Lines Matching +full:2 +full:e
13 # General Public License (GPL) Version 2, available from the file
48 # This code schedules 2 blocks at a time, with 4 lanes per block
93 INP = %rsi # 2nd arg
97 e = %edx # clobbers NUM_BLKS define
115 _XFER_SIZE = 2*64*4 # 2 blocks, 64 rounds, 4 bytes/round
145 f = e
146 e = d define
157 rorx $25, e, y0 # y0 = e >> 25 # S1A
158 rorx $11, e, y1 # y1 = e >> 11 # S1B
166 xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
168 vpaddd X0, XTMP0, XTMP0 # XTMP0 = W[-7] + W[-16]# y1 = (e >> 6)# S1
169 rorx $6, e, y1 # y1 = (e >> 6) # S1
171 and e, y2 # y2 = (f^g)&e # CH
172 xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
179 rorx $2, a, T1 # T1 = (a >> 2) # S0
181 xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
183 xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
205 rorx $25, e, y0 # y0 = e >> 25 # S1A
206 rorx $11, e, y1 # y1 = e >> 11 # S1B
215 xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
219 rorx $6, e, y1 # y1 = (e >> 6) # S1
220 xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
222 and e, y2 # y2 = (f^g)&e # CH
230 rorx $2, a, T1 # T1 = (a >> 2) # S0
231 xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
234 xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
240 vpshufd $0b11111010, X3, XTMP2 # XTMP2 = W[-2] {BBAA}
249 vpsrld $10, XTMP2, XTMP4 # XTMP4 = W[-2] >> 10 {BBAA}
254 ################################### RND N + 2 ############################
257 rorx $25, e, y0 # y0 = e >> 25 # S1A
258 offset = \disp + 2*4
261 vpsrlq $19, XTMP2, XTMP3 # XTMP3 = W[-2] ror 19 {xBxA}
262 rorx $11, e, y1 # y1 = e >> 11 # S1B
268 xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
269 vpsrlq $17, XTMP2, XTMP2 # XTMP2 = W[-2] ror 17 {xBxA}
270 and e, y2 # y2 = (f^g)&e # CH
272 rorx $6, e, y1 # y1 = (e >> 6) # S1
277 xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
280 xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
284 rorx $2, a ,T1 # T1 = (a >> 2) # S0
287 xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
291 vpshufd $0b01010000, XTMP0, XTMP2 # XTMP2 = W[-2] {DDCC}
306 rorx $25, e, y0 # y0 = e >> 25 # S1A
307 rorx $11, e, y1 # y1 = e >> 11 # S1B
313 vpsrld $10, XTMP2, XTMP5 # XTMP5 = W[-2] >> 10 {DDCC}
316 xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
320 vpsrlq $19, XTMP2, XTMP3 # XTMP3 = W[-2] ror 19 {xDxC}
321 rorx $6, e, y1 # y1 = (e >> 6) # S1
322 and e, y2 # y2 = (f^g)&e # CH
326 vpsrlq $17, XTMP2, XTMP2 # XTMP2 = W[-2] ror 17 {xDxC}
327 xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
328 xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
338 rorx $2, a, T1 # T1 = (a >> 2) # S0
341 vpaddd XTMP0, XTMP5, X0 # X0 = {W[3], W[2], W[1], W[0]}
342 xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
359 rorx $25, e, y0 # y0 = e >> 25 # S1A
360 rorx $11, e, y1 # y1 = e >> 11 # S1B
363 xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
364 rorx $6, e, y1 # y1 = (e >> 6) # S1
365 and e, y2 # y2 = (f^g)&e # CH
367 xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
369 xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
374 rorx $2, a, T1 # T1 = (a >> 2) # S0
378 xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
396 rorx $25, e, y0 # y0 = e >> 25 # S1A
397 rorx $11, e, y1 # y1 = e >> 11 # S1B
400 xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
401 rorx $6, e, y1 # y1 = (e >> 6) # S1
402 and e, y2 # y2 = (f^g)&e # CH
405 xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
407 xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
412 rorx $2, a, T1 # T1 = (a >> 2) # S0
417 xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
432 ################################### RND N + 2 ##############################
436 rorx $25, e, y0 # y0 = e >> 25 # S1A
437 rorx $11, e, y1 # y1 = e >> 11 # S1B
440 xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
441 rorx $6, e, y1 # y1 = (e >> 6) # S1
442 and e, y2 # y2 = (f^g)&e # CH
445 xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
447 xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
452 rorx $2, a, T1 # T1 = (a >> 2) # S0
453 offset = 4*2 + \disp
457 xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
476 rorx $25, e, y0 # y0 = e >> 25 # S1A
477 rorx $11, e, y1 # y1 = e >> 11 # S1B
480 xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
481 rorx $6, e, y1 # y1 = (e >> 6) # S1
482 and e, y2 # y2 = (f^g)&e # CH
485 xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
487 xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
492 rorx $2, a, T1 # T1 = (a >> 2) # S0
497 xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
522 ## arg 2 : pointer to input data
551 mov 4*2(CTX), c
553 mov 4*4(CTX), e
568 VMOVDQ 2*32(INP),XTMP2
600 vpaddd K256+2*32(SRND), X0, XFER
601 vmovdqa XFER, 2*32+_XFER(%rsp, SRND)
602 FOUR_ROUNDS_AND_SCHED _XFER + 2*32
621 add $2*32, SRND
634 addm (4*2)(CTX),c
636 addm (4*4)(CTX),e
650 add $2*32, SRND
660 addm (4*2)(CTX),c
662 addm (4*4)(CTX),e
674 VMOVDQ 2*16(INP),XWORD2
689 mov (4*2)(CTX),c
691 mov (4*4)(CTX),e