Lines Matching refs:rax
98 mov %rsp,%rax
99 .cfi_def_cfa_register %rax
155 mov %rax,8(%rsp,$num,8) # tp[num+1]=%rsp
251 mov ($ap),%rax
258 mov %rax,$lo0
259 mov ($np),%rax
265 add %rax,$lo0 # discarded
266 mov 8($ap),%rax
275 add %rax,$hi1
276 mov ($ap,$j,8),%rax
286 add %rax,$hi0
287 mov ($np,$j,8),%rax
297 add %rax,$hi1
342 mov ($ap),%rax # ap[0]
350 add %rax,$lo0 # ap[0]*bp[i]+tp[0]
351 mov ($np),%rax
358 add %rax,$lo0 # discarded
359 mov 8($ap),%rax
369 add %rax,$hi1
370 mov ($ap,$j,8),%rax
380 add %rax,$hi0
381 mov ($np,$j,8),%rax
392 add %rax,$hi1
413 mov (%rsp),%rax # tp[0]
418 .Lsub: sbb ($np,$i,8),%rax
419 mov %rax,($rp,$i,8) # rp[i]=tp[i]-np[i]
420 mov 8($ap,$i,8),%rax # tp[i+1]
425 sbb \$0,%rax # handle upmost overflow bit
427 xor %rax,%rbx
435 and %rax,%rdx
445 mov \$1,%rax
475 mov %rsp,%rax
476 .cfi_def_cfa_register %rax
551 mov %rax,40(%rsp)
559 mov \$1,%rax
585 movd `($win64?56:8)`(%rax),%xmm5 # load 7th argument, index
586 lea .Linc(%rip),%rax
595 movdqa 0(%rax),%xmm0 # 00000001000000010000000000000000
596 movdqa 16(%rax),%xmm1 # 00000002000000020000000200000002
685 mov ($ap),%rax
691 mov %rax,$A[0]
692 mov ($np),%rax
699 add %rax,$A[0] # discarded
700 mov 8($ap,$num),%rax
705 add %rax,$A[1]
706 mov 8*1($np),%rax
711 add %rax,$N[1]
712 mov 16($ap,$num),%rax
725 add %rax,$A[0]
726 mov -8*2($np),%rax
732 add %rax,$N[0]
733 mov -8($ap,$j),%rax
741 add %rax,$A[1]
742 mov -8*1($np),%rax
747 add %rax,$N[1]
748 mov ($ap,$j),%rax
756 add %rax,$A[0]
757 mov 8*0($np),%rax
762 add %rax,$N[0]
763 mov 8($ap,$j),%rax
771 add %rax,$A[1]
772 mov 8*1($np),%rax
777 add %rax,$N[1]
778 mov 16($ap,$j),%rax
790 add %rax,$A[0]
791 mov -8*2($np),%rax
797 add %rax,$N[0]
798 mov -8($ap),%rax
806 add %rax,$A[1]
807 mov -8*1($np),%rax
812 add %rax,$N[1]
813 mov ($ap,$num),%rax # ap[0]
861 add %rax,$A[0] # ap[0]*bp[i]+tp[0]
862 mov ($np),%rax
872 add %rax,$A[0] # "$N[0]", discarded
873 mov 8($ap,$num),%rax
878 add %rax,$A[1]
879 mov 8*1($np),%rax
886 add %rax,$N[1]
887 mov 16($ap,$num),%rax
899 add %rax,$A[0]
900 mov -8*2($np),%rax
908 add %rax,$N[0]
909 mov -8($ap,$j),%rax
917 add %rax,$A[1]
918 mov -8*1($np),%rax
925 add %rax,$N[1]
926 mov ($ap,$j),%rax
934 add %rax,$A[0]
935 mov 8*0($np),%rax
942 add %rax,$N[0]
943 mov 8($ap,$j),%rax
951 add %rax,$A[1]
952 mov 8*1($np),%rax
959 add %rax,$N[1]
960 mov 16($ap,$j),%rax
972 add %rax,$A[0]
973 mov -8*2($np),%rax
981 add %rax,$N[0]
982 mov -8($ap),%rax
990 add %rax,$A[1]
991 mov $m1,%rax
999 add %rax,$N[1]
1000 mov ($ap,$num),%rax # ap[0]
1022 xor %rax,%rax
1026 sub $N[1],%rax # %rax=-$N[1]
