Lines Matching +full:0 +full:x21
5 #define __has_feature(x) 0
28 add x29,sp,#0
30 stp x21,x22,[sp,#32]
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]
42 sub x21,x5,#16 // j=num-2
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
66 cbz x21,L1st_skip
71 sub x21,x21,#8 // j--
76 mul x10,x8,x9 // ap[j]*bp[0]
85 cbnz x21,L1st
106 ldr x23,[sp] // tp[0]
109 mul x6,x7,x9 // ap[0]*bp[i]
110 sub x21,x5,#16 // j=num-2
121 // (*) mul x12,x13,x15 // np[0]*m1
127 cbz x21,Linner_skip
134 sub x21,x21,#8 // j--
150 cbnz x21,Linner
178 ldr x23,[sp] // tp[0]
180 ldr x14,[x3],#8 // np[0]
181 subs x21,x5,#8 // j=num-1 and clear borrow
186 sub x21,x21,#8 // j--
189 cbnz x21,Lsub
195 ldr x23,[sp] // tp[0]
197 ldr x8,[x0],#8 // rp[0]
215 ldp x21,x22,[x29,#32]
231 add x29,sp,#0
233 stp x21,x22,[sp,#32]
239 ldp x6,x7,[x1,#8*0]
253 stp xzr,xzr,[x2,#8*0]
269 mov x21,xzr
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])
316 adcs x21,x21,x15
321 umulh x17,x7,x6 // hi(a[1..7]*a[0])
328 stp x19,x20,[x2],#8*2 // t[0..1]
330 adds x21,x21,x17 // t[2]+lo(a[1]*a[0])
357 stp x21,x22,[x2],#8*2 // t[2..3]
383 adc x21,xzr,xzr // t[10]
392 adc x21,x21,x17
401 adcs x21,x21,x17
409 adcs x21,x21,x16
416 adcs x21,x21,x15
421 adds x21,x21,x17
445 ldp x6,x7,[x2,#8*0]
451 ldp x6,x7,[x1,#8*0]
452 adcs x21,x21,x8
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]
499 adcs x21,x21,x16
515 adcs x20,x21,x15
517 adcs x21,x22,x16
533 ldp x6,x7,[x2,#8*0]
540 ldp x6,x7,[x1,#8*0]
541 adcs x21,x21,x8
557 ldp x6,x7,[x0,#8*0]
566 stp x19,x20,[x2,#8*0]
567 ldp x19,x20,[x15,#8*0]
568 stp x21,x22,[x2,#8*2]
569 ldp x21,x22,[x15,#8*2]
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]
586 stp x19,x20,[x2,#8*0]
588 stp x21,x22,[x2,#8*2]
600 adcs x21,x8,x15
611 stp x19,x20,[x2,#8*0]
614 stp x21,x22,[x2,#8*2]
639 adcs x21,x8,x15
645 stp x19,x20,[x2,#8*0]
648 stp x21,x22,[x2,#8*2]
652 ldp x19,x20,[sp,#8*0]
655 ldp x6,x7,[x1,#8*0]
663 mul x28,x4,x19 // t[0]*n0
666 ldp x21,x22,[sp,#8*2]
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
688 adcs x20,x21,x16
690 adcs x21,x22,x17
693 umulh x14,x6,x28 // hi(n[0-7])*lo(t[0]*n0)
705 adcs x21,x21,x16
709 mul x28,x4,x19 // next t[0]*n0
716 ldp x14,x15,[x2,#8*0]
723 adcs x21,x21,x16
734 ldp x6,x7,[x1,#8*0]
752 adcs x21,x21,x16
768 adcs x20,x21,x15
770 adcs x21,x22,x16
783 ldp x6,x7,[x2,#8*0]
794 ldp x6,x7,[x1,#8*0]
795 adcs x21,x21,x8
817 ldp x19,x20,[x0,#8*0]
818 adcs x21,x21,x8
819 ldp x6,x7,[x16,#8*0] // recall that x16 is &n[0]
831 stp x14,x15,[x2,#8*0]
832 stp x21,x22,[x2,#8*2]
833 ldp x21,x22,[x0,#8*2]
855 sbcs x16,x21,x8
856 ldp x6,x7,[x1,#8*0]
858 stp x14,x15,[x0,#8*0]
868 ldp x19,x20,[x2,#8*0]
870 ldp x21,x22,[x2,#8*2]
881 sbcs x16,x21,x8
884 ldp x6,x7,[x3,#8*0]
886 stp x14,x15,[x0,#8*0]
892 ldp x19,x20,[x1,#8*0]
894 ldp x21,x22,[x1,#8*2]
