bn/asm/rsaz-avx2.pl

150 my $aap=$r0;
247 	lea	32*18+128(%rsp), $aap		# size optimization
256 	vmovdqa		$ACC1, 32*0-128($aap)
258 	vmovdqa		$ACC2, 32*1-128($aap)
260 	vmovdqa		$ACC3, 32*2-128($aap)
262 	vmovdqa		$ACC4, 32*3-128($aap)
264 	vmovdqa		$ACC5, 32*4-128($aap)
266 	vmovdqa		$ACC6, 32*5-128($aap)
268 	vmovdqa		$ACC7, 32*6-128($aap)
270 	vmovdqa		$ACC8, 32*7-128($aap)
305 	vpmuludq	32*0-128($aap), $B1, $ACC1
307 	vpmuludq	32*1-128($aap), $B1, $ACC2
309 	vpmuludq	32*2-128($aap), $B1, $ACC3
311 	vpmuludq	32*3-128($aap), $B1, $ACC4
313 	vpmuludq	32*4-128($aap), $B1, $ACC5
315 	vpmuludq	32*5-128($aap), $B1, $ACC6
317 	vpmuludq	32*6-128($aap), $B1, $ACC7
319 	vpmuludq	32*7-128($aap), $B1, $ACC8
328 	vpmuludq	32*1-128($aap), $B2, $TEMP1
330 	vpmuludq	32*2-128($aap), $B2, $TEMP2
332 	vpmuludq	32*3-128($aap), $B2, $TEMP0
334 	vpmuludq	32*4-128($aap), $B2, $TEMP1
336 	vpmuludq	32*5-128($aap), $B2, $TEMP2
338 	vpmuludq	32*6-128($aap), $B2, $TEMP0
340 	vpmuludq	32*7-128($aap), $B2, $ACC0
349 	vpmuludq	32*2-128($aap), $B1, $TEMP0
351 	vpmuludq	32*3-128($aap), $B1, $TEMP1
353 	vpmuludq	32*4-128($aap), $B1, $TEMP2
355 	vpmuludq	32*5-128($aap), $B1, $TEMP0
357 	vpmuludq	32*6-128($aap), $B1, $TEMP1
359 	vpmuludq	32*7-128($aap), $B1, $ACC1
368 	vpmuludq	32*3-128($aap), $B2, $TEMP1
370 	vpmuludq	32*4-128($aap), $B2, $TEMP2
372 	vpmuludq	32*5-128($aap), $B2, $TEMP0
374 	vpmuludq	32*6-128($aap), $B2, $TEMP1
376 	vpmuludq	32*7-128($aap), $B2, $ACC2
385 	vpmuludq	32*4-128($aap), $B1, $TEMP1
387 	vpmuludq	32*5-128($aap), $B1, $TEMP2
389 	vpmuludq	32*6-128($aap), $B1, $TEMP0
391 	vpmuludq	32*7-128($aap), $B1, $ACC3
401 	vpmuludq	32*5-128($aap), $B2, $TEMP0
403 	vpmuludq	32*6-128($aap), $B2, $TEMP1
405 	vpmuludq	32*7-128($aap), $B2, $ACC4
414 	vpmuludq	32*6-128($aap), $B1, $TEMP1
417 	vpmuludq	32*7-128($aap), $B1, $ACC5
427 	vpmuludq	32*7-128($aap), $B2, $ACC6