725 __ umov(r0, v1, __ B, 3); // umov w0, v1.b[3]
726 __ fmovhid(r0, v1); // fmov x0, v1.d[1]
727 __ ld1(v31, v0, __ T2D, Address(__ post(r1, r0))); // ld1 {v31.2d, v0.2d}, [x1], x0
728 __ sve_cpy(z0, __ S, p0, v1); // mov z0.s, p0/m, s1
729 __ sve_cpy(z0, __ B, p0, 127, true); // mov z0.b, p0/m, 127
730 __ sve_cpy(z1, __ H, p0, -128, true); // mov z1.h, p0/m, -128
731 __ sve_cpy(z2, __ S, p0, 32512, true); // mov z2.s, p0/m, 32512
732 __ sve_cpy(z5, __ D, p0, -32768, false); // mov z5.d, p0/z, -32768
733 __ sve_cpy(z10, __ B, p0, -1, false); // mov z10.b, p0/z, -1
734 __ sve_cpy(z11, __ S, p0, -1, false); // mov z11.s, p0/z, -1
735 __ sve_inc(r0, __ S); // incw x0
736 __ sve_dec(r1, __ H); // dech x1
737 __ sve_lsl(z0, __ B, z1, 7); // lsl z0.b, z1.b, #7
738 __ sve_lsl(z21, __ H, z1, 15); // lsl z21.h, z1.h, #15
739 __ sve_lsl(z0, __ S, z1, 31); // lsl z0.s, z1.s, #31
740 __ sve_lsl(z0, __ D, z1, 63); // lsl z0.d, z1.d, #63
741 __ sve_lsr(z0, __ B, z1, 7); // lsr z0.b, z1.b, #7
742 __ sve_asr(z0, __ H, z11, 15); // asr z0.h, z11.h, #15
743 __ sve_lsr(z30, __ S, z1, 31); // lsr z30.s, z1.s, #31
744 __ sve_asr(z0, __ D, z1, 63); // asr z0.d, z1.d, #63
745 __ sve_addvl(sp, r0, 31); // addvl sp, x0, #31
746 __ sve_addpl(r1, sp, -32); // addpl x1, sp, -32
747 __ sve_cntp(r8, __ B, p0, p1); // cntp x8, p0, p1.b
748 __ sve_dup(z0, __ B, 127); // dup z0.b, 127
749 __ sve_dup(z1, __ H, -128); // dup z1.h, -128
750 __ sve_dup(z2, __ S, 32512); // dup z2.s, 32512
751 __ sve_dup(z7, __ D, -32768); // dup z7.d, -32768
752 __ sve_dup(z10, __ B, -1); // dup z10.b, -1
753 __ sve_dup(z11, __ S, -1); // dup z11.s, -1
754 __ sve_ld1b(z0, __ B, p0, Address(sp)); // ld1b {z0.b}, p0/z, [sp]
755 __ sve_ld1b(z0, __ H, p1, Address(sp)); // ld1b {z0.h}, p1/z, [sp]
756 __ sve_ld1b(z0, __ S, p2, Address(sp, r8)); // ld1b {z0.s}, p2/z, [sp, x8]
757 __ sve_ld1b(z0, __ D, p3, Address(sp, 7)); // ld1b {z0.d}, p3/z, [sp, #7, MUL VL]
758 __ sve_ld1h(z10, __ H, p1, Address(sp, -8)); // ld1h {z10.h}, p1/z, [sp, #-8, MUL VL]
759 __ sve_ld1w(z20, __ S, p2, Address(r0, 7)); // ld1w {z20.s}, p2/z, [x0, #7, MUL VL]
760 __ sve_ld1b(z30, __ B, p3, Address(sp, r8)); // ld1b {z30.b}, p3/z, [sp, x8]
761 __ sve_ld1w(z0, __ S, p4, Address(sp, r28)); // ld1w {z0.s}, p4/z, [sp, x28, LSL #2]
762 __ sve_ld1d(z11, __ D, p5, Address(r0, r1)); // ld1d {z11.d}, p5/z, [x0, x1, LSL #3]
763 __ sve_st1b(z22, __ B, p6, Address(sp)); // st1b {z22.b}, p6, [sp]
764 __ sve_st1b(z31, __ B, p7, Address(sp, -8)); // st1b {z31.b}, p7, [sp, #-8, MUL VL]
819 __ sve_scvtf(z6, __ H, p3, z1, __ D); // scvtf z6.h, p3/m, z1.d
820 __ sve_scvtf(z6, __ H, p3, z1, __ H); // scvtf z6.h, p3/m, z1.h
821 __ sve_fcvt(z5, __ D, p3, z4, __ S); // fcvt z5.d, p3/m, z4.s
822 __ sve_fcvt(z1, __ S, p3, z0, __ D); // fcvt z1.s, p3/m, z0.d
823 __ sve_fcvtzs(z19, __ D, p2, z1, __ D); // fcvtzs z19.d, p2/m, z1.d
824 __ sve_fcvtzs(z9, __ S, p1, z8, __ S); // fcvtzs z9.s, p1/m, z8.s
825 __ sve_fcvtzs(z1, __ S, p2, z0, __ D); // fcvtzs z1.s, p2/m, z0.d
826 __ sve_fcvtzs(z1, __ D, p3, z0, __ S); // fcvtzs z1.d, p3/m, z0.s
827 __ sve_fcvtzs(z1, __ S, p4, z18, __ H); // fcvtzs z1.s, p4/m, z18.h
828 __ sve_lasta(r0, __ B, p0, z15); // lasta w0, p0, z15.b
829 __ sve_lastb(r1, __ B, p1, z16); // lastb w1, p1, z16.b
830 __ sve_lasta(v0, __ B, p0, z15); // lasta b0, p0, z15.b
831 __ sve_lastb(v1, __ B, p1, z16); // lastb b1, p1, z16.b
832 __ sve_index(z6, __ S, 1, 1); // index z6.s, #1, #1
833 __ sve_cpy(z7, __ H, p3, r5); // cpy z7.h, p3/m, w5
834 __ sve_tbl(z16, __ S, z17, z18); // tbl z16.s, {z17.s}, z18.s
835 __ sve_ld1w_gather(z15, p0, r5, z16); // ld1w {z15.s}, p0/z, [x5, z16.s, uxtw #2]
836 __ sve_ld1d_gather(z15, p0, r5, z16); // ld1d {z15.d}, p0/z, [x5, z16.d, uxtw #3]
837 __ sve_st1w_scatter(z15, p0, r5, z16); // st1w {z15.s}, p0, [x5, z16.s, uxtw #2]
838 __ sve_st1d_scatter(z15, p0, r5, z16); // st1d {z15.d}, p0, [x5, z16.d, uxtw #3]
839
840 // FloatImmediateOp
841 __ fmovd(v0, 2.0); // fmov d0, #2.0
842 __ fmovd(v0, 2.125); // fmov d0, #2.125
843 __ fmovd(v0, 4.0); // fmov d0, #4.0
844 __ fmovd(v0, 4.25); // fmov d0, #4.25
845 __ fmovd(v0, 8.0); // fmov d0, #8.0
846 __ fmovd(v0, 8.5); // fmov d0, #8.5
847 __ fmovd(v0, 16.0); // fmov d0, #16.0
848 __ fmovd(v0, 17.0); // fmov d0, #17.0
849 __ fmovd(v0, 0.125); // fmov d0, #0.125
850 __ fmovd(v0, 0.1328125); // fmov d0, #0.1328125
851 __ fmovd(v0, 0.25); // fmov d0, #0.25
852 __ fmovd(v0, 0.265625); // fmov d0, #0.265625
853 __ fmovd(v0, 0.5); // fmov d0, #0.5
854 __ fmovd(v0, 0.53125); // fmov d0, #0.53125
855 __ fmovd(v0, 1.0); // fmov d0, #1.0
856 __ fmovd(v0, 1.0625); // fmov d0, #1.0625
857 __ fmovd(v0, -2.0); // fmov d0, #-2.0
858 __ fmovd(v0, -2.125); // fmov d0, #-2.125
962 // SHA3SIMDOp
963 __ bcax(v7, __ T16B, v4, v7, v15); // bcax v7.16B, v4.16B, v7.16B, v15.16B
964 __ eor3(v9, __ T16B, v22, v8, v2); // eor3 v9.16B, v22.16B, v8.16B, v2.16B
