Lines Matching +full:0 +full:x14
5 #define __has_feature(x) 0
28 add x29,sp,#0
33 ldr x9,[x2],#8 // bp[0]
35 ldp x7,x8,[x1],#16 // ap[0..1]
39 ldp x13,x14,[x3],#16 // np[0..1]
41 mul x6,x7,x9 // ap[0]*bp[0]
44 mul x10,x8,x9 // ap[1]*bp[0]
47 mul x15,x6,x4 // "tp[0]"*n0
50 // (*) mul x12,x13,x15 // np[0]*m1
52 mul x16,x14,x15 // np[1]*m1
64 umulh x17,x14,x15
74 ldr x14,[x3],#8
76 mul x10,x8,x9 // ap[j]*bp[0]
81 mul x16,x14,x15 // np[j]*m1
83 umulh x17,x14,x15
106 ldr x23,[sp] // tp[0]
109 mul x6,x7,x9 // ap[0]*bp[i]
112 ldp x13,x14,[x3],#16
121 // (*) mul x12,x13,x15 // np[0]*m1
123 mul x16,x14,x15 // np[1]*m1
126 umulh x17,x14,x15
138 ldr x14,[x3],#8
146 mul x16,x14,x15 // np[j]*m1
148 umulh x17,x14,x15
178 ldr x23,[sp] // tp[0]
180 ldr x14,[x3],#8 // np[0]
184 sbcs x8,x23,x14 // tp[j]-np[j]
187 ldr x14,[x3],#8
191 sbcs x8,x23,x14
195 ldr x23,[sp] // tp[0]
197 ldr x8,[x0],#8 // rp[0]
202 csel x14,x23,x8,lo // did it borrow?
206 str x14,[x0,#-16]
209 csel x14,x23,x8,lo
211 str x14,[x0,#-8]
231 add x29,sp,#0
239 ldp x6,x7,[x1,#8*0]
253 stp xzr,xzr,[x2,#8*0]
281 // a[1]a[0] (i)
282 // a[2]a[0]
283 // a[3]a[0]
284 // a[4]a[0]
285 // a[5]a[0]
286 // a[6]a[0]
287 // a[7]a[0]
310 mul x14,x7,x6 // lo(a[1..7]*a[0]) (i)
314 adds x20,x20,x14 // t[1]+lo(a[1]*a[0])
315 mul x14,x11,x6
321 umulh x17,x7,x6 // hi(a[1..7]*a[0])
322 adcs x24,x24,x14
323 umulh x14,x8,x6
328 stp x19,x20,[x2],#8*2 // t[0..1]
330 adds x21,x21,x17 // t[2]+lo(a[1]*a[0])
332 adcs x22,x22,x14
333 umulh x14,x12,x6
340 adcs x26,x26,x14
341 mul x14,x10,x7
349 adcs x24,x24,x14
350 umulh x14,x8,x7 // hi(a[2..7]*a[1])
359 adds x23,x23,x14
360 umulh x14,x12,x7
367 adcs x19,x19,x14
368 mul x14,x11,x8
376 adcs x26,x26,x14
377 umulh x14,x10,x8
386 adcs x26,x26,x14
387 mul x14,x10,x9 // lo(a[4..7]*a[3]) (iv)
395 adds x26,x26,x14
396 umulh x14,x10,x9 // hi(a[4..7]*a[3])
405 adds x19,x19,x14
406 mul x14,x11,x10 // lo(a[5..7]*a[4]) (v)
414 adds x20,x20,x14
415 umulh x14,x12,x10
423 adcs x22,x22,x14
424 umulh x14,x12,x11 // hi(a[6..7]*a[5])
433 adds x23,x23,x14
438 sub x14,x3,x5 // rewinded ap
445 ldp x6,x7,[x2,#8*0]
451 ldp x6,x7,[x1,#8*0]
466 // a[8]a[0]
467 // a[9]a[0]
468 // a[a]a[0]
469 // a[b]a[0]
470 // a[c]a[0]
471 // a[d]a[0]
472 // a[e]a[0]
473 // a[f]a[0]
489 mul x14,x6,x4
495 adds x19,x19,x14
496 mul x14,x10,x4
503 adcs x23,x23,x14
504 umulh x14,x6,x4
513 adds x19,x20,x14
514 umulh x14,x10,x4
522 adcs x23,x24,x14
533 ldp x6,x7,[x2,#8*0]
540 ldp x6,x7,[x1,#8*0]
557 ldp x6,x7,[x0,#8*0]
560 sub x14,x3,x1 // is it last iteration?
