Lines Matching +full:2 +full:w
13 # General Public License (GPL) Version 2, available from the file
99 INP = %rsi # 2nd arg
156 ## compute W[-16] + W[-7] 4 at a time
161 vpalignr $4, X2, X3, XTMP0 # XTMP0 = W[-7]
168 vpaddd X0, XTMP0, XTMP0 # XTMP0 = W[-7] + W[-16]
171 MY_ROR (13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
173 vpalignr $4, X0, X1, XTMP1 # XTMP1 = W[-15]
174 xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
177 MY_ROR 2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
179 add _XFER(%rsp), y2 # y2 = k + w + S1 + CH
181 add y2, h # h = h + S1 + CH + k + w
185 add h, d # d = d + h + S1 + CH + k + w
189 add y1, h # h = h + S1 + CH + k + w + S0
190 vpor XTMP2, XTMP3, XTMP3 # XTMP1 = W[-15] MY_ROR 7
192 add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
204 vpsrld $3, XTMP1, XTMP4 # XTMP4 = W[-15] >> 3
205 MY_ROR (13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
210 xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
214 add (1*4 + _XFER)(%rsp), y2 # y2 = k + w + S1 + CH
215 MY_ROR 2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
216 vpxor XTMP2, XTMP3, XTMP3 # XTMP1 = W[-15] MY_ROR 7 ^ W[-15] MY_ROR
218 add y2, h # h = h + S1 + CH + k + w
222 add h, d # d = d + h + S1 + CH + k + w
225 vpshufd $0b11111010, X3, XTMP2 # XTMP2 = W[-2] {BBAA}
227 add y1, h # h = h + S1 + CH + k + w + S0
228 vpaddd XTMP1, XTMP0, XTMP0 # XTMP0 = W[-16] + W[-7] + s0
230 add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
240 vpsrld $10, XTMP2, XTMP4 # XTMP4 = W[-2] >> 10 {BBAA}
242 vpsrlq $19, XTMP2, XTMP3 # XTMP3 = W[-2] MY_ROR 19 {xBxA}
245 vpsrlq $17, XTMP2, XTMP2 # XTMP2 = W[-2] MY_ROR 17 {xBxA}
246 MY_ROR (13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
247 xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
252 MY_ROR 2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
253 add (2*4 + _XFER)(%rsp), y2 # y2 = k + w + S1 + CH
256 add y2, h # h = h + S1 + CH + k + w
260 add h, d # d = d + h + S1 + CH + k + w
262 vpaddd XTMP4, XTMP0, XTMP0 # XTMP0 = {..., ..., W[1], W[0]}
264 add y1, h # h = h + S1 + CH + k + w + S0
266 vpshufd $0b01010000, XTMP0, XTMP2 # XTMP2 = W[-2] {DDCC}
268 add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
277 vpsrld $10, XTMP2, XTMP5 # XTMP5 = W[-2] >> 10 {DDCC}
280 vpsrlq $19, XTMP2, XTMP3 # XTMP3 = W[-2] MY_ROR 19 {xDxC}
283 MY_ROR (13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
284 vpsrlq $17, XTMP2, XTMP2 # XTMP2 = W[-2] MY_ROR 17 {xDxC}
285 xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
289 MY_ROR 2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
291 add (3*4 + _XFER)(%rsp), y2 # y2 = k + w + S1 + CH
294 add y2, h # h = h + S1 + CH + k + w
298 add h, d # d = d + h + S1 + CH + k + w
300 vpaddd XTMP0, XTMP5, X0 # X0 = {W[3], W[2], W[1], W[0]}
302 add y1, h # h = h + S1 + CH + k + w + S0
304 add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
321 MY_ROR (13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
323 xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
327 MY_ROR 2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
329 add offset(%rsp), y2 # y2 = k + w + S1 + CH
331 add y2, h # h = h + S1 + CH + k + w
334 add h, d # d = d + h + S1 + CH + k + w
337 add y1, h # h = h + S1 + CH + k + w + S0
339 add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
346 ## arg 2 : pointer to input data
370 mov 4*2(CTX), c
386 COPY_XMM_AND_BSWAP X2, 2*16(INP), BYTE_FLIP_MASK
403 vpaddd 2*16(TBL), X0, XFER
415 mov $2, SRND
421 DO_ROUND 2
426 add $2*16, TBL
429 DO_ROUND 2
440 addm (4*2)(CTX),c