965 __ rax1(v27, __ T2D, v20, v30); // rax1 v27.2D, v20.2D, v30.2D
966 __ xar(v5, __ T2D, v26, v0, 34); // xar v5.2D, v26.2D, v0.2D, #34
967
968 // SHA512SIMDOp
969 __ sha512h(v14, __ T2D, v3, v25); // sha512h q14, q3, v25.2D
970 __ sha512h2(v8, __ T2D, v27, v21); // sha512h2 q8, q27, v21.2D
971 __ sha512su0(v26, __ T2D, v26); // sha512su0 v26.2D, v26.2D
972 __ sha512su1(v24, __ T2D, v22, v0); // sha512su1 v24.2D, v22.2D, v0.2D
973
974 // SVEVectorOp
975 __ sve_add(z4, __ B, z6, z17); // add z4.b, z6.b, z17.b
976 __ sve_sub(z3, __ H, z15, z1); // sub z3.h, z15.h, z1.h
977 __ sve_fadd(z6, __ D, z5, z9); // fadd z6.d, z5.d, z9.d
978 __ sve_fmul(z7, __ D, z20, z22); // fmul z7.d, z20.d, z22.d
979 __ sve_fsub(z5, __ D, z10, z8); // fsub z5.d, z10.d, z8.d
980 __ sve_abs(z30, __ B, p1, z17); // abs z30.b, p1/m, z17.b
981 __ sve_add(z11, __ B, p7, z28); // add z11.b, p7/m, z11.b, z28.b
982 __ sve_asr(z26, __ H, p5, z28); // asr z26.h, p5/m, z26.h, z28.h
983 __ sve_cnt(z13, __ D, p7, z16); // cnt z13.d, p7/m, z16.d
984 __ sve_lsl(z5, __ H, p0, z13); // lsl z5.h, p0/m, z5.h, z13.h
985 __ sve_lsr(z15, __ S, p2, z26); // lsr z15.s, p2/m, z15.s, z26.s
986 __ sve_mul(z11, __ S, p1, z22); // mul z11.s, p1/m, z11.s, z22.s
987 __ sve_neg(z4, __ S, p0, z19); // neg z4.s, p0/m, z19.s
988 __ sve_not(z17, __ H, p3, z14); // not z17.h, p3/m, z14.h
989 __ sve_smax(z2, __ S, p4, z3); // smax z2.s, p4/m, z2.s, z3.s
990 __ sve_smin(z23, __ B, p1, z6); // smin z23.b, p1/m, z23.b, z6.b
991 __ sve_sub(z17, __ S, p3, z27); // sub z17.s, p3/m, z17.s, z27.s
992 __ sve_fabs(z16, __ D, p1, z2); // fabs z16.d, p1/m, z2.d
993 __ sve_fadd(z3, __ D, p1, z6); // fadd z3.d, p1/m, z3.d, z6.d
994 __ sve_fdiv(z19, __ D, p3, z12); // fdiv z19.d, p3/m, z19.d, z12.d
995 __ sve_fmax(z8, __ D, p6, z19); // fmax z8.d, p6/m, z8.d, z19.d
996 __ sve_fmin(z0, __ S, p2, z23); // fmin z0.s, p2/m, z0.s, z23.s
997 __ sve_fmul(z19, __ D, p7, z13); // fmul z19.d, p7/m, z19.d, z13.d
998 __ sve_fneg(z6, __ S, p0, z7); // fneg z6.s, p0/m, z7.s
999 __ sve_frintm(z17, __ S, p6, z8); // frintm z17.s, p6/m, z8.s
1000 __ sve_frintn(z22, __ D, p5, z22); // frintn z22.d, p5/m, z22.d
1001 __ sve_frintp(z2, __ D, p0, z15); // frintp z2.d, p0/m, z15.d
1002 __ sve_fsqrt(z20, __ D, p1, z4); // fsqrt z20.d, p1/m, z4.d
1003 __ sve_fsub(z7, __ D, p0, z8); // fsub z7.d, p0/m, z7.d, z8.d
1004 __ sve_fmla(z19, __ S, p5, z4, z15); // fmla z19.s, p5/m, z4.s, z15.s
1005 __ sve_fmls(z22, __ D, p2, z25, z5); // fmls z22.d, p2/m, z25.d, z5.d
1006 __ sve_fnmla(z16, __ S, p3, z22, z11); // fnmla z16.s, p3/m, z22.s, z11.s
1007 __ sve_fnmls(z13, __ D, p2, z20, z16); // fnmls z13.d, p2/m, z20.d, z16.d
1008 __ sve_mla(z15, __ H, p1, z4, z17); // mla z15.h, p1/m, z4.h, z17.h
1009 __ sve_mls(z6, __ S, p7, z4, z28); // mls z6.s, p7/m, z4.s, z28.s
1010 __ sve_and(z29, z26, z9); // and z29.d, z26.d, z9.d
1011 __ sve_eor(z2, z11, z28); // eor z2.d, z11.d, z28.d
1012 __ sve_orr(z7, z1, z26); // orr z7.d, z1.d, z26.d
1013 __ sve_bic(z17, z14, z8); // bic z17.d, z14.d, z8.d
1014 __ sve_uzp1(z21, __ S, z24, z5); // uzp1 z21.s, z24.s, z5.s
1015 __ sve_uzp2(z21, __ S, z17, z22); // uzp2 z21.s, z17.s, z22.s
1016
1017 // SVEReductionOp
1018 __ sve_andv(v29, __ B, p5, z19); // andv b29, p5, z19.b
1019 __ sve_orv(v4, __ B, p4, z23); // orv b4, p4, z23.b
1020 __ sve_eorv(v19, __ D, p1, z23); // eorv d19, p1, z23.d
1021 __ sve_smaxv(v19, __ H, p0, z8); // smaxv h19, p0, z8.h
1022 __ sve_sminv(v14, __ D, p6, z17); // sminv d14, p6, z17.d
1023 __ sve_fminv(v21, __ S, p1, z30); // fminv s21, p1, z30.s
1024 __ sve_fmaxv(v10, __ S, p5, z12); // fmaxv s10, p5, z12.s
1025 __ sve_fadda(v9, __ D, p1, z24); // fadda d9, p1, d9, z24.d
1026 __ sve_uaddv(v4, __ H, p6, z6); // uaddv d4, p6, z6.h
1027
1028 __ bind(forth);
1029
1030 /*
1031 */
1032
1033 static const unsigned int insns[] =
1034 {
1035 0x8b0d82fa, 0xcb49970c, 0xab889dfc, 0xeb9ee787,
1036 0x0b9b3ec9, 0x4b9179a3, 0x2b88474e, 0x6b8c56c0,
1037 0x8a1a51e0, 0xaa11f4ba, 0xca0281b8, 0xea918c7c,
1038 0x0a5d4a19, 0x2a4b262d, 0x4a513ca5, 0x6a9b6ae2,
1039 0x8a70b79b, 0xaaba9728, 0xca6dfe3d, 0xea627f1c,
1040 0x0aa70f53, 0x2aaa0f06, 0x4a6176a4, 0x6a604eb0,
1041 0x1105ed91, 0x3100583e, 0x5101f8bd, 0x710f0306,
1042 0x9101a1a0, 0xb10a5cc8, 0xd10810aa, 0xf10fd061,
1043 0x120cb166, 0x321764bc, 0x52174681, 0x720c0227,
1044 0x9241018e, 0xb25a2969, 0xd278b411, 0xf26aad01,
1045 0x14000000, 0x17ffffd7, 0x1400034c, 0x94000000,
1046 0x97ffffd4, 0x94000349, 0x3400000a, 0x34fffa2a,
1047 0x340068ca, 0x35000008, 0x35fff9c8, 0x35006868,
1048 0xb400000b, 0xb4fff96b, 0xb400680b, 0xb500001d,
1049 0xb5fff91d, 0xb50067bd, 0x10000013, 0x10fff8b3,
1050 0x10006753, 0x90000013, 0x36300016, 0x3637f836,
1051 0x363066d6, 0x3758000c, 0x375ff7cc, 0x3758666c,
1052 0x128313a0, 0x528a32c7, 0x7289173b, 0x92ab3acc,
1053 0xd2a0bf94, 0xf2c285e8, 0x9358722f, 0x330e652f,