562 sub x15,x2,x14
564 cbz x14,Lsqr8x_outer_loop
566 stp x19,x20,[x2,#8*0]
567 ldp x19,x20,[x15,#8*0]
579 // Now multiply above result by 2 and add a[n-1]*a[n-1]|...|a[0]*a[0]
580 ldp x7,x9,[x14,#8*0] // recall that x14 is &a[0]
582 ldp x11,x13,[x14,#8*2]
583 add x1,x14,#8*4
584 ldp x17,x14,[sp,#8*3]
586 stp x19,x20,[x2,#8*0]
610 extr x17,x14,x17,#63
611 stp x19,x20,[x2,#8*0]
613 extr x14,x15,x14,#63
615 adcs x24,x11,x14
616 ldp x17,x14,[x2,#8*7]
628 extr x17,x14,x17,#63
632 extr x14,x15,x14,#63
633 adcs x20,x7,x14
634 ldp x17,x14,[x2,#8*3]
645 stp x19,x20,[x2,#8*0]
649 extr x17,x14,x17,#63
651 extr x14,x15,x14,#63
652 ldp x19,x20,[sp,#8*0]
653 adcs x24,x11,x14
655 ldp x6,x7,[x1,#8*0]
663 mul x28,x4,x19 // t[0]*n0
677 // (*) mul x14,x6,x28 // lo(n[0-7])*lo(t[0]*n0)
681 str x28,[x2],#8 // put aside t[0]*n0 for tail processing
683 // (*) adds xzr,x19,x14
685 mul x14,x10,x28
692 adcs x22,x23,x14
693 umulh x14,x6,x28 // hi(n[0-7])*lo(t[0]*n0)
701 adds x19,x19,x14
702 umulh x14,x10,x28
709 mul x28,x4,x19 // next t[0]*n0
710 adcs x23,x23,x14
716 ldp x14,x15,[x2,#8*0]
720 adds x19,x19,x14
722 ldp x14,x15,[x2,#8*4]
726 adcs x23,x23,x14
734 ldp x6,x7,[x1,#8*0]
742 mul x14,x6,x4
748 adds x19,x19,x14
749 mul x14,x10,x4
756 adcs x23,x23,x14
757 umulh x14,x6,x4
766 adds x19,x20,x14
767 umulh x14,x10,x4
775 adcs x23,x24,x14
783 ldp x6,x7,[x2,#8*0]
794 ldp x6,x7,[x1,#8*0]
815 adcs x14,x19,x6
817 ldp x19,x20,[x0,#8*0]
819 ldp x6,x7,[x16,#8*0] // recall that x16 is &n[0]
831 stp x14,x15,[x2,#8*0]
849 subs x14,x19,x6
856 ldp x6,x7,[x1,#8*0]
858 stp x14,x15,[x0,#8*0]
859 sbcs x14,x23,x10
868 ldp x19,x20,[x2,#8*0]
874 stp x14,x15,[x0,#8*4]
875 sbcs x14,x19,x6
884 ldp x6,x7,[x3,#8*0]
886 stp x14,x15,[x0,#8*0]
887 sbcs x14,x23,x10
892 ldp x19,x20,[x1,#8*0]
897 stp x14,x15,[x0,#8*4]
903 csel x14,x19,x6,lo
904 stp xzr,xzr,[x2,#8*0]
915 stp x14,x15,[x3,#8*0]
918 stp xzr,xzr,[x1,#8*0]
922 csel x14,x19,x6,lo
923 stp xzr,xzr,[x2,#8*0]
928 stp x14,x15,[x3,#8*0]
941 stp xzr,xzr,[sp,#8*0]
962 stp x6,x7,[x1,#8*0]
991 add x29,sp,#0
1007 ldr x24,[x2,#8*0] // b[0]
1008 ldp x6,x7,[x1,#8*0] // a[0..3]