904 stp xzr,xzr,[x2,#8*0]
908 csel x16,x21,x8,lo
913 ldp x21,x22,[x1,#8*6]
915 stp x14,x15,[x3,#8*0]
918 stp xzr,xzr,[x1,#8*0]
923 stp xzr,xzr,[x2,#8*0]
926 csel x16,x21,x8,lo
928 stp x14,x15,[x3,#8*0]
941 stp xzr,xzr,[sp,#8*0]
942 sbcs x8,x21,x8
960 csel x8,x21,x8,lo
962 stp x6,x7,[x1,#8*0]
974 ldp x21,x22,[x29,#32]
991 add x29,sp,#0
993 stp x21,x22,[sp,#32]
1007 ldr x24,[x2,#8*0] // b[0]
1008 ldp x6,x7,[x1,#8*0] // a[0..3]
1013 mov x21,xzr
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
1034 adcs x21,x21,x12
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
1044 adcs x21,x21,x11
1052 umulh x10,x14,x25 // hi(n[0..3]*t[0]*n0)
1055 adcs x20,x21,x12
1057 adcs x21,x22,x13
1064 adcs x21,x21,x12
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]
1091 adcs x21,x21,x12
1096 ldr x24,[x2,x28] // next b[i] (or b[0])
1098 mul x10,x14,x25 // lo(n[4..7]*a[0]*n0)
1099 adcs x21,x21,x11
1106 umulh x10,x14,x25 // hi(n[4..7]*a[0]*n0)
1109 adcs x21,x21,x12
1115 ldr x25,[sp,x28] // next t[0]*n0
1119 adcs x20,x21,x11
1120 adcs x21,x22,x12
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]
1147 stp x21,x22,[x26,#8*2] // result!!!
1148 ldp x21,x22,[sp,#8*6]
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
1169 adcs x21,x21,x12
1178 str x25,[x26],#8 // put aside t[0]*n0 for tail processing
1179 adcs x21,x21,x11
1180 mul x11,x15,x25 // lo(n[0..3]*t[0]*n0
1187 umulh x10,x14,x25 // hi(n[0..3]*t[0]*n0
1190 adcs x20,x21,x12
1192 adcs x21,x22,x13
1198 adcs x21,x21,x12
1206 ldp x6,x7,[x1,#8*0] // a[4..7]
1211 adcs x21,x21,x12
1215 ldr x25,[sp] // t[0]*n0
1216 ldp x14,x15,[x3,#8*0] // n[4..7]
1233 adcs x21,x21,x12
1240 mul x10,x14,x25 // lo(n[4..7]*t[0]*n0)
1241 adcs x21,x21,x11
1248 umulh x10,x14,x25 // hi(n[4..7]*t[0]*n0)
1251 adcs x21,x21,x12
1256 ldr x25,[sp,x28] // next a[0]*n0
1261 adcs x20,x21,x11
1262 adcs x21,x22,x12
1273 ldp x6,x7,[x1,#8*0]
1278 adcs x21,x21,x12
1281 ldp x14,x15,[x3,#8*0]
1293 adcs x21,x21,xzr
1294 stp x19,x20,[x26,#8*0] // result!!!
1296 ldp x19,x20,[sp,#8*4] // t[0..3]
1298 stp x21,x22,[x26,#8*2] // result!!!
1300 ldp x21,x22,[sp,#8*6]
1301 ldp x14,x15,[x11,#8*0] // n[0..3]
1307 ldp x6,x7,[x1,#8*0] // a[0..3]
1328 sbcs x12,x21,x16
1329 ldp x14,x15,[x3,#8*0]
1331 ldp x19,x20,[x26,#8*0]
1335 ldp x21,x22,[x26,#8*2]
1337 stp x10,x11,[x0,#8*0]
1344 sbcs x12,x21,x16
1347 ldp x6,x7,[x27,#8*0]
1349 stp x10,x11,[x0,#8*0]
1352 ldp x19,x20,[x1,#8*0]
1353 ldp x21,x22,[x1,#8*2]
1361 stp xzr,xzr,[x26,#8*0]
1365 csel x12,x21,x8,lo
1370 ldp x21,x22,[x1,#8*6]
1372 stp x10,x11,[x27,#8*0]
1378 stp xzr,xzr,[x26,#8*0]
1381 csel x12,x21,x8,lo
1385 stp x10,x11,[x27,#8*0]
1398 stp xzr,xzr,[sp,#8*0]
1399 sbcs x8,x21,x16
1409 csel x8,x21,x8,lo
1411 stp x6,x7,[x1,#8*0]
1417 ldp x21,x22,[x29,#32]
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