1054 0x53067f3b, 0x93577c53, 0xb34a1aac, 0xd35a4016,
1055 0x13946c63, 0x93c3dbc8, 0x54000000, 0x54fff5a0,
1056 0x54006440, 0x54000001, 0x54fff541, 0x540063e1,
1057 0x54000002, 0x54fff4e2, 0x54006382, 0x54000002,
1058 0x54fff482, 0x54006322, 0x54000003, 0x54fff423,
1059 0x540062c3, 0x54000003, 0x54fff3c3, 0x54006263,
1060 0x54000004, 0x54fff364, 0x54006204, 0x54000005,
1061 0x54fff305, 0x540061a5, 0x54000006, 0x54fff2a6,
1062 0x54006146, 0x54000007, 0x54fff247, 0x540060e7,
1063 0x54000008, 0x54fff1e8, 0x54006088, 0x54000009,
1064 0x54fff189, 0x54006029, 0x5400000a, 0x54fff12a,
1065 0x54005fca, 0x5400000b, 0x54fff0cb, 0x54005f6b,
1066 0x5400000c, 0x54fff06c, 0x54005f0c, 0x5400000d,
1067 0x54fff00d, 0x54005ead, 0x5400000e, 0x54ffefae,
1068 0x54005e4e, 0x5400000f, 0x54ffef4f, 0x54005def,
1069 0xd40658e1, 0xd4014d22, 0xd4046543, 0xd4273f60,
1070 0xd44cad80, 0xd503201f, 0xd69f03e0, 0xd6bf03e0,
1071 0xd5033fdf, 0xd5033e9f, 0xd50332bf, 0xd61f0200,
1072 0xd63f0280, 0xc80a7d1b, 0xc800fea1, 0xc85f7fb1,
1073 0xc85fff9d, 0xc89ffee1, 0xc8dffe95, 0x88167e7b,
1074 0x880bfcd0, 0x885f7c11, 0x885ffd44, 0x889ffed8,
1075 0x88dffe6a, 0x48017fc5, 0x4808fe2c, 0x485f7dc9,
1076 0x485ffc27, 0x489ffe05, 0x48dffd82, 0x080a7c6c,
1077 0x081cff4e, 0x085f7d5e, 0x085ffeae, 0x089ffd2d,
1078 0x08dfff76, 0xc87f4d7c, 0xc87fcc5e, 0xc8220417,
1079 0xc82cb5f0, 0x887f55b1, 0x887ff90b, 0x88382c2d,
1080 0x883aedb5, 0xf819928b, 0xb803e21c, 0x381f713b,
1081 0x781ce322, 0xf850f044, 0xb85e129e, 0x385e92f1,
1082 0x785ff35d, 0x39801921, 0x7881318b, 0x78dce02b,
1083 0xb8829313, 0xfc45f318, 0xbc5d50af, 0xfc001375,
1084 0xbc1951b7, 0xf8008c0a, 0xb801dc03, 0x38009dca,
1085 0x781fdf3d, 0xf8570e0c, 0xb85faecc, 0x385f6d6d,
1086 0x785ebea0, 0x38804cd7, 0x789cbce3, 0x78df9c9c,
1087 0xb89eed18, 0xfc40cd6e, 0xbc5bdd93, 0xfc103c14,
1088 0xbc040c08, 0xf81a2783, 0xb81ca4eb, 0x381e855b,
1089 0x7801b4e6, 0xf853654d, 0xb85d74af, 0x384095a2,
1090 0x785ec5bc, 0x389e15a9, 0x789dc703, 0x78c06474,
1091 0xb89ff667, 0xfc57e51e, 0xbc4155f9, 0xfc05a6ee,
1092 0xbc1df408, 0xf835da2a, 0xb836d9a4, 0x3833580d,
1093 0x7826cb6c, 0xf8706900, 0xb87ae880, 0x3865db2e,
1094 0x78714889, 0x38a7789b, 0x78beca2f, 0x78f6c810,
1095 0xb8bef956, 0xfc6afabd, 0xbc734963, 0xfc3d5b8d,
1096 0xbc25fbb7, 0xf9189d05, 0xb91ecb1d, 0x39187a33,
1097 0x791f226d, 0xf95aa2f3, 0xb9587bb7, 0x395f7176,
1098 0x795d9143, 0x399e7e08, 0x799a2697, 0x79df3422,
1099 0xb99c2624, 0xfd5c2374, 0xbd5fa1d9, 0xfd1d595a,
1100 0xbd1b1869, 0x58004e3b, 0x1800000b, 0xf8945060,
1101 0xd8000000, 0xf8ae6ba0, 0xf99a0080, 0x1a070035,
1102 0x3a0700a8, 0x5a0e0367, 0x7a11009b, 0x9a000380,
1103 0xba1e030c, 0xda0f0320, 0xfa030301, 0x0b340b11,
1104 0x2b2a278d, 0xcb22aa0f, 0x6b2d29bd, 0x8b2cce8c,
1105 0xab2b877e, 0xcb21c8ee, 0xeb3ba47d, 0x3a4d400e,
1106 0x7a5132c6, 0xba5e622e, 0xfa53814c, 0x3a52d8c2,
1107 0x7a4d8924, 0xba4b3aab, 0xfa4d7882, 0x1a96804c,
1108 0x1a912618, 0x5a90b0e6, 0x5a96976b, 0x9a9db06a,
1109 0x9a9b374c, 0xda95c14f, 0xda89c6fe, 0x5ac0015e,
1110 0x5ac005fd, 0x5ac00bdd, 0x5ac012b9, 0x5ac01404,
1111 0xdac002b1, 0xdac0061d, 0xdac00a95, 0xdac00e66,
1112 0xdac0107e, 0xdac01675, 0x1ac00b0b, 0x1ace0f3b,
1113 0x1ad121c3, 0x1ad825e7, 0x1ad92a3c, 0x1adc2f42,
1114 0x9ada0b25, 0x9ad10e1b, 0x9acc22a6, 0x9acc2480,
1115 0x9adc2a3b, 0x9ad12c5c, 0x9bce7dea, 0x9b597c6e,
1116 0x1b0e166f, 0x1b1ae490, 0x9b023044, 0x9b089e3d,
1117 0x9b391083, 0x9b24c73a, 0x9bb15f40, 0x9bbcc6af,
1118 0x7ea3d55b, 0x1e3908e0, 0x1e2f18c9, 0x1e2a29fd,
1119 0x1e273a22, 0x7ef7d56b, 0x1e770ba7, 0x1e6b1b6e,
1120 0x1e78288b, 0x1e6e39ec, 0x1f1c3574, 0x1f17f98b,
1172 0x2e658c83, 0x6e6a8d28, 0x2eb88ef6, 0x6eb38e51,
1173 0x6eef8dcd, 0x0e26e4a4, 0x4e3ee7bc, 0x4e79e717,
1174 0x0e3736d5, 0x4e3b3759, 0x0e7a3738, 0x4e653483,
1175 0x0eb93717, 0x4ebc377a, 0x4ef93717, 0x2e3035ee,
1176 0x6e3736d5, 0x2e653483, 0x6e793717, 0x2eaa3528,
1177 0x6eba3738, 0x6ef53693, 0x2e313e0f, 0x6e323e30,
1178 0x2e643c62, 0x6e633c41, 0x2ea23c20, 0x6eba3f38,
1179 0x6ee63ca4, 0x2ea5e483, 0x6eade58b, 0x6ee0e7fe,
1180 0x0e3d3f9b, 0x4e2b3d49, 0x0e7b3f59, 0x4e643c62,
1181 0x0eae3dac, 0x4eb33e51, 0x4ee03ffe, 0x2e23e441,
1182 0x6e2ee5ac, 0x6e7ee7bc, 0xba5fd3e3, 0x3a5f03e5,
1183 0xfa411be4, 0x7a42cbe2, 0x93df03ff, 0xc820ffff,
1184 0x8822fc7f, 0xc8247cbf, 0x88267fff, 0x4e010fe0,
1185 0x4e081fe1, 0x4e0c1fe1, 0x4e0a1fe1, 0x4e071fe1,
1186 0x4e042c20, 0x4e062c20, 0x4e052c20, 0x4e083c20,
1187 0x0e0c3c20, 0x0e0a3c20, 0x0e073c20, 0x9eae0020,
1188 0x4cc0ac3f, 0x05a08020, 0x05104fe0, 0x05505001,
1189 0x05906fe2, 0x05d03005, 0x05101fea, 0x05901feb,
1190 0x04b0e3e0, 0x0470e7e1, 0x042f9c20, 0x043f9c35,
1191 0x047f9c20, 0x04ff9c20, 0x04299420, 0x04319160,
1192 0x0461943e, 0x04a19020, 0x042053ff, 0x047f5401,
1193 0x25208028, 0x2538cfe0, 0x2578d001, 0x25b8efe2,
1194 0x25f8f007, 0x2538dfea, 0x25b8dfeb, 0xa400a3e0,
1195 0xa420a7e0, 0xa4484be0, 0xa467afe0, 0xa4a8a7ea,
