Lines Matching +full:0 +full:x25
5 #define __has_feature(x) 0
31 add x29,sp,#0
36 ldr x9,[x2],#8 // bp[0]
38 ldp x7,x8,[x1],#16 // ap[0..1]
42 ldp x13,x14,[x3],#16 // np[0..1]
44 mul x6,x7,x9 // ap[0]*bp[0]
47 mul x10,x8,x9 // ap[1]*bp[0]
50 mul x15,x6,x4 // "tp[0]"*n0
53 // (*) mul x12,x13,x15 // np[0]*m1
79 mul x10,x8,x9 // ap[j]*bp[0]
109 ldr x23,[sp] // tp[0]
112 mul x6,x7,x9 // ap[0]*bp[i]
124 // (*) mul x12,x13,x15 // np[0]*m1
181 ldr x23,[sp] // tp[0]
183 ldr x14,[x3],#8 // np[0]
198 ldr x23,[sp] // tp[0]
200 ldr x8,[x0],#8 // rp[0]
234 add x29,sp,#0
238 stp x25,x26,[sp,#64]
242 ldp x6,x7,[x1,#8*0]
256 stp xzr,xzr,[x2,#8*0]
276 mov x25,xzr
284 // a[1]a[0] (i)
285 // a[2]a[0]
286 // a[3]a[0]
287 // a[4]a[0]
288 // a[5]a[0]
289 // a[6]a[0]
290 // a[7]a[0]
313 mul x14,x7,x6 // lo(a[1..7]*a[0]) (i)
317 adds x20,x20,x14 // t[1]+lo(a[1]*a[0])
324 umulh x17,x7,x6 // hi(a[1..7]*a[0])
327 adcs x25,x25,x15
331 stp x19,x20,[x2],#8*2 // t[0..1]
333 adds x21,x21,x17 // t[2]+lo(a[1]*a[0])
341 adcs x25,x25,x17
354 adcs x25,x25,x15
366 adcs x25,x25,x16
377 adcs x25,x25,x17
387 adds x25,x25,x17
406 stp x25,x26,[x2],#8*2 // t[6..7]
442 adc x25,xzr,xzr // t[14]
443 add x25,x25,x17
448 ldp x6,x7,[x2,#8*0]
454 ldp x6,x7,[x1,#8*0]
461 adcs x25,x25,x12
469 // a[8]a[0]
470 // a[9]a[0]
471 // a[a]a[0]
472 // a[b]a[0]
473 // a[c]a[0]
474 // a[d]a[0]
475 // a[e]a[0]
476 // a[f]a[0]
510 adcs x25,x25,x16
526 adcs x24,x25,x15
527 adcs x25,x26,x16
536 ldp x6,x7,[x2,#8*0]
543 ldp x6,x7,[x1,#8*0]
550 adcs x25,x25,x12
560 ldp x6,x7,[x0,#8*0]
569 stp x19,x20,[x2,#8*0]
570 ldp x19,x20,[x15,#8*0]
575 stp x25,x26,[x2,#8*6]
577 ldp x25,x26,[x15,#8*6]
582 // Now multiply above result by 2 and add a[n-1]*a[n-1]|...|a[0]*a[0]
583 ldp x7,x9,[x14,#8*0] // recall that x14 is &a[0]
589 stp x19,x20,[x2,#8*0]
595 stp x25,x26,[x2,#8*6]
614 stp x19,x20,[x2,#8*0]
621 adcs x25,x12,x15
632 stp x25,x26,[x2,#8*6]
648 stp x19,x20,[x2,#8*0]
655 ldp x19,x20,[sp,#8*0]
658 ldp x6,x7,[x1,#8*0]
659 adcs x25,x12,x15
666 mul x28,x4,x19 // t[0]*n0
672 stp x25,x26,[x2,#8*6]
673 ldp x25,x26,[sp,#8*6]
680 // (*) mul x14,x6,x28 // lo(n[0-7])*lo(t[0]*n0)
684 str x28,[x2],#8 // put aside t[0]*n0 for tail processing
696 umulh x14,x6,x28 // hi(n[0-7])*lo(t[0]*n0)
699 adcs x24,x25,x16
701 adcs x25,x26,x17
712 mul x28,x4,x19 // next t[0]*n0
715 adcs x25,x25,x16
719 ldp x14,x15,[x2,#8*0]
731 adcs x25,x25,x16
737 ldp x6,x7,[x1,#8*0]
763 adcs x25,x25,x16
779 adcs x24,x25,x15
780 adcs x25,x26,x16
786 ldp x6,x7,[x2,#8*0]
797 ldp x6,x7,[x1,#8*0]
804 adcs x25,x25,x12
820 ldp x19,x20,[x0,#8*0]
822 ldp x6,x7,[x16,#8*0] // recall that x16 is &n[0]
828 adcs x25,x25,x12
834 stp x14,x15,[x2,#8*0]
840 stp x25,x26,[x2,#8*6]
842 ldp x25,x26,[x0,#8*6]
859 ldp x6,x7,[x1,#8*0]
861 stp x14,x15,[x0,#8*0]
866 sbcs x16,x25,x12
871 ldp x19,x20,[x2,#8*0]
875 ldp x25,x26,[x2,#8*6]
887 ldp x6,x7,[x3,#8*0]
889 stp x14,x15,[x0,#8*0]