1041 my @ri=("%rax",$bp,$m0,$m1);
1104 mov %rsp,%rax
1105 .cfi_def_cfa_register %rax
1189 mov %rax, 40(%rsp) # save original %rsp
1211 mov 40(%rsp),%rax
1218 mov \$1,%rax
1326 mov -24($aptr,$i),%rax # a[1]
1329 mov %rax,$a1
1332 mov %rax,$A0[0] # a[1]*a[0]
1333 mov $ai,%rax # a[2]
1338 add %rax,$A0[1]
1339 mov $ai,%rax
1347 mov %rax,$A1[0] # a[2]*a[1]+t[3]
1348 mov $ai,%rax
1353 add %rax,$A0[0] # a[3]*a[0]+a[2]*a[1]+t[3]
1354 mov $ai,%rax
1366 add %rax,$A1[1] # a[3]*a[1]+t[4]
1367 mov $ai,%rax
1372 add %rax,$A0[1] # a[4]*a[0]+a[3]*a[1]+t[4]
1373 mov $ai,%rax # a[3]
1382 add %rax,$A1[0] # a[4]*a[3]+t[5]
1383 mov $ai,%rax
1389 add %rax,$A0[0] # a[5]*a[2]+a[4]*a[3]+t[5]
1390 mov $ai,%rax
1398 add %rax,$A1[1] # a[5]*a[3]+t[6]
1399 mov $ai,%rax
1405 add %rax,$A0[1] # a[6]*a[2]+a[5]*a[3]+t[6]
1406 mov $ai,%rax # a[3]
1415 add %rax,$A1[0] # a[6]*a[5]+t[7]
1416 mov $ai,%rax
1423 add %rax,$A0[0] # a[7]*a[4]+a[6]*a[5]+t[6]
1424 mov $ai,%rax
1435 add %rax,$A1[1]
1450 mov -24($aptr,$i),%rax # a[1]
1453 mov %rax,$a1
1457 add %rax,$A0[0] # a[1]*a[0]+t[1]
1458 mov $ai,%rax # a[2]
1464 add %rax,$A0[1]
1465 mov $ai,%rax
1476 add %rax,$A1[0] # a[2]*a[1]+t[3]
1477 mov $ai,%rax
1484 add %rax,$A0[0] # a[3]*a[0]+a[2]*a[1]+t[3]
1485 mov $ai,%rax
1499 add %rax,$A1[1] # a[3]*a[1]+t[4]
1500 mov $ai,%rax
1508 add %rax,$A0[1] # a[4]*a[0]+a[3]*a[1]+t[4]
1509 mov $ai,%rax # a[3]
1517 add %rax,$A1[0] # a[4]*a[3]+t[5]
1519 mov $ai,%rax
1527 add %rax,$A0[0] # a[5]*a[2]+a[4]*a[3]+t[5]
1528 mov $ai,%rax
1540 add %rax,$A1[1]
1555 mov -24($aptr),%rax # a[1]
1558 mov %rax,$a1
1561 add %rax,$A0[0] # a[1]*a[0]+t[1], preloaded t[1]
1562 mov $ai,%rax # a[2]
1567 add %rax,$A0[1]
1568 mov $ai,%rax
1577 add %rax,$A1[0] # a[2]*a[1]+t[3], preloaded t[3]
1578 mov $ai,%rax
1584 add %rax,$A0[0] # a[3]*a[0]+a[2]*a[1]+t[3]
1585 mov $ai,%rax
1593 add %rax,$A1[1]
1594 mov -16($aptr),%rax # a[2]
1614 add $A1[0],%rax # t[5]
1616 mov %rax,8($tptr) # t[5]
1620 mov -16($aptr,$i),%rax # a[0]
1632 mul %rax # a[i]*a[i]
1635 adc %rax,$S[0]
1636 mov -8($aptr,$i),%rax # a[i+1] # prefetch
1649 mul %rax # a[i]*a[i]
1652 adc %rax,$S[2]
1653 mov 0($aptr,$i),%rax # a[i+1] # prefetch
1671 mul %rax # a[i]*a[i]
1674 adc %rax,$S[0]
1675 mov -8($aptr,$i),%rax # a[i+1] # prefetch
1688 mul %rax # a[i]*a[i]
1691 adc %rax,$S[2]
1692 mov 0($aptr,$i),%rax # a[i+1] # prefetch
1705 mul %rax # a[i]*a[i]
1708 adc %rax,$S[0]
1709 mov 8($aptr,$i),%rax # a[i+1] # prefetch
1722 mul %rax # a[i]*a[i]
1725 adc %rax,$S[2]
1726 mov 16($aptr,$i),%rax # a[i+1] # prefetch
1743 mul %rax # a[i]*a[i]
1746 adc %rax,$S[0]
1747 mov -8($aptr),%rax # a[i+1] # prefetch