1196 0xa547a814, 0xa4084ffe, 0xa55c53e0, 0xa5e1540b,
1197 0xe400fbf6, 0xe408ffff, 0xe420e7e0, 0xe4484be0,
1198 0xe460efe0, 0xe547e400, 0xe4014be0, 0xe4a84fe0,
1199 0xe5f15000, 0x858043e0, 0x85a043ff, 0xe59f5d08,
1200 0x0420e3e9, 0x0460e3ea, 0x04a0e3eb, 0x04e0e3ec,
1201 0x25104042, 0x25104871, 0x25904861, 0x25904c92,
1202 0x05344020, 0x05744041, 0x05b44062, 0x05f44083,
1203 0x252c8840, 0x253c1420, 0x25681572, 0x25a21ce3,
1204 0x25ea1e34, 0x0522c020, 0x05e6c0a4, 0x2401a001,
1205 0x2443a051, 0x24858881, 0x24c78cd1, 0x24850891,
1206 0x24c70cc1, 0x250f9001, 0x25508051, 0x25802491,
1207 0x25df28c1, 0x25850c81, 0x251e10d1, 0x65816001,
1208 0x65c36051, 0x65854891, 0x65c74cc1, 0x05733820,
1209 0x05b238a4, 0x05f138e6, 0x0570396a, 0x65d0a001,
1210 0x65d6a443, 0x65d4a826, 0x6594ac26, 0x6554ac26,
1211 0x6556ac26, 0x6552ac26, 0x65cbac85, 0x65caac01,
1212 0x65dea833, 0x659ca509, 0x65d8a801, 0x65dcac01,
1213 0x655cb241, 0x0520a1e0, 0x0521a601, 0x052281e0,
1214 0x05238601, 0x04a14026, 0x0568aca7, 0x05b23230,
1215 0x853040af, 0xc5b040af, 0xe57080af, 0xe5b080af,
1216 0x1e601000, 0x1e603000, 0x1e621000, 0x1e623000,
1217 0x1e641000, 0x1e643000, 0x1e661000, 0x1e663000,
1218 0x1e681000, 0x1e683000, 0x1e6a1000, 0x1e6a3000,
1219 0x1e6c1000, 0x1e6c3000, 0x1e6e1000, 0x1e6e3000,
1220 0x1e701000, 0x1e703000, 0x1e721000, 0x1e723000,
1221 0x1e741000, 0x1e743000, 0x1e761000, 0x1e763000,
1222 0x1e781000, 0x1e783000, 0x1e7a1000, 0x1e7a3000,
1223 0x1e7c1000, 0x1e7c3000, 0x1e7e1000, 0x1e7e3000,
1224 0xf8208193, 0xf83101b6, 0xf83c13fe, 0xf821239a,
1225 0xf824309e, 0xf826535e, 0xf8304109, 0xf82c7280,
1226 0xf8216058, 0xf8a08309, 0xf8ba03d0, 0xf8a312ea,
1227 0xf8aa21e4, 0xf8a2310b, 0xf8aa522f, 0xf8a2418a,
1228 0xf8ac71af, 0xf8a26287, 0xf8fa8090, 0xf8e20184,
1229 0xf8f01215, 0xf8f022ab, 0xf8f7334c, 0xf8f751dc,
1230 0xf8eb4038, 0xf8ec715f, 0xf8f06047, 0xf863826d,
1231 0xf8710070, 0xf86113cb, 0xf86521e8, 0xf87d301e,
1232 0xf8745287, 0xf87742bc, 0xf87b70b9, 0xf8616217,
1233 0xb83f8185, 0xb82901fc, 0xb83d13f6, 0xb83320bf,
1234 0xb82e33f0, 0xb830529b, 0xb830416c, 0xb82973c6,
1235 0xb831639b, 0xb8be8147, 0xb8b4008a, 0xb8b81231,
1236 0xb8b623a3, 0xb8af3276, 0xb8b35056, 0xb8af4186,
1237 0xb8b071ab, 0xb8b763c1, 0xb8f38225, 0xb8e202d0,
1238 0xb8ed12aa, 0xb8fd219b, 0xb8fb3023, 0xb8ff5278,
1239 0xb8f14389, 0xb8fb70ef, 0xb8f563f7, 0xb87983e2,
1240 0xb87b0150, 0xb8771073, 0xb8702320, 0xb87a3057,
1241 0xb870508c, 0xb87c43be, 0xb87070db, 0xb86961fd,
1242 0xce273c87, 0xce080ac9, 0xce7e8e9b, 0xce808b45,
1243 0xce79806e, 0xce758768, 0xcec0835a, 0xce608ad8,
1244 0x043100c4, 0x046105e3, 0x65c900a6, 0x65d60a87,
1245 0x65c80545, 0x0416a63e, 0x04001f8b, 0x0450979a,
1246 0x04dabe0d, 0x045381a5, 0x04918b4f, 0x049006cb,
1247 0x0497a264, 0x045eadd1, 0x04881062, 0x040a04d7,
1248 0x04810f71, 0x04dca450, 0x65c084c3, 0x65cd8d93,
1249 0x65c69a68, 0x65878ae0, 0x65c29db3, 0x049da0e6,
1250 0x6582b911, 0x65c0b6d6, 0x65c1a1e2, 0x65cda494,
1251 0x65c18107, 0x65af1493, 0x65e52b36, 0x65ab4ed0,
1252 0x65f06a8d, 0x0451448f, 0x049c7c86, 0x0429335d,
1253 0x04bc3162, 0x047a3027, 0x04e831d1, 0x05a56b15,
1254 0x05b66e35, 0x041a367d, 0x041832e4, 0x04d926f3,
1255 0x04482113, 0x04ca3a2e, 0x658727d5, 0x6586358a,
1256 0x65d82709, 0x044138c4,
1257 };
1258 // END Generated code -- do not edit
1259
|
725 __ umov(r0, v1, __ B, 3); // umov w0, v1.b[3]
726 __ fmovhid(r0, v1); // fmov x0, v1.d[1]
727 __ ld1(v31, v0, __ T2D, Address(__ post(r1, r0))); // ld1 {v31.2d, v0.2d}, [x1], x0
728 __ sve_cpy(z0, __ S, p0, v1); // mov z0.s, p0/m, s1
729 __ sve_cpy(z0, __ B, p0, 127, true); // mov z0.b, p0/m, 127
730 __ sve_cpy(z1, __ H, p0, -128, true); // mov z1.h, p0/m, -128
731 __ sve_cpy(z2, __ S, p0, 32512, true); // mov z2.s, p0/m, 32512
732 __ sve_cpy(z5, __ D, p0, -32768, false); // mov z5.d, p0/z, -32768
733 __ sve_cpy(z10, __ B, p0, -1, false); // mov z10.b, p0/z, -1
734 __ sve_cpy(z11, __ S, p0, -1, false); // mov z11.s, p0/z, -1
735 __ sve_inc(r0, __ S); // incw x0
736 __ sve_dec(r1, __ H); // dech x1
737 __ sve_lsl(z0, __ B, z1, 7); // lsl z0.b, z1.b, #7
738 __ sve_lsl(z21, __ H, z1, 15); // lsl z21.h, z1.h, #15
739 __ sve_lsl(z0, __ S, z1, 31); // lsl z0.s, z1.s, #31
740 __ sve_lsl(z0, __ D, z1, 63); // lsl z0.d, z1.d, #63
741 __ sve_lsr(z0, __ B, z1, 7); // lsr z0.b, z1.b, #7
742 __ sve_asr(z0, __ H, z11, 15); // asr z0.h, z11.h, #15
743 __ sve_lsr(z30, __ S, z1, 31); // lsr z30.s, z1.s, #31
744 __ sve_asr(z0, __ D, z1, 63); // asr z0.d, z1.d, #63
745 __ sve_lsl(z0, __ B, p0, 0); // lsl z0.b, p0/m, z0.b, #0
746 __ sve_lsl(z0, __ B, p0, 5); // lsl z0.b, p0/m, z0.b, #5
747 __ sve_lsl(z1, __ H, p1, 15); // lsl z1.h, p1/m, z1.h, #15
748 __ sve_lsl(z2, __ S, p2, 31); // lsl z2.s, p2/m, z2.s, #31
749 __ sve_lsl(z3, __ D, p3, 63); // lsl z3.d, p3/m, z3.d, #63
750 __ sve_lsr(z0, __ B, p0, 1); // lsr z0.b, p0/m, z0.b, #1
751 __ sve_lsr(z0, __ B, p0, 8); // lsr z0.b, p0/m, z0.b, #8