894 sbcs x16,x25,x12
895 ldp x19,x20,[x1,#8*0]
907 stp xzr,xzr,[x2,#8*0]
918 stp x14,x15,[x3,#8*0]
921 stp xzr,xzr,[x1,#8*0]
926 stp xzr,xzr,[x2,#8*0]
931 stp x14,x15,[x3,#8*0]
944 stp xzr,xzr,[sp,#8*0]
953 sbcs x12,x25,x12
965 stp x6,x7,[x1,#8*0]
969 csel x12,x25,x12,lo
980 ldp x25,x26,[x29,#64]
994 add x29,sp,#0
998 stp x25,x26,[sp,#64]
1010 ldr x24,[x2,#8*0] // b[0]
1011 ldp x6,x7,[x1,#8*0] // a[0..3]
1018 ldp x14,x15,[x3,#8*0] // n[0..3]
1022 mov x28,#0
1026 mul x10,x6,x24 // lo(a[0..3]*b[0])
1034 umulh x10,x6,x24 // hi(a[0..3]*b[0])
1036 mul x25,x19,x4 // t[0]*n0
1043 ldr x24,[x2,x28] // next b[i] (or b[0])
1045 // (*) mul x10,x14,x25 // lo(n[0..3]*t[0]*n0)
1046 str x25,[x26],#8 // put aside t[0]*n0 for tail processing
1048 mul x11,x15,x25
1050 mul x12,x16,x25
1052 mul x13,x17,x25
1055 umulh x10,x14,x25 // hi(n[0..3]*t[0]*n0)
1057 umulh x11,x15,x25
1059 umulh x12,x16,x25
1061 umulh x13,x17,x25
1074 ldp x6,x7,[x1,#8*0] // a[4..7]
1077 ldr x25,[sp] // a[0]*n0
1078 ldp x14,x15,[x3,#8*0] // n[4..7]
1099 ldr x24,[x2,x28] // next b[i] (or b[0])
1101 mul x10,x14,x25 // lo(n[4..7]*a[0]*n0)
1103 mul x11,x15,x25
1105 mul x12,x16,x25
1107 mul x13,x17,x25
1109 umulh x10,x14,x25 // hi(n[4..7]*a[0]*n0)
1111 umulh x11,x15,x25
1113 umulh x12,x16,x25
1116 umulh x13,x17,x25
1118 ldr x25,[sp,x28] // next t[0]*n0
1131 ldp x6,x7,[x1,#8*0]
1134 ldp x14,x15,[x3,#8*0]
1143 ldp x6,x7,[x11,#8*0] // a[0..3]
1148 stp x19,x20,[x26,#8*0] // result!!!
1149 ldp x19,x20,[sp,#8*4] // t[0..3]
1153 ldp x14,x15,[x3,#8*0] // n[0..3]
1161 mul x10,x6,x24 // lo(a[0..3]*b[4])
1169 umulh x10,x6,x24 // hi(a[0..3]*b[4])
1171 mul x25,x19,x4 // t[0]*n0
1180 // (*) mul x10,x14,x25
1181 str x25,[x26],#8 // put aside t[0]*n0 for tail processing
1183 mul x11,x15,x25 // lo(n[0..3]*t[0]*n0
1185 mul x12,x16,x25
1187 mul x13,x17,x25
1190 umulh x10,x14,x25 // hi(n[0..3]*t[0]*n0
1192 umulh x11,x15,x25
1194 umulh x12,x16,x25
1196 umulh x13,x17,x25
1209 ldp x6,x7,[x1,#8*0] // a[4..7]
1218 ldr x25,[sp] // t[0]*n0
1219 ldp x14,x15,[x3,#8*0] // n[4..7]
1243 mul x10,x14,x25 // lo(n[4..7]*t[0]*n0)
1245 mul x11,x15,x25
1247 mul x12,x16,x25
1249 mul x13,x17,x25
1251 umulh x10,x14,x25 // hi(n[4..7]*t[0]*n0)
1253 umulh x11,x15,x25
1255 umulh x12,x16,x25
1257 umulh x13,x17,x25
1259 ldr x25,[sp,x28] // next a[0]*n0
1276 ldp x6,x7,[x1,#8*0]
1284 ldp x14,x15,[x3,#8*0]
1297 stp x19,x20,[x26,#8*0] // result!!!
1299 ldp x19,x20,[sp,#8*4] // t[0..3]
1304 ldp x14,x15,[x11,#8*0] // n[0..3]
1310 ldp x6,x7,[x1,#8*0] // a[0..3]
1332 ldp x14,x15,[x3,#8*0]
1334 ldp x19,x20,[x26,#8*0]
1340 stp x10,x11,[x0,#8*0]
1350 ldp x6,x7,[x27,#8*0]
1352 stp x10,x11,[x0,#8*0]
1355 ldp x19,x20,[x1,#8*0]
1364 stp xzr,xzr,[x26,#8*0]
1375 stp x10,x11,[x27,#8*0]
1381 stp xzr,xzr,[x26,#8*0]
1388 stp x10,x11,[x27,#8*0]
1401 stp xzr,xzr,[sp,#8*0]
1414 stp x6,x7,[x1,#8*0]
1423 ldp x25,x26,[x29,#64]
1430 …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