+ switch (opcode) {
+ case 0x0: /* FMOV */
+ tcg_gen_mov_i32(tcg_res, tcg_op);
+ break;
+ case 0x1: /* FABS */
+ gen_helper_vfp_abss(tcg_res, tcg_op);
+ break;
+ case 0x2: /* FNEG */
+ gen_helper_vfp_negs(tcg_res, tcg_op);
+ break;
+ case 0x3: /* FSQRT */
+ gen_helper_vfp_sqrts(tcg_res, tcg_op, cpu_env);
+ break;
+ case 0x8: /* FRINTN */
+ case 0x9: /* FRINTP */
+ case 0xa: /* FRINTM */
+ case 0xb: /* FRINTZ */
+ case 0xc: /* FRINTA */
+ {
+ TCGv_i32 tcg_rmode = tcg_const_i32(arm_rmode_to_sf(opcode & 7));
+
+ gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+ gen_helper_rints(tcg_res, tcg_op, fpst);
+
+ gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+ tcg_temp_free_i32(tcg_rmode);
+ break;
+ }
+ case 0xe: /* FRINTX */
+ gen_helper_rints_exact(tcg_res, tcg_op, fpst);
+ break;
+ case 0xf: /* FRINTI */
+ gen_helper_rints(tcg_res, tcg_op, fpst);
+ break;
+ default:
+ abort();
+ }
+
+ write_fp_sreg(s, rd, tcg_res);
+
+ tcg_temp_free_ptr(fpst);
+ tcg_temp_free_i32(tcg_op);
+ tcg_temp_free_i32(tcg_res);
+}
+
+/* C3.6.25 Floating-point data-processing (1 source) - double precision */
+static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn)
+{
+ TCGv_ptr fpst;
+ TCGv_i64 tcg_op;
+ TCGv_i64 tcg_res;
+
+ fpst = get_fpstatus_ptr();
+ tcg_op = read_fp_dreg(s, rn);
+ tcg_res = tcg_temp_new_i64();
+
+ switch (opcode) {
+ case 0x0: /* FMOV */
+ tcg_gen_mov_i64(tcg_res, tcg_op);
+ break;
+ case 0x1: /* FABS */
+ gen_helper_vfp_absd(tcg_res, tcg_op);
+ break;
+ case 0x2: /* FNEG */
+ gen_helper_vfp_negd(tcg_res, tcg_op);
+ break;
+ case 0x3: /* FSQRT */
+ gen_helper_vfp_sqrtd(tcg_res, tcg_op, cpu_env);
+ break;
+ case 0x8: /* FRINTN */
+ case 0x9: /* FRINTP */
+ case 0xa: /* FRINTM */
+ case 0xb: /* FRINTZ */
+ case 0xc: /* FRINTA */
+ {
+ TCGv_i32 tcg_rmode = tcg_const_i32(arm_rmode_to_sf(opcode & 7));
+
+ gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+ gen_helper_rintd(tcg_res, tcg_op, fpst);
+
+ gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+ tcg_temp_free_i32(tcg_rmode);
+ break;
+ }
+ case 0xe: /* FRINTX */
+ gen_helper_rintd_exact(tcg_res, tcg_op, fpst);
+ break;
+ case 0xf: /* FRINTI */
+ gen_helper_rintd(tcg_res, tcg_op, fpst);
+ break;
+ default:
+ abort();
+ }
+
+ write_fp_dreg(s, rd, tcg_res);
+
+ tcg_temp_free_ptr(fpst);
+ tcg_temp_free_i64(tcg_op);
+ tcg_temp_free_i64(tcg_res);
+}
+
+static void handle_fp_fcvt(DisasContext *s, int opcode,
+ int rd, int rn, int dtype, int ntype)
+{
+ switch (ntype) {
+ case 0x0:
+ {
+ TCGv_i32 tcg_rn = read_fp_sreg(s, rn);
+ if (dtype == 1) {
+ /* Single to double */
+ TCGv_i64 tcg_rd = tcg_temp_new_i64();
+ gen_helper_vfp_fcvtds(tcg_rd, tcg_rn, cpu_env);
+ write_fp_dreg(s, rd, tcg_rd);
+ tcg_temp_free_i64(tcg_rd);
+ } else {
+ /* Single to half */
+ TCGv_i32 tcg_rd = tcg_temp_new_i32();
+ gen_helper_vfp_fcvt_f32_to_f16(tcg_rd, tcg_rn, cpu_env);
+ /* write_fp_sreg is OK here because top half of tcg_rd is zero */
+ write_fp_sreg(s, rd, tcg_rd);
+ tcg_temp_free_i32(tcg_rd);
+ }
+ tcg_temp_free_i32(tcg_rn);
+ break;
+ }
+ case 0x1:
+ {
+ TCGv_i64 tcg_rn = read_fp_dreg(s, rn);
+ TCGv_i32 tcg_rd = tcg_temp_new_i32();
+ if (dtype == 0) {
+ /* Double to single */
+ gen_helper_vfp_fcvtsd(tcg_rd, tcg_rn, cpu_env);
+ } else {
+ /* Double to half */
+ gen_helper_vfp_fcvt_f64_to_f16(tcg_rd, tcg_rn, cpu_env);
+ /* write_fp_sreg is OK here because top half of tcg_rd is zero */
+ }
+ write_fp_sreg(s, rd, tcg_rd);
+ tcg_temp_free_i32(tcg_rd);
+ tcg_temp_free_i64(tcg_rn);
+ break;