1015 ldp x14,x15,[x3,#8*0] // n[0..3]
1019 mov x28,#0
1023 mul x10,x6,x24 // lo(a[0..3]*b[0])
1031 umulh x10,x6,x24 // hi(a[0..3]*b[0])
1033 mul x25,x19,x4 // t[0]*n0
1040 ldr x24,[x2,x28] // next b[i] (or b[0])
1042 // (*) mul x10,x14,x25 // lo(n[0..3]*t[0]*n0)
1043 str x25,[x26],#8 // put aside t[0]*n0 for tail processing
1052 umulh x10,x14,x25 // hi(n[0..3]*t[0]*n0)
1071 ldp x6,x7,[x1,#8*0] // a[4..7]
1074 ldr x25,[sp] // a[0]*n0
1075 ldp x14,x15,[x3,#8*0] // n[4..7]
1096 ldr x24,[x2,x28] // next b[i] (or b[0])
1098 mul x10,x14,x25 // lo(n[4..7]*a[0]*n0)
1106 umulh x10,x14,x25 // hi(n[4..7]*a[0]*n0)
1115 ldr x25,[sp,x28] // next t[0]*n0
1128 ldp x6,x7,[x1,#8*0]
1131 ldp x14,x15,[x3,#8*0]
1140 ldp x6,x7,[x11,#8*0] // a[0..3]
1145 stp x19,x20,[x26,#8*0] // result!!!
1146 ldp x19,x20,[sp,#8*4] // t[0..3]
1150 ldp x14,x15,[x3,#8*0] // n[0..3]
1158 mul x10,x6,x24 // lo(a[0..3]*b[4])
1166 umulh x10,x6,x24 // hi(a[0..3]*b[4])
1168 mul x25,x19,x4 // t[0]*n0
1177 // (*) mul x10,x14,x25
1178 str x25,[x26],#8 // put aside t[0]*n0 for tail processing
1180 mul x11,x15,x25 // lo(n[0..3]*t[0]*n0
1187 umulh x10,x14,x25 // hi(n[0..3]*t[0]*n0
1206 ldp x6,x7,[x1,#8*0] // a[4..7]
1215 ldr x25,[sp] // t[0]*n0
1216 ldp x14,x15,[x3,#8*0] // n[4..7]
1240 mul x10,x14,x25 // lo(n[4..7]*t[0]*n0)
1248 umulh x10,x14,x25 // hi(n[4..7]*t[0]*n0)
1256 ldr x25,[sp,x28] // next a[0]*n0
1273 ldp x6,x7,[x1,#8*0]
1281 ldp x14,x15,[x3,#8*0]
1294 stp x19,x20,[x26,#8*0] // result!!!
1296 ldp x19,x20,[sp,#8*4] // t[0..3]
1301 ldp x14,x15,[x11,#8*0] // n[0..3]
1307 ldp x6,x7,[x1,#8*0] // a[0..3]
1322 subs x10,x19,x14
1329 ldp x14,x15,[x3,#8*0]
1331 ldp x19,x20,[x26,#8*0]
1337 stp x10,x11,[x0,#8*0]
1338 sbcs x10,x19,x14
1347 ldp x6,x7,[x27,#8*0]
1349 stp x10,x11,[x0,#8*0]
1352 ldp x19,x20,[x1,#8*0]
1361 stp xzr,xzr,[x26,#8*0]
1372 stp x10,x11,[x27,#8*0]
1378 stp xzr,xzr,[x26,#8*0]
1385 stp x10,x11,[x27,#8*0]
1394 // x19-3,x0 hold result, x14-7 hold modulus
1395 subs x6,x19,x14
1398 stp xzr,xzr,[sp,#8*0]
1411 stp x6,x7,[x1,#8*0]
1427 …9,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0