Lines Matching refs:A0
701 my @A0=("%r10","%r11");
703 my ($a0,$a1,$ai)=("%r14","%r15","%rbx");
753 mov -32($aptr,$i),$a0 # a[0]
760 mul $a0 # a[1]*a[0]
761 mov %rax,$A0[0] # a[1]*a[0]
763 mov %rdx,$A0[1]
764 mov $A0[0],-24($tptr,$i) # t[1]
766 xor $A0[0],$A0[0]
767 mul $a0 # a[2]*a[0]
768 add %rax,$A0[1]
770 adc %rdx,$A0[0]
771 mov $A0[1],-16($tptr,$i) # t[2]
782 xor $A0[1],$A0[1]
783 add $A1[0],$A0[0]
785 adc \$0,$A0[1]
786 mul $a0 # a[3]*a[0]
787 add %rax,$A0[0] # a[3]*a[0]+a[2]*a[1]+t[3]
789 adc %rdx,$A0[1]
790 mov $A0[0],-8($tptr,$j) # t[3]
802 xor $A0[0],$A0[0]
803 add $A1[1],$A0[1]
804 adc \$0,$A0[0]
805 mul $a0 # a[4]*a[0]
806 A0[1] # a[4]*a[0]+a[3]*a[1]+t[4]
808 adc %rdx,$A0[0]
809 mov $A0[1],($tptr,$j) # t[4]
819 xor $A0[1],$A0[1]
820 add $A1[0],$A0[0]
821 adc \$0,$A0[1]
822 mul $a0 # a[5]*a[2]
823 add %rax,$A0[0] # a[5]*a[2]+a[4]*a[3]+t[5]
825 adc %rdx,$A0[1]
826 mov $A0[0],8($tptr,$j) # t[5]
835 xor $A0[0],$A0[0]
836 add $A1[1],$A0[1]
837 adc \$0,$A0[0]
838 mul $a0 # a[6]*a[2]
839 add %rax,$A0[1] # a[6]*a[2]+a[5]*a[3]+t[6]
841 adc %rdx,$A0[0]
842 mov $A0[1],16($tptr,$j) # t[6]
852 xor $A0[1],$A0[1]
853 add $A1[0],$A0[0]
855 adc \$0,$A0[1]
856 mul $a0 # a[7]*a[4]
857 add %rax,$A0[0] # a[7]*a[4]+a[6]*a[5]+t[6]
859 adc %rdx,$A0[1]
860 mov $A0[0],-8($tptr,$j) # t[7]
866 add $A0[1],$A1[1]
879 mov -32($aptr,$i),$a0 # a[0]
886 mov -24($tptr,$i),$A0[0] # t[1]
887 xor $A0[1],$A0[1]
888 mul $a0 # a[1]*a[0]
889 add %rax,$A0[0] # a[1]*a[0]+t[1]
891 adc %rdx,$A0[1]
892 mov $A0[0],-24($tptr,$i) # t[1]
894 xor $A0[0],$A0[0]
895 add -16($tptr,$i),$A0[1] # a[2]*a[0]+t[2]
896 adc \$0,$A0[0]
897 mul $a0 # a[2]*a[0]
898 add %rax,$A0[1]
900 adc %rdx,$A0[0]
901 mov $A0[1],-16($tptr,$i) # t[2]
916 xor $A0[1],$A0[1]
917 add $A1[0],$A0[0]
918 adc \$0,$A0[1]
919 mul $a0 # a[3]*a[0]
920 add %rax,$A0[0] # a[3]*a[0]+a[2]*a[1]+t[3]
922 adc %rdx,$A0[1]
923 mov $A0[0],8($tptr,$j) # t[3]
939 xor $A0[0],$A0[0]
940 add $A1[1],$A0[1]
941 adc \$0,$A0[0]
942 mul $a0 # a[4]*a[0]
943 add %rax,$A0[1] # a[4]*a[0]+a[3]*a[1]+t[4]
945 adc %rdx,$A0[0]
946 mov $A0[1],($tptr,$j) # t[4]
957 xor $A0[1],$A0[1]
958 add $A1[0],$A0[0]
960 adc \$0,$A0[1]
961 mul $a0 # a[5]*a[2]
962 add %rax,$A0[0] # a[5]*a[2]+a[4]*a[3]+t[5]
964 adc %rdx,$A0[1]
965 mov $A0[0],-8($tptr,$j) # t[5], "preloaded t[1]" below
971 add $A0[1],$A1[1]