+ }
+ case 0x3:
+ {
+ TCGv_i32 tcg_rn = read_fp_sreg(s, rn);
+ tcg_gen_ext16u_i32(tcg_rn, tcg_rn);
+ if (dtype == 0) {
+ /* Half to single */
+ TCGv_i32 tcg_rd = tcg_temp_new_i32();
+ gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, cpu_env);
+ write_fp_sreg(s, rd, tcg_rd);
+ tcg_temp_free_i32(tcg_rd);
+ } else {
+ /* Half to double */
+ TCGv_i64 tcg_rd = tcg_temp_new_i64();
+ gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, cpu_env);
+ write_fp_dreg(s, rd, tcg_rd);
+ tcg_temp_free_i64(tcg_rd);
+ }
+ tcg_temp_free_i32(tcg_rn);
+ break;
+ }
+ default:
+ abort();
+ }
+}
+
+/* C3.6.25 Floating point data-processing (1 source)
+ * 31 30 29 28 24 23 22 21 20 15 14 10 9 5 4 0
+ * +---+---+---+-----------+------+---+--------+-----------+------+------+
+ * | M | 0 | S | 1 1 1 1 0 | type | 1 | opcode | 1 0 0 0 0 | Rn | Rd |
+ * +---+---+---+-----------+------+---+--------+-----------+------+------+
+ */
+static void disas_fp_1src(DisasContext *s, uint32_t insn)
+{
+ int type = extract32(insn, 22, 2);
+ int opcode = extract32(insn, 15, 6);
+ int rn = extract32(insn, 5, 5);
+ int rd = extract32(insn, 0, 5);
+
+ switch (opcode) {
+ case 0x4: case 0x5: case 0x7:
+ {
+ /* FCVT between half, single and double precision */
+ int dtype = extract32(opcode, 0, 2);
+ if (type == 2 || dtype == type) {
+ unallocated_encoding(s);
+ return;
+ }
+ handle_fp_fcvt(s, opcode, rd, rn, dtype, type);
+ break;
+ }
+ case 0x0 ... 0x3:
+ case 0x8 ... 0xc:
+ case 0xe ... 0xf:
+ /* 32-to-32 and 64-to-64 ops */
+ switch (type) {
+ case 0:
+ handle_fp_1src_single(s, opcode, rd, rn);
+ break;
+ case 1:
+ handle_fp_1src_double(s, opcode, rd, rn);
+ break;
+ default:
+ unallocated_encoding(s);
+ }
+ break;
+ default:
+ unallocated_encoding(s);
+ break;
+ }
+}
+
+/* C3.6.26 Floating-point data-processing (2 source) - single precision */
+static void handle_fp_2src_single(DisasContext *s, int opcode,
+ int rd, int rn, int rm)
+{
+ TCGv_i32 tcg_op1;
+ TCGv_i32 tcg_op2;
+ TCGv_i32 tcg_res;
+ TCGv_ptr fpst;
+
+ tcg_res = tcg_temp_new_i32();
+ fpst = get_fpstatus_ptr();
+ tcg_op1 = read_fp_sreg(s, rn);
+ tcg_op2 = read_fp_sreg(s, rm);
+
+ switch (opcode) {
+ case 0x0: /* FMUL */
+ gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1: /* FDIV */
+ gen_helper_vfp_divs(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x2: /* FADD */
+ gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x3: /* FSUB */
+ gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x4: /* FMAX */
+ gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5: /* FMIN */
+ gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x6: /* FMAXNM */
+ gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x7: /* FMINNM */
+ gen_helper_vfp_minnums(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x8: /* FNMUL */
+ gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst);
+ gen_helper_vfp_negs(tcg_res, tcg_res);
+ break;
+ }
+
+ write_fp_sreg(s, rd, tcg_res);
+
+ tcg_temp_free_ptr(fpst);
+ tcg_temp_free_i32(tcg_op1);
+ tcg_temp_free_i32(tcg_op2);
+ tcg_temp_free_i32(tcg_res);
+}
+
+/* C3.6.26 Floating-point data-processing (2 source) - double precision */
+static void handle_fp_2src_double(DisasContext *s, int opcode,
+ int rd, int rn, int rm)
+{
+ TCGv_i64 tcg_op1;
+ TCGv_i64 tcg_op2;
+ TCGv_i64 tcg_res;
+ TCGv_ptr fpst;
+
+ tcg_res = tcg_temp_new_i64();
+ fpst = get_fpstatus_ptr();
+ tcg_op1 = read_fp_dreg(s, rn);
+ tcg_op2 = read_fp_dreg(s, rm);
+
+ switch (opcode) {
+ case 0x0: /* FMUL */
+ gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1: /* FDIV */
+ gen_helper_vfp_divd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x2: /* FADD */
+ gen_helper_vfp_addd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x3: /* FSUB */
+ gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x4: /* FMAX */
+ gen_helper_vfp_maxd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5: /* FMIN */
+ gen_helper_vfp_mind(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x6: /* FMAXNM */
+ gen_helper_vfp_maxnumd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x7: /* FMINNM */
+ gen_helper_vfp_minnumd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x8: /* FNMUL */
+ gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst);
+ gen_helper_vfp_negd(tcg_res, tcg_res);
+ break;
+ }
+
+ write_fp_dreg(s, rd, tcg_res);
+
+ tcg_temp_free_ptr(fpst);
+ tcg_temp_free_i64(tcg_op1);
+ tcg_temp_free_i64(tcg_op2);
+ tcg_temp_free_i64(tcg_res);
+}
+
+/* C3.6.26 Floating point data-processing (2 source)
+ * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0
+ * +---+---+---+-----------+------+---+------+--------+-----+------+------+
+ * | M | 0 | S | 1 1 1 1 0 | type | 1 | Rm | opcode | 1 0 | Rn | Rd |
+ * +---+---+---+-----------+------+---+------+--------+-----+------+------+
+ */
+static void disas_fp_2src(DisasContext *s, uint32_t insn)
+{
+ int type = extract32(insn, 22, 2);
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int rm = extract32(insn, 16, 5);
+ int opcode = extract32(insn, 12, 4);
+
+ if (opcode > 8) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ switch (type) {
+ case 0:
+ handle_fp_2src_single(s, opcode, rd, rn, rm);
+ break;
+ case 1:
+ handle_fp_2src_double(s, opcode, rd, rn, rm);
+ break;
+ default:
+ unallocated_encoding(s);
+ }
+}
+
+/* C3.6.27 Floating-point data-processing (3 source) - single precision */
+static void handle_fp_3src_single(DisasContext *s, bool o0, bool o1,
+ int rd, int rn, int rm, int ra)
+{
+ TCGv_i32 tcg_op1, tcg_op2, tcg_op3;
+ TCGv_i32 tcg_res = tcg_temp_new_i32();
+ TCGv_ptr fpst = get_fpstatus_ptr();
+
+ tcg_op1 = read_fp_sreg(s, rn);
+ tcg_op2 = read_fp_sreg(s, rm);
+ tcg_op3 = read_fp_sreg(s, ra);
+
+ /* These are fused multiply-add, and must be done as one
+ * floating point operation with no rounding between the
+ * multiplication and addition steps.
+ * NB that doing the negations here as separate steps is
+ * correct : an input NaN should come out with its sign bit
+ * flipped if it is a negated-input.
+ */
+ if (o1 == true) {
+ gen_helper_vfp_negs(tcg_op3, tcg_op3);
+ }
+
+ if (o0 != o1) {
+ gen_helper_vfp_negs(tcg_op1, tcg_op1);
+ }
+
+ gen_helper_vfp_muladds(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst);
+
+ write_fp_sreg(s, rd, tcg_res);
+
+ tcg_temp_free_ptr(fpst);
+ tcg_temp_free_i32(tcg_op1);
+ tcg_temp_free_i32(tcg_op2);
+ tcg_temp_free_i32(tcg_op3);
+ tcg_temp_free_i32(tcg_res);
+}
+
+/* C3.6.27 Floating-point data-processing (3 source) - double precision */
+static void handle_fp_3src_double(DisasContext *s, bool o0, bool o1,
+ int rd, int rn, int rm, int ra)
+{
+ TCGv_i64 tcg_op1, tcg_op2, tcg_op3;
+ TCGv_i64 tcg_res = tcg_temp_new_i64();
+ TCGv_ptr fpst = get_fpstatus_ptr();
+
+ tcg_op1 = read_fp_dreg(s, rn);
+ tcg_op2 = read_fp_dreg(s, rm);
+ tcg_op3 = read_fp_dreg(s, ra);
+
+ /* These are fused multiply-add, and must be done as one
+ * floating point operation with no rounding between the
+ * multiplication and addition steps.
