Lines Matching +full:0 +full:x21
5 #define __has_feature(x) 0
34 add x29,sp,#0
36 stp x21,x22,[sp,#32]
39 ldr x9,[x2],#8 // bp[0]
41 ldp x7,x8,[x1],#16 // ap[0..1]
45 ldp x13,x14,[x3],#16 // np[0..1]
47 mul x6,x7,x9 // ap[0]*bp[0]
48 sub x21,x5,#16 // j=num-2
50 mul x10,x8,x9 // ap[1]*bp[0]
53 mul x15,x6,x4 // "tp[0]"*n0
56 // (*) mul x12,x13,x15 // np[0]*m1
72 cbz x21,L1st_skip
77 sub x21,x21,#8 // j--
82 mul x10,x8,x9 // ap[j]*bp[0]
91 cbnz x21,L1st
112 ldr x23,[sp] // tp[0]
115 mul x6,x7,x9 // ap[0]*bp[i]
116 sub x21,x5,#16 // j=num-2
127 // (*) mul x12,x13,x15 // np[0]*m1
133 cbz x21,Linner_skip
140 sub x21,x21,#8 // j--
156 cbnz x21,Linner
184 ldr x23,[sp] // tp[0]
186 ldr x14,[x3],#8 // np[0]
187 subs x21,x5,#8 // j=num-1 and clear borrow
192 sub x21,x21,#8 // j--
195 cbnz x21,Lsub
201 ldr x23,[sp] // tp[0]
203 ldr x8,[x0],#8 // rp[0]
221 ldp x21,x22,[x29,#32]
239 add x29,sp,#0
241 stp x21,x22,[sp,#32]
247 ldp x6,x7,[x1,#8*0]
261 stp xzr,xzr,[x2,#8*0]
277 mov x21,xzr
289 // a[1]a[0] (i)
290 // a[2]a[0]
291 // a[3]a[0]
292 // a[4]a[0]
293 // a[5]a[0]
294 // a[6]a[0]
295 // a[7]a[0]
318 mul x14,x7,x6 // lo(a[1..7]*a[0]) (i)
322 adds x20,x20,x14 // t[1]+lo(a[1]*a[0])
324 adcs x21,x21,x15
329 umulh x17,x7,x6 // hi(a[1..7]*a[0])
336 stp x19,x20,[x2],#8*2 // t[0..1]
338 adds x21,x21,x17 // t[2]+lo(a[1]*a[0])
365 stp x21,x22,[x2],#8*2 // t[2..3]
391 adc x21,xzr,xzr // t[10]
400 adc x21,x21,x17
409 adcs x21,x21,x17
417 adcs x21,x21,x16
424 adcs x21,x21,x15
429 adds x21,x21,x17
453 ldp x6,x7,[x2,#8*0]
459 ldp x6,x7,[x1,#8*0]
460 adcs x21,x21,x8
474 // a[8]a[0]
475 // a[9]a[0]
476 // a[a]a[0]
477 // a[b]a[0]
478 // a[c]a[0]
479 // a[d]a[0]
480 // a[e]a[0]
481 // a[f]a[0]
507 adcs x21,x21,x16
523 adcs x20,x21,x15
525 adcs x21,x22,x16
541 ldp x6,x7,[x2,#8*0]
548 ldp x6,x7,[x1,#8*0]
549 adcs x21,x21,x8
565 ldp x6,x7,[x0,#8*0]
574 stp x19,x20,[x2,#8*0]
575 ldp x19,x20,[x15,#8*0]
576 stp x21,x22,[x2,#8*2]
577 ldp x21,x22,[x15,#8*2]
587 // Now multiply above result by 2 and add a[n-1]*a[n-1]|...|a[0]*a[0]
588 ldp x7,x9,[x14,#8*0] // recall that x14 is &a[0]
594 stp x19,x20,[x2,#8*0]
596 stp x21,x22,[x2,#8*2]
608 adcs x21,x8,x15
619 stp x19,x20,[x2,#8*0]
622 stp x21,x22,[x2,#8*2]
647 adcs x21,x8,x15
653 stp x19,x20,[x2,#8*0]
656 stp x21,x22,[x2,#8*2]
660 ldp x19,x20,[sp,#8*0]
663 ldp x6,x7,[x1,#8*0]
671 mul x28,x4,x19 // t[0]*n0