752 __ sve_lsr(z1, __ H, p1, 15); // lsr z1.h, p1/m, z1.h, #15
753 __ sve_lsr(z2, __ S, p2, 7); // lsr z2.s, p2/m, z2.s, #7
754 __ sve_lsr(z2, __ S, p2, 31); // lsr z2.s, p2/m, z2.s, #31
755 __ sve_lsr(z3, __ D, p3, 63); // lsr z3.d, p3/m, z3.d, #63
756 __ sve_asr(z0, __ B, p0, 1); // asr z0.b, p0/m, z0.b, #1
757 __ sve_asr(z0, __ B, p0, 7); // asr z0.b, p0/m, z0.b, #7
758 __ sve_asr(z1, __ H, p1, 5); // asr z1.h, p1/m, z1.h, #5
759 __ sve_asr(z1, __ H, p1, 15); // asr z1.h, p1/m, z1.h, #15
760 __ sve_asr(z2, __ S, p2, 31); // asr z2.s, p2/m, z2.s, #31
761 __ sve_asr(z3, __ D, p3, 63); // asr z3.d, p3/m, z3.d, #63
762 __ sve_addvl(sp, r0, 31); // addvl sp, x0, #31
763 __ sve_addpl(r1, sp, -32); // addpl x1, sp, -32
764 __ sve_cntp(r8, __ B, p0, p1); // cntp x8, p0, p1.b
765 __ sve_dup(z0, __ B, 127); // dup z0.b, 127
766 __ sve_dup(z1, __ H, -128); // dup z1.h, -128
767 __ sve_dup(z2, __ S, 32512); // dup z2.s, 32512
768 __ sve_dup(z7, __ D, -32768); // dup z7.d, -32768
769 __ sve_dup(z10, __ B, -1); // dup z10.b, -1
770 __ sve_dup(z11, __ S, -1); // dup z11.s, -1
771 __ sve_ld1b(z0, __ B, p0, Address(sp)); // ld1b {z0.b}, p0/z, [sp]
772 __ sve_ld1b(z0, __ H, p1, Address(sp)); // ld1b {z0.h}, p1/z, [sp]
773 __ sve_ld1b(z0, __ S, p2, Address(sp, r8)); // ld1b {z0.s}, p2/z, [sp, x8]
774 __ sve_ld1b(z0, __ D, p3, Address(sp, 7)); // ld1b {z0.d}, p3/z, [sp, #7, MUL VL]
775 __ sve_ld1h(z10, __ H, p1, Address(sp, -8)); // ld1h {z10.h}, p1/z, [sp, #-8, MUL VL]
776 __ sve_ld1w(z20, __ S, p2, Address(r0, 7)); // ld1w {z20.s}, p2/z, [x0, #7, MUL VL]
777 __ sve_ld1b(z30, __ B, p3, Address(sp, r8)); // ld1b {z30.b}, p3/z, [sp, x8]
778 __ sve_ld1w(z0, __ S, p4, Address(sp, r28)); // ld1w {z0.s}, p4/z, [sp, x28, LSL #2]
779 __ sve_ld1d(z11, __ D, p5, Address(r0, r1)); // ld1d {z11.d}, p5/z, [x0, x1, LSL #3]
780 __ sve_st1b(z22, __ B, p6, Address(sp)); // st1b {z22.b}, p6, [sp]
781 __ sve_st1b(z31, __ B, p7, Address(sp, -8)); // st1b {z31.b}, p7, [sp, #-8, MUL VL]
836 __ sve_scvtf(z6, __ H, p3, z1, __ D); // scvtf z6.h, p3/m, z1.d
837 __ sve_scvtf(z6, __ H, p3, z1, __ H); // scvtf z6.h, p3/m, z1.h
838 __ sve_fcvt(z5, __ D, p3, z4, __ S); // fcvt z5.d, p3/m, z4.s
839 __ sve_fcvt(z1, __ S, p3, z0, __ D); // fcvt z1.s, p3/m, z0.d
840 __ sve_fcvtzs(z19, __ D, p2, z1, __ D); // fcvtzs z19.d, p2/m, z1.d
841 __ sve_fcvtzs(z9, __ S, p1, z8, __ S); // fcvtzs z9.s, p1/m, z8.s
842 __ sve_fcvtzs(z1, __ S, p2, z0, __ D); // fcvtzs z1.s, p2/m, z0.d
843 __ sve_fcvtzs(z1, __ D, p3, z0, __ S); // fcvtzs z1.d, p3/m, z0.s
844 __ sve_fcvtzs(z1, __ S, p4, z18, __ H); // fcvtzs z1.s, p4/m, z18.h
845 __ sve_lasta(r0, __ B, p0, z15); // lasta w0, p0, z15.b
846 __ sve_lastb(r1, __ B, p1, z16); // lastb w1, p1, z16.b
847 __ sve_lasta(v0, __ B, p0, z15); // lasta b0, p0, z15.b
848 __ sve_lastb(v1, __ B, p1, z16); // lastb b1, p1, z16.b
849 __ sve_index(z6, __ S, 1, 1); // index z6.s, #1, #1
850 __ sve_cpy(z7, __ H, p3, r5); // cpy z7.h, p3/m, w5
851 __ sve_tbl(z16, __ S, z17, z18); // tbl z16.s, {z17.s}, z18.s
852 __ sve_ld1w_gather(z15, p0, r5, z16); // ld1w {z15.s}, p0/z, [x5, z16.s, uxtw #2]
853 __ sve_ld1d_gather(z15, p0, r5, z16); // ld1d {z15.d}, p0/z, [x5, z16.d, uxtw #3]
854 __ sve_st1w_scatter(z15, p0, r5, z16); // st1w {z15.s}, p0, [x5, z16.s, uxtw #2]
855 __ sve_st1d_scatter(z15, p0, r5, z16); // st1d {z15.d}, p0, [x5, z16.d, uxtw #3]
856 __ sve_and(p0, p1, p2, p3); // and p0.b, p1/z, p2.b, p3.b
857 __ sve_ands(p4, p5, p6, p0); // ands p4.b, p5/z, p6.b, p0.b
858 __ sve_eor(p0, p1, p2, p3); // eor p0.b, p1/z, p2.b, p3.b
859 __ sve_eors(p5, p6, p0, p1); // eors p5.b, p6/z, p0.b, p1.b
860 __ sve_orr(p0, p1, p2, p3); // orr p0.b, p1/z, p2.b, p3.b
861 __ sve_orrs(p9, p1, p4, p5); // orrs p9.b, p1/z, p4.b, p5.b
862 __ sve_bic(p10, p7, p9, p11); // bic p10.b, p7/z, p9.b, p11.b
863 __ sve_ptest(p7, p1); // ptest p7, p1.b
864 __ sve_ptrue(p1, __ B); // ptrue p1.b
865 __ sve_ptrue(p2, __ H); // ptrue p2.h
866 __ sve_ptrue(p3, __ S); // ptrue p3.s
867 __ sve_ptrue(p4, __ D); // ptrue p4.d
868 __ sve_pfalse(p7); // pfalse p7.b
869 __ sve_uzp1(p0, __ B, p0, p1); // uzp1 p0.b, p0.b, p1.b
870 __ sve_uzp1(p0, __ H, p0, p1); // uzp1 p0.h, p0.h, p1.h
871 __ sve_uzp1(p0, __ S, p0, p1); // uzp1 p0.s, p0.s, p1.s
872 __ sve_uzp1(p0, __ D, p0, p1); // uzp1 p0.d, p0.d, p1.d
873 __ sve_uzp2(p0, __ B, p0, p1); // uzp2 p0.b, p0.b, p1.b
874 __ sve_uzp2(p0, __ H, p0, p1); // uzp2 p0.h, p0.h, p1.h
875 __ sve_uzp2(p0, __ S, p0, p1); // uzp2 p0.s, p0.s, p1.s
876 __ sve_uzp2(p0, __ D, p0, p1); // uzp2 p0.d, p0.d, p1.d
877 __ sve_punpklo(p1, p0); // punpklo p1.h, p0.b
878 __ sve_punpkhi(p1, p0); // punpkhi p1.h, p0.b
879
880 // FloatImmediateOp
881 __ fmovd(v0, 2.0); // fmov d0, #2.0
882 __ fmovd(v0, 2.125); // fmov d0, #2.125
883 __ fmovd(v0, 4.0); // fmov d0, #4.0
884 __ fmovd(v0, 4.25); // fmov d0, #4.25
885 __ fmovd(v0, 8.0); // fmov d0, #8.0