+ * NB that doing the negations here as separate steps is
+ * correct : an input NaN should come out with its sign bit
+ * flipped if it is a negated-input.
+ */
+ if (o1 == true) {
+ gen_helper_vfp_negd(tcg_op3, tcg_op3);
+ }
+
+ if (o0 != o1) {
+ gen_helper_vfp_negd(tcg_op1, tcg_op1);
+ }
+
+ gen_helper_vfp_muladdd(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst);
+
+ write_fp_dreg(s, rd, tcg_res);
+
+ tcg_temp_free_ptr(fpst);
+ tcg_temp_free_i64(tcg_op1);
+ tcg_temp_free_i64(tcg_op2);
+ tcg_temp_free_i64(tcg_op3);
+ tcg_temp_free_i64(tcg_res);
+}
+
+/* C3.6.27 Floating point data-processing (3 source)
+ * 31 30 29 28 24 23 22 21 20 16 15 14 10 9 5 4 0
+ * +---+---+---+-----------+------+----+------+----+------+------+------+
+ * | M | 0 | S | 1 1 1 1 1 | type | o1 | Rm | o0 | Ra | Rn | Rd |
+ * +---+---+---+-----------+------+----+------+----+------+------+------+
+ */
+static void disas_fp_3src(DisasContext *s, uint32_t insn)
+{
+ int type = extract32(insn, 22, 2);
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int ra = extract32(insn, 10, 5);
+ int rm = extract32(insn, 16, 5);
+ bool o0 = extract32(insn, 15, 1);
+ bool o1 = extract32(insn, 21, 1);
+
+ switch (type) {
+ case 0:
+ handle_fp_3src_single(s, o0, o1, rd, rn, rm, ra);
+ break;
+ case 1:
+ handle_fp_3src_double(s, o0, o1, rd, rn, rm, ra);
+ break;
+ default:
+ unallocated_encoding(s);
+ }
+}
+
+/* C3.6.28 Floating point immediate
+ * 31 30 29 28 24 23 22 21 20 13 12 10 9 5 4 0
+ * +---+---+---+-----------+------+---+------------+-------+------+------+
+ * | M | 0 | S | 1 1 1 1 0 | type | 1 | imm8 | 1 0 0 | imm5 | Rd |
+ * +---+---+---+-----------+------+---+------------+-------+------+------+
+ */
+static void disas_fp_imm(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int imm8 = extract32(insn, 13, 8);
+ int is_double = extract32(insn, 22, 2);
+ uint64_t imm;
+ TCGv_i64 tcg_res;
+
+ if (is_double > 1) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ /* The imm8 encodes the sign bit, enough bits to represent
+ * an exponent in the range 01....1xx to 10....0xx,
+ * and the most significant 4 bits of the mantissa; see
+ * VFPExpandImm() in the v8 ARM ARM.
+ */
+ if (is_double) {
+ imm = (extract32(imm8, 7, 1) ? 0x8000 : 0) |
+ (extract32(imm8, 6, 1) ? 0x3fc0 : 0x4000) |
+ extract32(imm8, 0, 6);
+ imm <<= 48;
+ } else {
+ imm = (extract32(imm8, 7, 1) ? 0x8000 : 0) |
+ (extract32(imm8, 6, 1) ? 0x3e00 : 0x4000) |
+ (extract32(imm8, 0, 6) << 3);
+ imm <<= 16;
+ }
+
+ tcg_res = tcg_const_i64(imm);
+ write_fp_dreg(s, rd, tcg_res);
+ tcg_temp_free_i64(tcg_res);
+}
+
+/* Handle floating point <=> fixed point conversions. Note that we can
+ * also deal with fp <=> integer conversions as a special case (scale == 64)
+ * OPTME: consider handling that special case specially or at least skipping
+ * the call to scalbn in the helpers for zero shifts.
