rev64 v0.16b, v0.16b )
372 CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
373 eor v7.16b, v7.16b, v0.16b
375 b.ge .Lfold_16_bytes_loop_\@
381 b.eq .Lreduce_final_16_bytes_\@
393 CPU_LE( rev64 v0.16b, v0.16b )
394 CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
399 ld1 {v2.16b}, [x4]
400 tbl v1.16b, {v7.16b}, v2.16b
403 movi v3.16b, #0x80
404 eor v2.16b, v2.16b, v3.16b
405 tbl v3.16b, {v7.16b}, v2.16b
408 sshr v2.16b, v2.16b, #7
412 bsl v2.16b, v1.16b, v0.16b
417 eor v7.16b, v7.16b, v0.16b
418 eor v7.16b, v7.16b, v2.16b
423 movi v2.16b, #0 // init zero register
432 ext v0.16b, v2.16b, v7.16b, #8
434 eor v0.16b, v0.16b, v7.16b // + low bits * x^64
438 ext v1.16b, v0.16b, v2.16b, #12 // extract high 32 bits
441 eor v0.16b, v0.16b, v1.16b // + low bits
452 eor v0.16b, v0.16b, v1.16b // + low 16 nonzero bits
466 CPU_LE( rev64 v7.16b, v7.16b )
467 CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
470 movi v0.16b, #0
472 eor v7.16b, v7.16b, v0.16b
479 b.eq .Lreduce_final_16_bytes_\@ // len == 16
481 b.ge .Lfold_16_bytes_loop_\@ // 32 <= len <= 255
483 b .Lhandle_partial_segment_\@ // 17 <= len <= 31