984 mov -32($aptr),$a0 # a[0]
991 xor $A0[1],$A0[1]
992 mul $a0 # a[1]*a[0]
993 add %rax,$A0[0] # a[1]*a[0]+t[1], preloaded t[1]
995 adc %rdx,$A0[1]
996 mov $A0[0],-24($tptr) # t[1]
998 xor $A0[0],$A0[0]
999 add $A1[1],$A0[1] # a[2]*a[0]+t[2], preloaded t[2]
1000 adc \$0,$A0[0]
1001 mul $a0 # a[2]*a[0]
1002 add %rax,$A0[1]
1004 adc %rdx,$A0[0]
1005 mov $A0[1],-16($tptr) # t[2]
1013 xor $A0[1],$A0[1]
1014 add $A1[0],$A0[0]
1016 adc \$0,$A0[1]
1017 mul $a0 # a[3]*a[0]
1018 add %rax,$A0[0] # a[3]*a[0]+a[2]*a[1]+t[3]
1020 adc %rdx,$A0[1]
1021 mov $A0[0],-8($tptr) # t[3]
1024 add $A0[1],$A1[1]
1037 my ($shift,$carry)=($a0,$a1);
1053 xor $A0[0],$A0[0] # t[0]
1054 mov -24($tptr,$i,2),$A0[1] # t[1]
1056 lea ($shift,$A0[0],2),$S[0] # t[2*i]<<1 | shift
1057 shr \$63,$A0[0]
1058 lea ($j,$A0[1],2),$S[1] # t[2*i+1]<<1 |
1059 shr \$63,$A0[1]
1060 or $A0[0],$S[1] # | t[2*i]>>63
1061 mov -16($tptr,$i,2),$A0[0] # t[2*i+2] # prefetch
1062 mov $A0[1],$shift # shift=t[2*i+1]>>63
1065 mov -8($tptr,$i,2),$A0[1] # t[2*i+2+1] # prefetch
1071 lea ($shift,$A0[0],2),$S[2] # t[2*i]<<1 | shift
1074 shr \$63,$A0[0]
1075 lea ($j,$A0[1],2),$S[3] # t[2*i+1]<<1 |
1076 shr \$63,$A0[1]
1077 or $A0[0],$S[3] # | t[2*i]>>63
1078 mov 0($tptr,$i,2),$A0[0] # t[2*i+2] # prefetch
1079 mov $A0[1],$shift # shift=t[2*i+1]>>63
1082 mov 8($tptr,$i,2),$A0[1] # t[2*i+2+1] # prefetch
1094 lea ($shift,$A0[0],2),$S[0] # t[2*i]<<1 | shift
1095 shr \$63,$A0[0]
1096 lea ($j,$A0[1],2),$S[1] # t[2*i+1]<<1 |
1097 shr \$63,$A0[1]
1098 or $A0[0],$S[1] # | t[2*i]>>63
1099 mov -16($tptr,$i,2),$A0[0] # t[2*i+2] # prefetch
1100 mov $A0[1],$shift # shift=t[2*i+1]>>63
1103 mov -8($tptr,$i,2),$A0[1] # t[2*i+2+1] # prefetch
1109 lea ($shift,$A0[0],2),$S[2] # t[2*i]<<1 | shift
1112 shr \$63,$A0[0]
1113 lea ($j,$A0[1],2),$S[3] # t[2*i+1]<<1 |
1114 shr \$63,$A0[1]
1115 or $A0[0],$S[3] # | t[2*i]>>63
1116 mov 0($tptr,$i,2),$A0[0] # t[2*i+2] # prefetch
1117 mov $A0[1],$shift # shift=t[2*i+1]>>63
1120 mov 8($tptr,$i,2),$A0[1] # t[2*i+2+1] # prefetch
1126 lea ($shift,$A0[0],2),$S[0] # t[2*i]<<1 | shift
1129 shr \$63,$A0[0]
1130 lea ($j,$A0[1],2),$S[1] # t[2*i+1]<<1 |
1131 shr \$63,$A0[1]
1132 or $A0[0],$S[1] # | t[2*i]>>63
1133 mov 16($tptr,$i,2),$A0[0] # t[2*i+2] # prefetch
1134 mov $A0[1],$shift # shift=t[2*i+1]>>63
1137 mov 24($tptr,$i,2),$A0[1] # t[2*i+2+1] # prefetch