886 __ fmovd(v0, 8.5); // fmov d0, #8.5
887 __ fmovd(v0, 16.0); // fmov d0, #16.0
888 __ fmovd(v0, 17.0); // fmov d0, #17.0
889 __ fmovd(v0, 0.125); // fmov d0, #0.125
890 __ fmovd(v0, 0.1328125); // fmov d0, #0.1328125
891 __ fmovd(v0, 0.25); // fmov d0, #0.25
892 __ fmovd(v0, 0.265625); // fmov d0, #0.265625
893 __ fmovd(v0, 0.5); // fmov d0, #0.5
894 __ fmovd(v0, 0.53125); // fmov d0, #0.53125
895 __ fmovd(v0, 1.0); // fmov d0, #1.0
896 __ fmovd(v0, 1.0625); // fmov d0, #1.0625
897 __ fmovd(v0, -2.0); // fmov d0, #-2.0
898 __ fmovd(v0, -2.125); // fmov d0, #-2.125
1002 // SHA3SIMDOp
1003 __ bcax(v7, __ T16B, v4, v7, v15); // bcax v7.16B, v4.16B, v7.16B, v15.16B
1004 __ eor3(v9, __ T16B, v22, v8, v2); // eor3 v9.16B, v22.16B, v8.16B, v2.16B
1005 __ rax1(v27, __ T2D, v20, v30); // rax1 v27.2D, v20.2D, v30.2D
1006 __ xar(v5, __ T2D, v26, v0, 34); // xar v5.2D, v26.2D, v0.2D, #34
1007
1008 // SHA512SIMDOp
1009 __ sha512h(v14, __ T2D, v3, v25); // sha512h q14, q3, v25.2D
1010 __ sha512h2(v8, __ T2D, v27, v21); // sha512h2 q8, q27, v21.2D
1011 __ sha512su0(v26, __ T2D, v26); // sha512su0 v26.2D, v26.2D
1012 __ sha512su1(v24, __ T2D, v22, v0); // sha512su1 v24.2D, v22.2D, v0.2D
1013
1014 // SVEVectorOp
1015 __ sve_add(z4, __ B, z6, z17); // add z4.b, z6.b, z17.b
1016 __ sve_sub(z3, __ H, z15, z1); // sub z3.h, z15.h, z1.h
1017 __ sve_fadd(z6, __ D, z5, z9); // fadd z6.d, z5.d, z9.d
1018 __ sve_fmul(z7, __ D, z20, z22); // fmul z7.d, z20.d, z22.d
1019 __ sve_fsub(z5, __ D, z10, z8); // fsub z5.d, z10.d, z8.d
1020 __ sve_abs(z30, __ B, p1, z17); // abs z30.b, p1/m, z17.b
1021 __ sve_add(z11, __ B, p7, z28); // add z11.b, p7/m, z11.b, z28.b
1022 __ sve_and(z26, __ H, p5, z28); // and z26.h, p5/m, z26.h, z28.h
1023 __ sve_asr(z13, __ D, p7, z16); // asr z13.d, p7/m, z13.d, z16.d
1024 __ sve_cnt(z5, __ H, p0, z13); // cnt z5.h, p0/m, z13.h
1025 __ sve_eor(z15, __ S, p2, z26); // eor z15.s, p2/m, z15.s, z26.s
1026 __ sve_lsl(z11, __ S, p1, z22); // lsl z11.s, p1/m, z11.s, z22.s
1027 __ sve_lsr(z4, __ S, p0, z19); // lsr z4.s, p0/m, z4.s, z19.s
1028 __ sve_mul(z17, __ H, p3, z14); // mul z17.h, p3/m, z17.h, z14.h
1029 __ sve_neg(z2, __ S, p4, z3); // neg z2.s, p4/m, z3.s
1030 __ sve_not(z23, __ B, p1, z6); // not z23.b, p1/m, z6.b
1031 __ sve_orr(z17, __ S, p3, z27); // orr z17.s, p3/m, z17.s, z27.s
1032 __ sve_smax(z16, __ D, p1, z2); // smax z16.d, p1/m, z16.d, z2.d
1033 __ sve_smin(z3, __ S, p1, z6); // smin z3.s, p1/m, z3.s, z6.s
1034 __ sve_sub(z19, __ S, p3, z12); // sub z19.s, p3/m, z19.s, z12.s
1035 __ sve_fabs(z8, __ D, p6, z19); // fabs z8.d, p6/m, z19.d
1036 __ sve_fadd(z0, __ S, p2, z23); // fadd z0.s, p2/m, z0.s, z23.s
1037 __ sve_fdiv(z19, __ D, p7, z13); // fdiv z19.d, p7/m, z19.d, z13.d
1038 __ sve_fmax(z6, __ S, p0, z7); // fmax z6.s, p0/m, z6.s, z7.s
1039 __ sve_fmin(z17, __ S, p6, z8); // fmin z17.s, p6/m, z17.s, z8.s
1040 __ sve_fmul(z22, __ D, p5, z22); // fmul z22.d, p5/m, z22.d, z22.d
1041 __ sve_fneg(z2, __ D, p0, z15); // fneg z2.d, p0/m, z15.d
1042 __ sve_frintm(z20, __ D, p1, z4); // frintm z20.d, p1/m, z4.d
1043 __ sve_frintn(z7, __ D, p0, z8); // frintn z7.d, p0/m, z8.d
1044 __ sve_frintp(z19, __ D, p5, z4); // frintp z19.d, p5/m, z4.d
1045 __ sve_fsqrt(z9, __ D, p5, z11); // fsqrt z9.d, p5/m, z11.d
1046 __ sve_fsub(z5, __ S, p7, z16); // fsub z5.s, p7/m, z5.s, z16.s
1047 __ sve_fmad(z22, __ S, p3, z1, z13); // fmad z22.s, p3/m, z1.s, z13.s
1048 __ sve_fmla(z20, __ S, p4, z25, z15); // fmla z20.s, p4/m, z25.s, z15.s
1049 __ sve_fmls(z4, __ D, p4, z8, z6); // fmls z4.d, p4/m, z8.d, z6.d
1050 __ sve_fnmla(z4, __ D, p7, z16, z29); // fnmla z4.d, p7/m, z16.d, z29.d
1051 __ sve_fnmls(z9, __ D, p3, z2, z11); // fnmls z9.d, p3/m, z2.d, z11.d
1052 __ sve_mla(z3, __ S, p1, z1, z26); // mla z3.s, p1/m, z1.s, z26.s
1053 __ sve_mls(z17, __ S, p3, z8, z17); // mls z17.s, p3/m, z8.s, z17.s
1054 __ sve_and(z24, z5, z19); // and z24.d, z5.d, z19.d
1055 __ sve_eor(z17, z22, z16); // eor z17.d, z22.d, z16.d
1056 __ sve_orr(z20, z19, z0); // orr z20.d, z19.d, z0.d
1057 __ sve_bic(z17, z23, z4); // bic z17.d, z23.d, z4.d
1058 __ sve_uzp1(z4, __ S, z23, z25); // uzp1 z4.s, z23.s, z25.s
1059 __ sve_uzp2(z2, __ H, z8, z8); // uzp2 z2.h, z8.h, z8.h
1060
1061 // SVEReductionOp
1062 __ sve_andv(v24, __ S, p4, z30); // andv s24, p4, z30.s
1063 __ sve_orv(v4, __ H, p7, z1); // orv h4, p7, z1.h
1064 __ sve_eorv(v19, __ H, p3, z0); // eorv h19, p3, z0.h
1065 __ sve_smaxv(v7, __ B, p6, z17); // smaxv b7, p6, z17.b
1066 __ sve_sminv(v27, __ D, p1, z9); // sminv d27, p1, z9.d
1067 __ sve_fminv(v23, __ D, p3, z16); // fminv d23, p3, z16.d
1068 __ sve_fmaxv(v22, __ D, p5, z20); // fmaxv d22, p5, z20.d
1069 __ sve_fadda(v28, __ D, p2, z13); // fadda d28, p2, d28, z13.d
1070 __ sve_uaddv(v7, __ H, p5, z28); // uaddv d7, p5, z28.h
1071
1072 __ bind(forth);
1073
1074 /*
1075 */
1076
