x86/crypto/sha512-avx2-asm.S

166 	# Extract w[t-7]
167 	MY_VPALIGNR	YTMP0, Y_3, Y_2, 8		# YTMP0 = W[-7]
168 	# Calculate w[t-16] + w[t-7]
169 	vpaddq		Y_0, YTMP0, YTMP0		# YTMP0 = W[-7] + W[-16]
179 	# Calculate w[t-15] shr 7
180 	vpsrlq		$7, YTMP1, YTMP4		# YTMP4 = W[-15] >> 7
185 	add	frame_XFER(%rsp),h		# h = k + w + h         # --
197 	add	h, d		# d = k + w + h + d                     # --
210 	add	y1, h		# h = k + w + h + S0                    # --
212 	add	y2, d		# d = k + w + h + d + S1 + CH = d + t1  # --
214 	add	y2, h		# h = k + w + h + S0 + S1 + CH = t1 + S0# --
226 	vpxor		YTMP4, YTMP3, YTMP3		# YTMP3 = W[-15] ror 1 ^ W[-15] >> 7
230 	# Add three components, w[t-16], w[t-7] and sigma0
231 	vpaddq		YTMP1, YTMP0, YTMP0		# YTMP0 = W[-16] + W[-7] + s0
233 	vperm2f128	$0x0, YTMP0, YTMP0, Y_0		# Y_0 = W[-16] + W[-7] + s0 {BABA}
235 	vpand		MASK_YMM_LO(%rip), YTMP0, YTMP0	# YTMP0 = W[-16] + W[-7] + s0 {DC00}
247 	add	1*8+frame_XFER(%rsp), h		# h = k + w + h         # --
261 	add	h, d		# d = k + w + h + d                     # --
275 	add	y1, h		# h = k + w + h + S0                    # --
277 	add	y2, d		# d = k + w + h + d + S1 + CH = d + t1  # --
278 	add	y2, h		# h = k + w + h + S0 + S1 + CH = t1 + S0# --
304 	add	2*8+frame_XFER(%rsp), h		# h = k + w + h         # --
316 	add	h, d		# d = k + w + h + d                     # --
332 	add	y1, h		# h = k + w + h + S0                    # --
333 	add	y2, d		# d = k + w + h + d + S1 + CH = d + t1  # --
334 	add	y2, h		# h = k + w + h + S0 + S1 + CH = t1 + S0# --
352 	# Add the sigma0 + w[t-7] + w[t-16] for w[18] and w[19]
362 	add	3*8+frame_XFER(%rsp), h		# h = k + w + h         # --
374 	add	h, d		# d = k + w + h + d                     # --
384 	add	y2, d		# d = k + w + h + d + S1 + CH = d + t1  # --
393 	add	y1, h		# h = k + w + h + S0                    # --
394 	add	y2, h		# h = k + w + h + S0 + S1 + CH = t1 + S0# --
423 	add	frame_XFER(%rsp), h		# h = k + w + h         # --
432 	add	h, d		# d = k + w + h + d                     # --
434 	add	y1, h		# h = k + w + h + S0                    # --
436 	add	y2, d		# d = k + w + h + d + S1 + CH = d + t1  # --
442 	add	y2, old_h	# h = k + w + h + S0 + S1 + CH = t1 + S0# --
461 	add	8*1+frame_XFER(%rsp), h		# h = k + w + h         # --
470 	add	h, d		# d = k + w + h + d                     # --
472 	add	y1, h		# h = k + w + h + S0                    # --
474 	add	y2, d		# d = k + w + h + d + S1 + CH = d + t1  # --
480 	add	y2, old_h	# h = k + w + h + S0 + S1 + CH = t1 + S0# --
499 	add	8*2+frame_XFER(%rsp), h		# h = k + w + h         # --
508 	add	h, d		# d = k + w + h + d                     # --
510 	add	y1, h		# h = k + w + h + S0                    # --
512 	add	y2, d		# d = k + w + h + d + S1 + CH = d + t1  # --
518 	add	y2, old_h	# h = k + w + h + S0 + S1 + CH = t1 + S0# --
537 	add	8*3+frame_XFER(%rsp), h		# h = k + w + h         # --
547 	add	h, d		# d = k + w + h + d                     # --
549 	add	y1, h		# h = k + w + h + S0                    # --
551 	add	y2, d		# d = k + w + h + d + S1 + CH = d + t1  # --
553 	add	y2, h		# h = k + w + h + S0 + S1 + CH = t1 + S0# --
583 	shl	$7, NUM_BLKS	# convert to bytes
596 	mov	8*7(CTX1), h
663 	addm	8*7(CTX2), h
696 # K[t] used in SHA512 hashing