674 ldp x21,x22,[sp,#8*2]
685 // (*) mul x14,x6,x28 // lo(n[0-7])*lo(t[0]*n0)
689 str x28,[x2],#8 // put aside t[0]*n0 for tail processing
696 adcs x20,x21,x16
698 adcs x21,x22,x17
701 umulh x14,x6,x28 // hi(n[0-7])*lo(t[0]*n0)
713 adcs x21,x21,x16
717 mul x28,x4,x19 // next t[0]*n0
724 ldp x14,x15,[x2,#8*0]
731 adcs x21,x21,x16
742 ldp x6,x7,[x1,#8*0]
760 adcs x21,x21,x16
776 adcs x20,x21,x15
778 adcs x21,x22,x16
791 ldp x6,x7,[x2,#8*0]
802 ldp x6,x7,[x1,#8*0]
803 adcs x21,x21,x8
825 ldp x19,x20,[x0,#8*0]
826 adcs x21,x21,x8
827 ldp x6,x7,[x16,#8*0] // recall that x16 is &n[0]
839 stp x14,x15,[x2,#8*0]
840 stp x21,x22,[x2,#8*2]
841 ldp x21,x22,[x0,#8*2]
863 sbcs x16,x21,x8
864 ldp x6,x7,[x1,#8*0]
866 stp x14,x15,[x0,#8*0]
876 ldp x19,x20,[x2,#8*0]
878 ldp x21,x22,[x2,#8*2]
889 sbcs x16,x21,x8
892 ldp x6,x7,[x3,#8*0]
894 stp x14,x15,[x0,#8*0]
900 ldp x19,x20,[x1,#8*0]
902 ldp x21,x22,[x1,#8*2]
912 stp xzr,xzr,[x2,#8*0]
916 csel x16,x21,x8,lo
921 ldp x21,x22,[x1,#8*6]
923 stp x14,x15,[x3,#8*0]
926 stp xzr,xzr,[x1,#8*0]
931 stp xzr,xzr,[x2,#8*0]
934 csel x16,x21,x8,lo
936 stp x14,x15,[x3,#8*0]
949 stp xzr,xzr,[sp,#8*0]
950 sbcs x8,x21,x8
968 csel x8,x21,x8,lo
970 stp x6,x7,[x1,#8*0]
982 ldp x21,x22,[x29,#32]
1001 add x29,sp,#0
1003 stp x21,x22,[sp,#32]
1017 ldr x24,[x2,#8*0] // b[0]
1018 ldp x6,x7,[x1,#8*0] // a[0..3]
1023 mov x21,xzr
1025 ldp x14,x15,[x3,#8*0] // n[0..3]
1029 mov x28,#0
1033 mul x10,x6,x24 // lo(a[0..3]*b[0])
1041 umulh x10,x6,x24 // hi(a[0..3]*b[0])
1043 mul x25,x19,x4 // t[0]*n0
1044 adcs x21,x21,x12
1050 ldr x24,[x2,x28] // next b[i] (or b[0])
1052 // (*) mul x10,x14,x25 // lo(n[0..3]*t[0]*n0)
1053 str x25,[x26],#8 // put aside t[0]*n0 for tail processing
1054 adcs x21,x21,x11
1062 umulh x10,x14,x25 // hi(n[0..3]*t[0]*n0)
1065 adcs x20,x21,x12
1067 adcs x21,x22,x13
1074 adcs x21,x21,x12
1081 ldp x6,x7,[x1,#8*0] // a[4..7]
1084 ldr x25,[sp] // a[0]*n0
1085 ldp x14,x15,[x3,#8*0] // n[4..7]
1101 adcs x21,x21,x12
1106 ldr x24,[x2,x28] // next b[i] (or b[0])
1108 mul x10,x14,x25 // lo(n[4..7]*a[0]*n0)
1109 adcs x21,x21,x11
1116 umulh x10,x14,x25 // hi(n[4..7]*a[0]*n0)
1119 adcs x21,x21,x12
1125 ldr x25,[sp,x28] // next t[0]*n0
1129 adcs x20,x21,x11
1130 adcs x21,x22,x12
1138 ldp x6,x7,[x1,#8*0]
1141 ldp x14,x15,[x3,#8*0]
1150 ldp x6,x7,[x11,#8*0] // a[0..3]
1155 stp x19,x20,[x26,#8*0] // result!!!