1077 static const unsigned int insns[] =
1078 {
1079 0x8b0d82fa, 0xcb49970c, 0xab889dfc, 0xeb9ee787,
1080 0x0b9b3ec9, 0x4b9179a3, 0x2b88474e, 0x6b8c56c0,
1081 0x8a1a51e0, 0xaa11f4ba, 0xca0281b8, 0xea918c7c,
1082 0x0a5d4a19, 0x2a4b262d, 0x4a513ca5, 0x6a9b6ae2,
1083 0x8a70b79b, 0xaaba9728, 0xca6dfe3d, 0xea627f1c,
1084 0x0aa70f53, 0x2aaa0f06, 0x4a6176a4, 0x6a604eb0,
1085 0x1105ed91, 0x3100583e, 0x5101f8bd, 0x710f0306,
1086 0x9101a1a0, 0xb10a5cc8, 0xd10810aa, 0xf10fd061,
1087 0x120cb166, 0x321764bc, 0x52174681, 0x720c0227,
1088 0x9241018e, 0xb25a2969, 0xd278b411, 0xf26aad01,
1089 0x14000000, 0x17ffffd7, 0x14000378, 0x94000000,
1090 0x97ffffd4, 0x94000375, 0x3400000a, 0x34fffa2a,
1091 0x34006e4a, 0x35000008, 0x35fff9c8, 0x35006de8,
1092 0xb400000b, 0xb4fff96b, 0xb4006d8b, 0xb500001d,
1093 0xb5fff91d, 0xb5006d3d, 0x10000013, 0x10fff8b3,
1094 0x10006cd3, 0x90000013, 0x36300016, 0x3637f836,
1095 0x36306c56, 0x3758000c, 0x375ff7cc, 0x37586bec,
1096 0x128313a0, 0x528a32c7, 0x7289173b, 0x92ab3acc,
1097 0xd2a0bf94, 0xf2c285e8, 0x9358722f, 0x330e652f,
1098 0x53067f3b, 0x93577c53, 0xb34a1aac, 0xd35a4016,
1099 0x13946c63, 0x93c3dbc8, 0x54000000, 0x54fff5a0,
1100 0x540069c0, 0x54000001, 0x54fff541, 0x54006961,
1101 0x54000002, 0x54fff4e2, 0x54006902, 0x54000002,
1102 0x54fff482, 0x540068a2, 0x54000003, 0x54fff423,
1103 0x54006843, 0x54000003, 0x54fff3c3, 0x540067e3,
1104 0x54000004, 0x54fff364, 0x54006784, 0x54000005,
1105 0x54fff305, 0x54006725, 0x54000006, 0x54fff2a6,
1106 0x540066c6, 0x54000007, 0x54fff247, 0x54006667,
1107 0x54000008, 0x54fff1e8, 0x54006608, 0x54000009,
1108 0x54fff189, 0x540065a9, 0x5400000a, 0x54fff12a,
1109 0x5400654a, 0x5400000b, 0x54fff0cb, 0x540064eb,
1110 0x5400000c, 0x54fff06c, 0x5400648c, 0x5400000d,
1111 0x54fff00d, 0x5400642d, 0x5400000e, 0x54ffefae,
1112 0x540063ce, 0x5400000f, 0x54ffef4f, 0x5400636f,
1113 0xd40658e1, 0xd4014d22, 0xd4046543, 0xd4273f60,
1114 0xd44cad80, 0xd503201f, 0xd69f03e0, 0xd6bf03e0,
1115 0xd5033fdf, 0xd5033e9f, 0xd50332bf, 0xd61f0200,
1116 0xd63f0280, 0xc80a7d1b, 0xc800fea1, 0xc85f7fb1,
1117 0xc85fff9d, 0xc89ffee1, 0xc8dffe95, 0x88167e7b,
1118 0x880bfcd0, 0x885f7c11, 0x885ffd44, 0x889ffed8,
1119 0x88dffe6a, 0x48017fc5, 0x4808fe2c, 0x485f7dc9,
1120 0x485ffc27, 0x489ffe05, 0x48dffd82, 0x080a7c6c,
1121 0x081cff4e, 0x085f7d5e, 0x085ffeae, 0x089ffd2d,
1122 0x08dfff76, 0xc87f4d7c, 0xc87fcc5e, 0xc8220417,
1123 0xc82cb5f0, 0x887f55b1, 0x887ff90b, 0x88382c2d,
1124 0x883aedb5, 0xf819928b, 0xb803e21c, 0x381f713b,
1125 0x781ce322, 0xf850f044, 0xb85e129e, 0x385e92f1,
1126 0x785ff35d, 0x39801921, 0x7881318b, 0x78dce02b,
1127 0xb8829313, 0xfc45f318, 0xbc5d50af, 0xfc001375,
1128 0xbc1951b7, 0xf8008c0a, 0xb801dc03, 0x38009dca,
1129 0x781fdf3d, 0xf8570e0c, 0xb85faecc, 0x385f6d6d,
1130 0x785ebea0, 0x38804cd7, 0x789cbce3, 0x78df9c9c,
1131 0xb89eed18, 0xfc40cd6e, 0xbc5bdd93, 0xfc103c14,
1132 0xbc040c08, 0xf81a2783, 0xb81ca4eb, 0x381e855b,
1133 0x7801b4e6, 0xf853654d, 0xb85d74af, 0x384095a2,
1134 0x785ec5bc, 0x389e15a9, 0x789dc703, 0x78c06474,
1135 0xb89ff667, 0xfc57e51e, 0xbc4155f9, 0xfc05a6ee,
1136 0xbc1df408, 0xf835da2a, 0xb836d9a4, 0x3833580d,
1137 0x7826cb6c, 0xf8706900, 0xb87ae880, 0x3865db2e,
1138 0x78714889, 0x38a7789b, 0x78beca2f, 0x78f6c810,
1139 0xb8bef956, 0xfc6afabd, 0xbc734963, 0xfc3d5b8d,
1140 0xbc25fbb7, 0xf9189d05, 0xb91ecb1d, 0x39187a33,
1141 0x791f226d, 0xf95aa2f3, 0xb9587bb7, 0x395f7176,
1142 0x795d9143, 0x399e7e08, 0x799a2697, 0x79df3422,
1143 0xb99c2624, 0xfd5c2374, 0xbd5fa1d9, 0xfd1d595a,
1144 0xbd1b1869, 0x580053bb, 0x1800000b, 0xf8945060,
1145 0xd8000000, 0xf8ae6ba0, 0xf99a0080, 0x1a070035,
1146 0x3a0700a8, 0x5a0e0367, 0x7a11009b, 0x9a000380,
1147 0xba1e030c, 0xda0f0320, 0xfa030301, 0x0b340b11,
1148 0x2b2a278d, 0xcb22aa0f, 0x6b2d29bd, 0x8b2cce8c,
1149 0xab2b877e, 0xcb21c8ee, 0xeb3ba47d, 0x3a4d400e,
1150 0x7a5132c6, 0xba5e622e, 0xfa53814c, 0x3a52d8c2,
1151 0x7a4d8924, 0xba4b3aab, 0xfa4d7882, 0x1a96804c,
1152 0x1a912618, 0x5a90b0e6, 0x5a96976b, 0x9a9db06a,
1153 0x9a9b374c, 0xda95c14f, 0xda89c6fe, 0x5ac0015e,
1154 0x5ac005fd, 0x5ac00bdd, 0x5ac012b9, 0x5ac01404,
1155 0xdac002b1, 0xdac0061d, 0xdac00a95, 0xdac00e66,
1156 0xdac0107e, 0xdac01675, 0x1ac00b0b, 0x1ace0f3b,
1157 0x1ad121c3, 0x1ad825e7, 0x1ad92a3c, 0x1adc2f42,
1158 0x9ada0b25, 0x9ad10e1b, 0x9acc22a6, 0x9acc2480,
1159 0x9adc2a3b, 0x9ad12c5c, 0x9bce7dea, 0x9b597c6e,
1160 0x1b0e166f, 0x1b1ae490, 0x9b023044, 0x9b089e3d,
1161 0x9b391083, 0x9b24c73a, 0x9bb15f40, 0x9bbcc6af,
1162 0x7ea3d55b, 0x1e3908e0, 0x1e2f18c9, 0x1e2a29fd,
1163 0x1e273a22, 0x7ef7d56b, 0x1e770ba7, 0x1e6b1b6e,
1164 0x1e78288b, 0x1e6e39ec, 0x1f1c3574, 0x1f17f98b,
1216 0x2e658c83, 0x6e6a8d28, 0x2eb88ef6, 0x6eb38e51,
1217 0x6eef8dcd, 0x0e26e4a4, 0x4e3ee7bc, 0x4e79e717,
1218 0x0e3736d5, 0x4e3b3759, 0x0e7a3738, 0x4e653483,
1219 0x0eb93717, 0x4ebc377a, 0x4ef93717, 0x2e3035ee,
1220 0x6e3736d5, 0x2e653483, 0x6e793717, 0x2eaa3528,
