• Home
  • Raw
  • Download

Lines Matching refs:xmm0

69 ##  AES-encrypt %xmm0.
72 ## %xmm0 = input
76 ## Output in %xmm0
89 pandn %xmm0, %xmm1
92 pand %xmm9, %xmm0
93 pshufb %xmm0, %xmm2
94 movdqa .Lk_ipt+16(%rip), %xmm0 # ipthi
95 pshufb %xmm1, %xmm0
97 pxor %xmm2, %xmm0
108 movdqa %xmm12, %xmm0 # 0 : sb1t
109 pshufb %xmm3, %xmm0 # 0 = sb1t
110 pxor %xmm4, %xmm0 # 0 = A
118 movdqa %xmm0, %xmm3 # 3 = A
119 pshufb %xmm1, %xmm0 # 0 = B
121 pxor %xmm2, %xmm0 # 0 = 2A+B
124 pxor %xmm0, %xmm3 # 3 = 2A+B+D
125 pshufb %xmm1, %xmm0 # 0 = 2B+C
127 pxor %xmm3, %xmm0 # 0 = 2A+3B+C+D
133 pandn %xmm0, %xmm1 # 1 = i<<4
135 pand %xmm9, %xmm0 # 0 = k
137 pshufb %xmm0, %xmm5 # 2 = a/k
138 pxor %xmm1, %xmm0 # 0 = j
143 pshufb %xmm0, %xmm4 # 4 = 1/j
147 pxor %xmm0, %xmm2 # 2 = io
156 movdqa -0x50(%r10), %xmm0 # 0 : sbot .Lk_sbo+16
159 pshufb %xmm3, %xmm0 # 0 = sb1t
161 pxor %xmm4, %xmm0 # 0 = A
162 pshufb %xmm1, %xmm0
178 pandn %xmm0, %xmm1
183 pand %xmm9, %xmm0
184 pshufb %xmm0, %xmm2
185 movdqa .Lk_dipt+16(%rip), %xmm0 # ipthi
188 pshufb %xmm1, %xmm0
192 pxor %xmm2, %xmm0
204 pxor %xmm0, %xmm4
205 movdqa -0x10(%r10),%xmm0 # 0 : sb9t
206 pshufb %xmm3, %xmm0 # 0 = sb9t
207 pxor %xmm4, %xmm0 # 0 = ch
210 pshufb %xmm5, %xmm0 # MC ch
213 pxor %xmm0, %xmm4 # 4 = ch
214 movdqa 0x10(%r10),%xmm0 # 0 : sbdt
215 pshufb %xmm3, %xmm0 # 0 = sbdt
216 pxor %xmm4, %xmm0 # 0 = ch
219 pshufb %xmm5, %xmm0 # MC ch
222 pxor %xmm0, %xmm4 # 4 = ch
223 movdqa 0x30(%r10),%xmm0 # 0 : sbbt
224 pshufb %xmm3, %xmm0 # 0 = sbbt
225 pxor %xmm4, %xmm0 # 0 = ch
227 pshufb %xmm5, %xmm0 # MC ch
230 pxor %xmm0, %xmm4 # 4 = ch
231 movdqa 0x50(%r10),%xmm0 # 0 : sbet
232 pshufb %xmm3, %xmm0 # 0 = sbet
233 pxor %xmm4, %xmm0 # 0 = ch
240 pandn %xmm0, %xmm1 # 1 = i<<4
242 pand %xmm9, %xmm0 # 0 = k
244 pshufb %xmm0, %xmm2 # 2 = a/k
245 pxor %xmm1, %xmm0 # 0 = j
250 pshufb %xmm0, %xmm4 # 4 = 1/j
254 pxor %xmm0, %xmm2 # 2 = io
258 movdqu (%r9), %xmm0
264 pxor %xmm0, %xmm4 # 4 = sb1u + k
265 movdqa 0x70(%r10), %xmm0 # 0 : sbot
267 pshufb %xmm3, %xmm0 # 0 = sb1t
268 pxor %xmm4, %xmm0 # 0 = A
269 pshufb %xmm2, %xmm0
288 movdqu (%rdi), %xmm0 # load key (unaligned)
291 movdqa %xmm0, %xmm3
294 movdqa %xmm0, %xmm7
301 movdqu %xmm0, (%rdx)
352 movdqu 8(%rdi),%xmm0 # load key part 2 (very unaligned)
354 movdqa %xmm0, %xmm6 # save short part
361 palignr \$8,%xmm6,%xmm0
384 movdqu 16(%rdi),%xmm0 # load key part 2 (unaligned)
390 movdqa %xmm0, %xmm6 # save cur_lo in xmm6
399 pshufd \$0xFF, %xmm0, %xmm0
412 ## Mangles %xmm0
413 ## when encrypting, outputs out(%xmm0) ^ 63
414 ## when decrypting, outputs unskew(%xmm0)
427 pshufb %xmm1, %xmm0 # output permute
433 pxor .Lk_s63(%rip), %xmm0
435 movdqu %xmm0, (%rdx) # save last key
438 pxor %xmm0, %xmm0
461 ## %xmm0: b+c+d b+c b a
466 pshufd \$0x80, %xmm6, %xmm0 # d c 0 0 -> c 0 0 0
467 pxor %xmm0, %xmm6 # -> c+d c 0 0
468 pshufd \$0xFE, %xmm7, %xmm0 # b a _ _ -> b b b a
469 pxor %xmm0, %xmm6 # -> b+c+d b+c b a
470 movdqa %xmm6, %xmm0
479 ## Runs one main round of the key schedule on %xmm0, %xmm7
481 ## Specifically, runs subbytes on the high dword of %xmm0
491 ## Returns results in %xmm7 = %xmm0.
504 pshufd \$0xFF, %xmm0, %xmm0
505 palignr \$1, %xmm0, %xmm0
522 pandn %xmm0, %xmm1
524 pand %xmm9, %xmm0 # 0 = k
526 pshufb %xmm0, %xmm2 # 2 = a/k
527 pxor %xmm1, %xmm0 # 0 = j
532 pshufb %xmm0, %xmm4 # 4 = 1/j
536 pxor %xmm0, %xmm2 # 2 = io
542 movdqa %xmm12, %xmm0 # 0 : sbot
543 pshufb %xmm3, %xmm0 # 0 = sb1t
544 pxor %xmm4, %xmm0 # 0 = sbox output
547 pxor %xmm7, %xmm0
548 movdqa %xmm0, %xmm7
555 ## Linear-transform %xmm0 according to tables at (%r11)
558 ## Output in %xmm0
565 pandn %xmm0, %xmm1
567 pand %xmm9, %xmm0
569 pshufb %xmm0, %xmm2
570 movdqa 16(%r11), %xmm0 # hi
571 pshufb %xmm1, %xmm0
572 pxor %xmm2, %xmm0
602 movdqa %xmm0, %xmm4 # save xmm0 for later
792 movdqu (%rdi),%xmm0
795 movdqu %xmm0,(%rsi)
835 movdqu (%rdi),%xmm0
838 movdqu %xmm0,(%rsi)
898 movdqu ($inp),%xmm0
899 pxor %xmm6,%xmm0
901 movdqa %xmm0,%xmm6
902 movdqu %xmm0,($out,$inp)
909 movdqu ($inp),%xmm0
910 movdqa %xmm0,%xmm7
912 pxor %xmm6,%xmm0
914 movdqu %xmm0,($out,$inp)
1111 mov \$20,%ecx # 10*sizeof(%xmm0)/sizeof(%rax)