1156 ldp x19,x20,[sp,#8*4] // t[0..3]
1157 stp x21,x22,[x26,#8*2] // result!!!
1158 ldp x21,x22,[sp,#8*6]
1160 ldp x14,x15,[x3,#8*0] // n[0..3]
1168 mul x10,x6,x24 // lo(a[0..3]*b[4])
1176 umulh x10,x6,x24 // hi(a[0..3]*b[4])
1178 mul x25,x19,x4 // t[0]*n0
1179 adcs x21,x21,x12
1188 str x25,[x26],#8 // put aside t[0]*n0 for tail processing
1189 adcs x21,x21,x11
1190 mul x11,x15,x25 // lo(n[0..3]*t[0]*n0
1197 umulh x10,x14,x25 // hi(n[0..3]*t[0]*n0
1200 adcs x20,x21,x12
1202 adcs x21,x22,x13
1208 adcs x21,x21,x12
1216 ldp x6,x7,[x1,#8*0] // a[4..7]
1221 adcs x21,x21,x12
1225 ldr x25,[sp] // t[0]*n0
1226 ldp x14,x15,[x3,#8*0] // n[4..7]
1243 adcs x21,x21,x12
1250 mul x10,x14,x25 // lo(n[4..7]*t[0]*n0)
1251 adcs x21,x21,x11
1258 umulh x10,x14,x25 // hi(n[4..7]*t[0]*n0)
1261 adcs x21,x21,x12
1266 ldr x25,[sp,x28] // next a[0]*n0
1271 adcs x20,x21,x11
1272 adcs x21,x22,x12
1283 ldp x6,x7,[x1,#8*0]
1288 adcs x21,x21,x12
1291 ldp x14,x15,[x3,#8*0]
1303 adcs x21,x21,xzr
1304 stp x19,x20,[x26,#8*0] // result!!!
1306 ldp x19,x20,[sp,#8*4] // t[0..3]
1308 stp x21,x22,[x26,#8*2] // result!!!
1310 ldp x21,x22,[sp,#8*6]
1311 ldp x14,x15,[x11,#8*0] // n[0..3]
1317 ldp x6,x7,[x1,#8*0] // a[0..3]
1338 sbcs x12,x21,x16
1339 ldp x14,x15,[x3,#8*0]
1341 ldp x19,x20,[x26,#8*0]
1345 ldp x21,x22,[x26,#8*2]
1347 stp x10,x11,[x0,#8*0]
1354 sbcs x12,x21,x16
1357 ldp x6,x7,[x27,#8*0]
1359 stp x10,x11,[x0,#8*0]
1362 ldp x19,x20,[x1,#8*0]
1363 ldp x21,x22,[x1,#8*2]
1371 stp xzr,xzr,[x26,#8*0]
1375 csel x12,x21,x8,lo
1380 ldp x21,x22,[x1,#8*6]
1382 stp x10,x11,[x27,#8*0]
1388 stp xzr,xzr,[x26,#8*0]
1391 csel x12,x21,x8,lo
1395 stp x10,x11,[x27,#8*0]
1408 stp xzr,xzr,[sp,#8*0]
1409 sbcs x8,x21,x16
1419 csel x8,x21,x8,lo
1421 stp x6,x7,[x1,#8*0]
1427 ldp x21,x22,[x29,#32]
1437 …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