1758 mul %rax # a[i]*a[i]
1760 adc %rax,$S[2]
1778 xor %rax,%rax
1799 mov %rax,(%rdx) # store top-most carry bit
1805 mov 8*0($nptr),%rax # n[0]
1812 mov 8*1($nptr),%rax # n[1]
1818 add %rax,%r9
1819 mov 8*2($nptr),%rax
1827 add %rax,%r10
1828 mov 8*3($nptr),%rax
1836 add %rax,%r11
1837 mov 8*4($nptr),%rax
1845 add %rax,%r12
1846 mov 8*5($nptr),%rax
1853 add %rax,%r13
1854 mov 8*6($nptr),%rax
1861 add %rax,%r14
1862 mov 8*7($nptr),%rax
1870 add %rax,%r15
1871 mov 8*0($nptr),%rax # n[0]
1881 xor %rax,%rax
1899 mov 8*0($nptr),%rax
1905 add %rax,%r8
1906 mov 8*1($nptr),%rax
1912 add %rax,%r9
1913 mov 8*2($nptr),%rax
1921 add %rax,%r10
1922 mov 8*3($nptr),%rax
1929 add %rax,%r11
1930 mov 8*4($nptr),%rax
1937 add %rax,%r12
1938 mov 8*5($nptr),%rax
1945 add %rax,%r13
1946 mov 8*6($nptr),%rax
1953 add %rax,%r14
1954 mov 8*7($nptr),%rax
1962 add %rax,%r15
1965 mov 8*0($nptr),%rax # pull n[0]
1979 mov 8*0($nptr),%rax # pull n[0]
1995 xor %rax,%rax
2004 adc \$0,%rax
2016 adc \$0,%rax # top-most carry
2054 neg %rax
2076 and %rax,%r12
2077 and %rax,%r13
2078 and %rax,%r14
2079 and %rax,%r15
2123 mov %rsp,%rax
2124 .cfi_def_cfa_register %rax
2200 mov %rax, 40(%rsp) # save original %rsp
2204 lea 48(%rsp),%rax
2213 movdqa %xmm0,(%rax,$num)
2215 movdqa %xmm0,16(%rax,$num)
2217 movdqa %xmm1,(%rax)
2218 movdqa %xmm0,32(%rax,$num)
2219 movdqa %xmm2,16(%rax)
2220 movdqa %xmm0,48(%rax,$num)
2221 movdqa %xmm3,32(%rax)
2222 movdqa %xmm4,48(%rax)
2223 lea 64(%rax),%rax
2239 lea (%rax,$num),$rptr
2244 lea 48(%rsp),%rax
2255 lea 48(%rsp),%rax
2262 movdqa %xmm0,16*0(%rax)
2263 movdqa %xmm0,16*1(%rax)
2264 movdqa %xmm0,16*2(%rax)
2265 movdqa %xmm0,16*3(%rax)
2266 lea 16*4(%rax),%rax
2270 mov \$1,%rax
2301 mov %rsp,%rax
2302 .cfi_def_cfa_register %rax
2380 mov %rax,40(%rsp) # save original %rsp
2387 mov \$1,%rax
2419 movd `($win64?56:8)`(%rax),%xmm5 # load 7th argument
2421 lea .Linc(%rip),%rax
2427 ("%rsi","%rdi","%rcx","%rbx","%r8","%r9","%rbp","%rax");
2432 movdqa 0(%rax),%xmm0 # 00000001000000010000000000000000
2433 movdqa 16(%rax),%xmm1 # 00000002000000020000000200000002
2520 mulx 0*8($aptr),$mi,%rax # a[0]*b[0]
2522 add %rax,%r11
2523 mulx 2*8($aptr),%rax,%r13 # ...
2524 adc %rax,%r12
2526 mulx 3*8($aptr),%rax,%r14
2536 adcx %rax,%r13
2539 mulx 0*8($nptr),%rax,%r10
2540 adcx %rax,%r15 # discarded
2542 mulx 1*8($nptr),%rax,%r11
2543 adcx %rax,%r10
2545 mulx 2*8($nptr),%rax,%r12
2548 adcx %rax,%r11
2550 mulx 3*8($nptr),%rax,%r15
2553 adcx %rax,%r12
2562 mulx 0*8($aptr),%r10,%rax # a[4]*b[0]
2565 adcx %rax,%r11
2566 mulx 2*8($aptr),%r12,%rax # ...