1221 0x6eba3738, 0x6ef53693, 0x2e313e0f, 0x6e323e30,
1222 0x2e643c62, 0x6e633c41, 0x2ea23c20, 0x6eba3f38,
1223 0x6ee63ca4, 0x2ea5e483, 0x6eade58b, 0x6ee0e7fe,
1224 0x0e3d3f9b, 0x4e2b3d49, 0x0e7b3f59, 0x4e643c62,
1225 0x0eae3dac, 0x4eb33e51, 0x4ee03ffe, 0x2e23e441,
1226 0x6e2ee5ac, 0x6e7ee7bc, 0xba5fd3e3, 0x3a5f03e5,
1227 0xfa411be4, 0x7a42cbe2, 0x93df03ff, 0xc820ffff,
1228 0x8822fc7f, 0xc8247cbf, 0x88267fff, 0x4e010fe0,
1229 0x4e081fe1, 0x4e0c1fe1, 0x4e0a1fe1, 0x4e071fe1,
1230 0x4e042c20, 0x4e062c20, 0x4e052c20, 0x4e083c20,
1231 0x0e0c3c20, 0x0e0a3c20, 0x0e073c20, 0x9eae0020,
1232 0x4cc0ac3f, 0x05a08020, 0x05104fe0, 0x05505001,
1233 0x05906fe2, 0x05d03005, 0x05101fea, 0x05901feb,
1234 0x04b0e3e0, 0x0470e7e1, 0x042f9c20, 0x043f9c35,
1235 0x047f9c20, 0x04ff9c20, 0x04299420, 0x04319160,
1236 0x0461943e, 0x04a19020, 0x04038100, 0x040381a0,
1237 0x040387e1, 0x04438be2, 0x04c38fe3, 0x040181e0,
1238 0x04018100, 0x04018621, 0x04418b22, 0x04418822,
1239 0x04818c23, 0x040081e0, 0x04008120, 0x04008761,
1240 0x04008621, 0x04408822, 0x04808c23, 0x042053ff,
1241 0x047f5401, 0x25208028, 0x2538cfe0, 0x2578d001,
1242 0x25b8efe2, 0x25f8f007, 0x2538dfea, 0x25b8dfeb,
1243 0xa400a3e0, 0xa420a7e0, 0xa4484be0, 0xa467afe0,
1244 0xa4a8a7ea, 0xa547a814, 0xa4084ffe, 0xa55c53e0,
1245 0xa5e1540b, 0xe400fbf6, 0xe408ffff, 0xe420e7e0,
1246 0xe4484be0, 0xe460efe0, 0xe547e400, 0xe4014be0,
1247 0xe4a84fe0, 0xe5f15000, 0x858043e0, 0x85a043ff,
1248 0xe59f5d08, 0x0420e3e9, 0x0460e3ea, 0x04a0e3eb,
1249 0x04e0e3ec, 0x25104042, 0x25104871, 0x25904861,
1250 0x25904c92, 0x05344020, 0x05744041, 0x05b44062,
1251 0x05f44083, 0x252c8840, 0x253c1420, 0x25681572,
1252 0x25a21ce3, 0x25ea1e34, 0x0522c020, 0x05e6c0a4,
1253 0x2401a001, 0x2443a051, 0x24858881, 0x24c78cd1,
1254 0x24850891, 0x24c70cc1, 0x250f9001, 0x25508051,
1255 0x25802491, 0x25df28c1, 0x25850c81, 0x251e10d1,
1256 0x65816001, 0x65c36051, 0x65854891, 0x65c74cc1,
1257 0x05733820, 0x05b238a4, 0x05f138e6, 0x0570396a,
1258 0x65d0a001, 0x65d6a443, 0x65d4a826, 0x6594ac26,
1259 0x6554ac26, 0x6556ac26, 0x6552ac26, 0x65cbac85,
1260 0x65caac01, 0x65dea833, 0x659ca509, 0x65d8a801,
1261 0x65dcac01, 0x655cb241, 0x0520a1e0, 0x0521a601,
1262 0x052281e0, 0x05238601, 0x04a14026, 0x0568aca7,
1263 0x05b23230, 0x853040af, 0xc5b040af, 0xe57080af,
1264 0xe5b080af, 0x25034440, 0x254054c4, 0x25034640,
1265 0x25415a05, 0x25834440, 0x25c54489, 0x250b5d3a,
1266 0x2550dc20, 0x2518e3e1, 0x2558e3e2, 0x2598e3e3,
1267 0x25d8e3e4, 0x2518e407, 0x05214800, 0x05614800,
1268 0x05a14800, 0x05e14800, 0x05214c00, 0x05614c00,
1269 0x05a14c00, 0x05e14c00, 0x05304001, 0x05314001,
1270 0x1e601000, 0x1e603000, 0x1e621000, 0x1e623000,
1271 0x1e641000, 0x1e643000, 0x1e661000, 0x1e663000,
1272 0x1e681000, 0x1e683000, 0x1e6a1000, 0x1e6a3000,
1273 0x1e6c1000, 0x1e6c3000, 0x1e6e1000, 0x1e6e3000,
1274 0x1e701000, 0x1e703000, 0x1e721000, 0x1e723000,
1275 0x1e741000, 0x1e743000, 0x1e761000, 0x1e763000,
1276 0x1e781000, 0x1e783000, 0x1e7a1000, 0x1e7a3000,
1277 0x1e7c1000, 0x1e7c3000, 0x1e7e1000, 0x1e7e3000,
1278 0xf8208193, 0xf83101b6, 0xf83c13fe, 0xf821239a,
1279 0xf824309e, 0xf826535e, 0xf8304109, 0xf82c7280,
1280 0xf8216058, 0xf8a08309, 0xf8ba03d0, 0xf8a312ea,
1281 0xf8aa21e4, 0xf8a2310b, 0xf8aa522f, 0xf8a2418a,
1282 0xf8ac71af, 0xf8a26287, 0xf8fa8090, 0xf8e20184,
1283 0xf8f01215, 0xf8f022ab, 0xf8f7334c, 0xf8f751dc,
1284 0xf8eb4038, 0xf8ec715f, 0xf8f06047, 0xf863826d,
1285 0xf8710070, 0xf86113cb, 0xf86521e8, 0xf87d301e,
1286 0xf8745287, 0xf87742bc, 0xf87b70b9, 0xf8616217,
1287 0xb83f8185, 0xb82901fc, 0xb83d13f6, 0xb83320bf,
1288 0xb82e33f0, 0xb830529b, 0xb830416c, 0xb82973c6,
1289 0xb831639b, 0xb8be8147, 0xb8b4008a, 0xb8b81231,
1290 0xb8b623a3, 0xb8af3276, 0xb8b35056, 0xb8af4186,
1291 0xb8b071ab, 0xb8b763c1, 0xb8f38225, 0xb8e202d0,
1292 0xb8ed12aa, 0xb8fd219b, 0xb8fb3023, 0xb8ff5278,
1293 0xb8f14389, 0xb8fb70ef, 0xb8f563f7, 0xb87983e2,
1294 0xb87b0150, 0xb8771073, 0xb8702320, 0xb87a3057,
1295 0xb870508c, 0xb87c43be, 0xb87070db, 0xb86961fd,
1296 0xce273c87, 0xce080ac9, 0xce7e8e9b, 0xce808b45,
1297 0xce79806e, 0xce758768, 0xcec0835a, 0xce608ad8,
1298 0x043100c4, 0x046105e3, 0x65c900a6, 0x65d60a87,
1299 0x65c80545, 0x0416a63e, 0x04001f8b, 0x045a179a,
1300 0x04d09e0d, 0x045aa1a5, 0x04990b4f, 0x049386cb,
1301 0x04918264, 0x04500dd1, 0x0497b062, 0x041ea4d7,
1302 0x04980f71, 0x04c80450, 0x048a04c3, 0x04810d93,
1303 0x04dcba68, 0x65808ae0, 0x65cd9db3, 0x658680e6,
1304 0x65879911, 0x65c296d6, 0x04dda1e2, 0x65c2a494,
1305 0x65c0a107, 0x65c1b493, 0x65cdb569, 0x65819e05,
1306 0x65ad8c36, 0x65af1334, 0x65e63104, 0x65fd5e04,
1307 0x65eb6c49, 0x049a4423, 0x04916d11, 0x043330b8,
1308 0x04b032d1, 0x04603274, 0x04e432f1, 0x05b96ae4,
1309 0x05686d02, 0x049a33d8, 0x04583c24, 0x04592c13,
1310 0x04083a27, 0x04ca253b, 0x65c72e17, 0x65c63696,
1311 0x65d829bc, 0x04413787,
1312 };
1313 // END Generated code -- do not edit
|