1143 lea ($shift,$A0[0],2),$S[2] # t[2*i]<<1 | shift
1146 shr \$63,$A0[0]
1147 lea ($j,$A0[1],2),$S[3] # t[2*i+1]<<1 |
1148 shr \$63,$A0[1]
1149 or $A0[0],$S[3] # | t[2*i]>>63
1150 mov 32($tptr,$i,2),$A0[0] # t[2*i+2] # prefetch
1151 mov $A0[1],$shift # shift=t[2*i+1]>>63
1154 mov 40($tptr,$i,2),$A0[1] # t[2*i+2+1] # prefetch
1164 lea ($shift,$A0[0],2),$S[0] # t[2*i]<<1 | shift
1165 shr \$63,$A0[0]
1166 lea ($j,$A0[1],2),$S[1] # t[2*i+1]<<1 |
1167 shr \$63,$A0[1]
1168 or $A0[0],$S[1] # | t[2*i]>>63
1169 mov -16($tptr),$A0[0] # t[2*i+2] # prefetch
1170 mov $A0[1],$shift # shift=t[2*i+1]>>63
1173 mov -8($tptr),$A0[1] # t[2*i+2+1] # prefetch
1179 lea ($shift,$A0[0],2),$S[2] # t[2*i]<<1|shift
1182 shr \$63,$A0[0]
1183 lea ($j,$A0[1],2),$S[3] # t[2*i+1]<<1 |
1184 shr \$63,$A0[1]
1185 or $A0[0],$S[3] # | t[2*i]>>63
1200 my ($m0,$m1)=($a0,$a1);
1208 mov 64(%rsp),$A0[0] # t[0] # modsched #
1218 imulq $A0[0],$m0 # m0=t[0]*n0 # modsched #
1224 xor $A0[1],$A0[1]
1226 add %rax,$A0[0] # n[0]*m0+t[0]
1228 adc %rdx,$A0[1]
1231 xor $A0[0],$A0[0]
1232 add 8($tptr,$j),$A0[1]
1233 adc \$0,$A0[0]
1235 add %rax,$A0[1] # n[1]*m0+t[1]
1237 adc %rdx,$A0[0]
1239 imulq $A0[1],$m1
1243 add $A0[1],$A1[0]
1251 xor $A0[1],$A0[1]
1252 add 16($tptr,$j),$A0[0]
1253 adc \$0,$A0[1]
1255 add %rax,$A0[0] # n[2]*m0+t[2]
1257 adc %rdx,$A0[1]
1261 add $A0[0],$A1[1]
1269 xor $A0[0],$A0[0]
1270 add 24($tptr,$j),$A0[1]
1272 adc \$0,$A0[0]
1274 add %rax,$A0[1] # n[3]*m0+t[3]
1276 adc %rdx,$A0[0]
1283 add $A0[1],$A1[0]
1291 xor $A0[1],$A0[1]
1292 add ($tptr,$j),$A0[0]
1293 adc \$0,$A0[1]
1295 add %rax,$A0[0] # n[4]*m0+t[4]
1297 adc %rdx,$A0[1]
1301 add $A0[0],$A1[1]
1309 xor $A0[0],$A0[0]
1310 add 8($tptr,$j),$A0[1]
1311 adc \$0,$A0[0]
1313 add %rax,$A0[1] # n[5]*m0+t[5]
1315 adc %rdx,$A0[0]
1320 add $A0[1],$A1[0]
1328 xor $A0[1],$A0[1]
1329 add 16($tptr,$j),$A0[0]
1330 adc \$0,$A0[1]
1332 add %rax,$A0[0] # n[6]*m0+t[6]
1334 adc %rdx,$A0[1]
1338 add $A0[0],$A1[1]
1346 xor $A0[0],$A0[0]
1347 add 24($tptr,$j),$A0[1]
1349 adc \$0,$A0[0]
1351 add %rax,$A0[1] # n[7]*m0+t[7]
1353 adc %rdx,$A0[0]
1361 add $A0[1],$A1[0]
1369 xor $A0[1],$A0[1]
1370 add ($tptr),$A0[0] # +t[8]
1371 adc \$0,$A0[1]
1373 add $topbit,$A0[0]
1374 adc \$0,$A0[1]
1379 add $A0[0],$A1[1]
1380 mov 16($tptr,$j),$A0[0] # t[0] # modsched #
1391 add $A0[1],$A1[0]