2571 adcx %rax,%r13
2577 mulx 0*8($nptr),%rax,%r15
2578 adcx %rax,%r10
2580 mulx 1*8($nptr),%rax,%r15
2581 adcx %rax,%r11
2583 mulx 2*8($nptr),%rax,%r15
2585 adcx %rax,%r12
2588 mulx 3*8($nptr),%rax,%r15
2591 adcx %rax,%r13
2665 mulx 0*8($nptr),%rax,%r10
2666 adcx %rax,%r15 # discarded
2668 mulx 1*8($nptr),%rax,%r11
2669 adcx %rax,%r10
2671 mulx 2*8($nptr),%rax,%r12
2672 adcx %rax,%r11
2674 mulx 3*8($nptr),%rax,%r15
2678 adcx %rax,%r12
2687 mulx 0*8($aptr),%r10,%rax # a[4]*b[i]
2692 adox %rax,%r11
2693 mulx 2*8($aptr),%r12,%rax # ...
2699 adox %rax,%r13
2707 mulx 0*8($nptr),%rax,%r15
2708 adcx %rax,%r10
2710 mulx 1*8($nptr),%rax,%r15
2711 adcx %rax,%r11
2713 mulx 2*8($nptr),%rax,%r15
2715 adcx %rax,%r12
2718 mulx 3*8($nptr),%rax,%r15
2722 adcx %rax,%r13
2754 sub %r8,%rax # %rax=-%r8
2786 mov %rsp,%rax
2787 .cfi_def_cfa_register %rax
2871 mov %rax, 40(%rsp) # save original %rsp
2890 mov 40(%rsp),%rax
2896 mov \$1,%rax
3006 mulx 1*8($aptr),%r8,%rax # a[1]*a[0]
3008 adox %rax,%r10
3009 mulx 2*8($aptr),%r9,%rax # a[2]*a[0]
3011 adox %rax,%r11
3012 .byte 0xc4,0xe2,0xab,0xf6,0x86,0x18,0x00,0x00,0x00 # mulx 3*8($aptr),%r10,%rax # ...
3014 adox %rax,%r12
3015 .byte 0xc4,0xe2,0xa3,0xf6,0x86,0x20,0x00,0x00,0x00 # mulx 4*8($aptr),%r11,%rax
3017 adox %rax,%r13
3018 mulx 5*8($aptr),%r12,%rax
3020 adox %rax,%r14
3021 mulx 6*8($aptr),%r13,%rax
3023 adox %r15,%rax
3026 adcx %rax,%r14
3036 mulx 3*8($aptr),%r9,%rax # a[3]*a[1]
3041 adox %rax,%r10
3042 .byte 0xc4,0xe2,0xa3,0xf6,0x86,0x28,0x00,0x00,0x00 # mulx 5*8($aptr),%r11,%rax
3050 adcx %rax,%r12
3060 mulx 4*8($aptr),%r9,%rax # a[4]*a[2]
3065 adox %rax,%r10
3066 .byte 0xc4,0xe2,0xa3,0xf6,0x86,0x30,0x00,0x00,0x00 # mulx 6*8($aptr),%r11,%rax
3073 adox %rax,%r12
3077 mulx 4*8($aptr),%r8,%rax # a[4]*a[3]
3083 adox %rax,%r9
3084 mulx 6*8($aptr),%r10,%rax # ...
3091 adox %rax,%r11
3100 mulx %r14,%r9,%rax # a[5]*a[4]
3104 adox %rax,%r10
3106 mulx %r8,%r11,%rax # a[7]*a[4]
3110 #adox $zero,%rax # of=0
3111 adcx $zero,%rax # cf=0
3119 adcx %rax,%r12
3143 sbb %rax,%rax # mov %cf,$carry
3146 mov %rax,16+8(%rsp) # offload $carry
3156 mulx 0*8($aaptr),%rax,%r8 # a[8]*a[i]
3157 adcx %rax,%rbx # +=t[8]
3160 mulx 1*8($aaptr),%rax,%r9 # ...
