crypto/intel/sha1edp.s

141 #define	xmov	movaps						// aligned 16-byte move
215 	xmov	W_TMP, $0						// save W_TMP in the circular buffer
228 	xmov	W_TMP, WK($0&~3)				// save quadruple W[i]+K in the stack memory, which would be used later for updating the hashes A/B/C/D/E
268 	xmov	14*16(sp), W_TMP				// load the bswapped 16-bytes from the aligned stack memory
269 	xmov	W_TMP, $0						// save W = W_TMP in the circular buffer
291 	xmov	$1, $4					// W = W12
293 	xmov	$3, W_TMP				// W_TMP = W4
301 	xmov	$1, W_TMP2				// W_TMP2 = W3 ^ W16 ^ W8 ^ W14
302 	xmov	$1, W_TMP				// W_TMP = W3 ^ W16 ^ W8 ^ W14
310 	xmov	W_TMP2, $0				// copy W[i] at location of W[i+3]
321 	xmov	W_TMP, $0				// save W = W_TMP in the W circular buffer
327 	xmov	W_TMP, WK($1&~3)		// save WK = W+K for later update of the hashes A/B/C/D/E
333 	xmov	$1, $4						// W = W12 = (w9 w10 w11 w12)
336 	xmov	$0, W_TMP					// W16 = (w13 w14 w15 w16)
341 	xmov	$3, W_TMP					// W_TMP = W4 = (w1 w2 w3 w4)
362 	xmov	$2, W_TMP					// (w1 w2 w3 w4)
369 	xmov	$2, W_TMP					// (w1 w2 w3 w4)
370 	xmov    $1, W_TMP2					// (w5 w6 w7 w8)
379     xmov    $3, W_TMP						// W32
381     xmov    W_TMP, $3						// W = W28 ^ W32;
382     xmov    $2, W_TMP						// W4
388     xmov    $3, W_TMP						// W32
390     xmov    W_TMP, $3						// W = W28 ^ W32
391     xmov    $2, W_TMP						// W4 = (w1 w2 w3 w4)
392 	xmov    $1, W_TMP2						// W8 = (w5 w6 w7 w8)
401 	xmov	W_TMP, $1					// W = W_tmp = W6 ^ W16 ^ W28 ^ W32
413     xmov    $0, W_TMP2					// W
415     xmov    W_TMP2, $0					// save (W >> 30) at W
422 	xmov	W_TMP, $0					// W = (W6 ^ W16 ^ W28 ^ W32) rol 2
424 	xmov	W_TMP, WK($1&~3)			// write W+K
427     xmov    W_TMP, $0					// W = (W6 ^ W16 ^ W28 ^ W32) rol 2
429     xmov    W_TMP, WK($1&~3)			// write WK
1294 	xmov	%xmm0, 4*16(sp)
1295 	xmov	%xmm1, 5*16(sp)
1296 	xmov	%xmm2, 6*16(sp)
1297 	xmov	%xmm3, 7*16(sp)
1298 	xmov	%xmm4, 8*16(sp)
1299 	xmov	%xmm5, 9*16(sp)
1300 	xmov	%xmm6, 10*16(sp)
1301 	xmov	%xmm7, 11*16(sp)
1303 	xmov	%xmm8, 12*16(sp)
1304 	xmov	%xmm9, 13*16(sp)
1305 	xmov	%xmm10, 14*16(sp)
1318 	xmov	0x40(K_BASE), XMM_SHUFB_BSWAP
1331     xmov    0x40(%eax), %xmm0
1332     xmov    %xmm0, XMM_SHUFB_BSWAP
1340 	xmov	4*16(sp), %xmm0
1341 	xmov	5*16(sp), %xmm1
1342 	xmov	6*16(sp), %xmm2
1343 	xmov	7*16(sp), %xmm3
1344 	xmov	8*16(sp), %xmm4
1345 	xmov	9*16(sp), %xmm5
1346 	xmov	10*16(sp), %xmm6
1347 	xmov	11*16(sp), %xmm7
1349 	xmov	12*16(sp), %xmm8
1350 	xmov	13*16(sp), %xmm9
1351 	xmov	14*16(sp), %xmm10
1391 	xmov	%xmm0, 4*16(sp)
1392 	xmov	%xmm1, 5*16(sp)
1393 	xmov	%xmm2, 6*16(sp)
1394 	xmov	%xmm3, 7*16(sp)
1395 	xmov	%xmm4, 8*16(sp)
1396 	xmov	%xmm5, 9*16(sp)
1397 	xmov	%xmm6, 10*16(sp)
1398 	xmov	%xmm7, 11*16(sp)
1400 	xmov	%xmm8, 12*16(sp)
1401 	xmov	%xmm9, 13*16(sp)
1433 	xmov	4*16(sp), %xmm0
1434 	xmov	5*16(sp), %xmm1
1435 	xmov	6*16(sp), %xmm2
1436 	xmov	7*16(sp), %xmm3
1437 	xmov	8*16(sp), %xmm4
1438 	xmov	9*16(sp), %xmm5
1439 	xmov	10*16(sp), %xmm6
1440 	xmov	11*16(sp), %xmm7
1442 	xmov	12*16(sp), %xmm8
1443 	xmov	13*16(sp), %xmm9