3161 adcx %rax,%r8
3164 mulx 2*8($aaptr),%rax,%r10
3165 adcx %rax,%r9
3168 mulx 3*8($aaptr),%rax,%r11
3169 adcx %rax,%r10
3172 .byte 0xc4,0x62,0xfb,0xf6,0xa5,0x20,0x00,0x00,0x00 # mulx 4*8($aaptr),%rax,%r12
3173 adcx %rax,%r11
3176 mulx 5*8($aaptr),%rax,%r13
3177 adcx %rax,%r12
3180 mulx 6*8($aaptr),%rax,%r14
3183 adcx %rax,%r13
3186 .byte 0xc4,0x62,0xfb,0xf6,0xbd,0x38,0x00,0x00,0x00 # mulx 7*8($aaptr),%rax,%r15
3188 adcx %rax,%r14
3214 sbb %rax,%rax # mov %cf,%rax
3216 mov %rax,16+8(%rsp) # offload carry
3280 mulx %rdx,%rax,%rbx
3282 adcx $A0[0],%rax
3288 mov %rax,0($tptr)
3291 mulx %rdx,%rax,%rbx
3293 adcx $A1[0],%rax
3299 mov %rax,16($tptr)
3302 mulx %rdx,%rax,%rbx
3304 adcx $A0[0],%rax
3311 mov %rax,32($tptr)
3314 mulx %rdx,%rax,%rbx
3316 adcx $A1[0],%rax
3323 mov %rax,48($tptr)
3332 mov %rax,48($tptr)
3371 mov %rax,24+8(%rsp) # store top-most carry bit
3381 mulx 8*0($nptr),%rax,%r8 # n[0]
3382 adcx %rbx,%rax # discarded
3398 mov %rdx,%rax
3404 mov %rax,%rdx
3405 mov %rax,64+48+8(%rsp,%rcx,8) # put aside n0*a[i]
3407 mulx 8*5($nptr),%rax,%r13
3408 adcx %rax,%r12
3411 mulx 8*6($nptr),%rax,%r14
3412 adcx %rax,%r13
3415 mulx 8*7($nptr),%rax,%r15
3417 adcx %rax,%r14
3425 mov $carry,%rax # xor %rax,%rax
3441 sbb %rax,%rax # top carry
3444 mov %rax,16+8(%rsp)
3450 mulx 8*0($nptr),%rax,%r8
3451 adcx %rax,%rbx
3454 mulx 8*1($nptr),%rax,%r9
3455 adcx %rax,%r8
3458 mulx 8*2($nptr),%rax,%r10
3459 adcx %rax,%r9
3462 mulx 8*3($nptr),%rax,%r11
3463 adcx %rax,%r10
3466 .byte 0xc4,0x62,0xfb,0xf6,0xa5,0x20,0x00,0x00,0x00 # mulx 8*4($nptr),%rax,%r12
3467 adcx %rax,%r11
3470 mulx 8*5($nptr),%rax,%r13
3471 adcx %rax,%r12
3474 mulx 8*6($nptr),%rax,%r14
3475 adcx %rax,%r13
3478 mulx 8*7($nptr),%rax,%r15
3480 adcx %rax,%r14
3504 sbb %rax,%rax
3508 mov %rax,16+8(%rsp)
3513 xor %rax,%rax
3522 adc \$0,%rax
3537 adc \$0,%rax # top-most carry
3572 neg %rax
3591 andn %rax,%r12,%r12
3593 andn %rax,%r13,%r13
3594 andn %rax,%r14,%r14
3595 andn %rax,%r15,%r15
3659 mov ($inp),%rax
3661 mov %rax,($tbl)
3679 lea .Linc(%rip),%rax
3683 movdqa 0(%rax),%xmm0 # 00000001000000010000000000000000
3684 movdqa 16(%rax),%xmm1 # 00000002000000020000000200000002
3686 lea 128(%rsp),%rax # size optimization
3701 movdqa %xmm3,`16*($i-1)-128`(%rax)
3708 movdqa %xmm0,`16*($i+0)-128`(%rax)
3713 movdqa %xmm1,`16*($i+1)-128`(%rax)
3718 movdqa %xmm2,`16*($i+2)-128`(%rax)
3723 movdqa %xmm3,`16*($i-1)-128`(%rax)
3736 pand `16*($i+0)-128`(%rax),%xmm0
3738 pand `16*($i+1)-128`(%rax),%xmm1
3740 pand `16*($i+2)-128`(%rax),%xmm2
3742 pand `16*($i+3)-128`(%rax),%xmm3
3796 mov 120($context),%rax # pull context->Rax
3812 mov 152($context),%rax # pull context->Rsp
3824 mov 8(%rax,%r10,8),%rax # pull saved stack pointer
3829 mov 40(%rax),%rax # pull saved stack pointer
3831 mov -8(%rax),%rbx
3832 mov -16(%rax),%rbp
3833 mov -24(%rax),%r12
3834 mov -32(%rax),%r13
3835 mov -40(%rax),%r14
3836 mov -48(%rax),%r15
3845 mov 8(%rax),%rdi
3846 mov 16(%rax),%rsi
3847 mov %rax,152($context) # restore context->Rsp