+ */
+static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode,
+ bool itof, int rmode, int scale, int sf, int type)
+{
+ bool is_signed = !(opcode & 1);
+ bool is_double = type;
+ TCGv_ptr tcg_fpstatus;
+ TCGv_i32 tcg_shift;
+
+ tcg_fpstatus = get_fpstatus_ptr();
+
+ tcg_shift = tcg_const_i32(64 - scale);
+
+ if (itof) {
+ TCGv_i64 tcg_int = cpu_reg(s, rn);
+ if (!sf) {
+ TCGv_i64 tcg_extend = new_tmp_a64(s);
+
+ if (is_signed) {
+ tcg_gen_ext32s_i64(tcg_extend, tcg_int);
+ } else {
+ tcg_gen_ext32u_i64(tcg_extend, tcg_int);
+ }
+
+ tcg_int = tcg_extend;
+ }
+
+ if (is_double) {
+ TCGv_i64 tcg_double = tcg_temp_new_i64();
+ if (is_signed) {
+ gen_helper_vfp_sqtod(tcg_double, tcg_int,
+ tcg_shift, tcg_fpstatus);
+ } else {
+ gen_helper_vfp_uqtod(tcg_double, tcg_int,
+ tcg_shift, tcg_fpstatus);
+ }
+ write_fp_dreg(s, rd, tcg_double);
+ tcg_temp_free_i64(tcg_double);
+ } else {
+ TCGv_i32 tcg_single = tcg_temp_new_i32();
+ if (is_signed) {
+ gen_helper_vfp_sqtos(tcg_single, tcg_int,
+ tcg_shift, tcg_fpstatus);
+ } else {
+ gen_helper_vfp_uqtos(tcg_single, tcg_int,
+ tcg_shift, tcg_fpstatus);
+ }
+ write_fp_sreg(s, rd, tcg_single);
+ tcg_temp_free_i32(tcg_single);
+ }
+ } else {
+ TCGv_i64 tcg_int = cpu_reg(s, rd);
+ TCGv_i32 tcg_rmode;
+
+ if (extract32(opcode, 2, 1)) {
+ /* There are too many rounding modes to all fit into rmode,
+ * so FCVTA[US] is a special case.
+ */
+ rmode = FPROUNDING_TIEAWAY;
+ }
+
+ tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
+
+ gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+
+ if (is_double) {
+ TCGv_i64 tcg_double = read_fp_dreg(s, rn);
+ if (is_signed) {
+ if (!sf) {
+ gen_helper_vfp_tosld(tcg_int, tcg_double,
+ tcg_shift, tcg_fpstatus);
+ } else {
+ gen_helper_vfp_tosqd(tcg_int, tcg_double,
+ tcg_shift, tcg_fpstatus);
+ }
+ } else {
+ if (!sf) {
+ gen_helper_vfp_tould(tcg_int, tcg_double,
+ tcg_shift, tcg_fpstatus);
+ } else {
+ gen_helper_vfp_touqd(tcg_int, tcg_double,
+ tcg_shift, tcg_fpstatus);
+ }
+ }
+ tcg_temp_free_i64(tcg_double);
+ } else {
+ TCGv_i32 tcg_single = read_fp_sreg(s, rn);
+ if (sf) {
+ if (is_signed) {
+ gen_helper_vfp_tosqs(tcg_int, tcg_single,
+ tcg_shift, tcg_fpstatus);
+ } else {
+ gen_helper_vfp_touqs(tcg_int, tcg_single,
+ tcg_shift, tcg_fpstatus);
+ }
+ } else {
+ TCGv_i32 tcg_dest = tcg_temp_new_i32();
+ if (is_signed) {
+ gen_helper_vfp_tosls(tcg_dest, tcg_single,
+ tcg_shift, tcg_fpstatus);
+ } else {
+ gen_helper_vfp_touls(tcg_dest, tcg_single,
+ tcg_shift, tcg_fpstatus);
+ }
+ tcg_gen_extu_i32_i64(tcg_int, tcg_dest);
+ tcg_temp_free_i32(tcg_dest);
+ }
+ tcg_temp_free_i32(tcg_single);
+ }
+
+ gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+ tcg_temp_free_i32(tcg_rmode);
+
+ if (!sf) {
+ tcg_gen_ext32u_i64(tcg_int, tcg_int);
+ }
+ }
+
+ tcg_temp_free_ptr(tcg_fpstatus);
+ tcg_temp_free_i32(tcg_shift);
+}
+
+/* C3.6.29 Floating point <-> fixed point conversions
+ * 31 30 29 28 24 23 22 21 20 19 18 16 15 10 9 5 4 0
+ * +----+---+---+-----------+------+---+-------+--------+-------+------+------+
+ * | sf | 0 | S | 1 1 1 1 0 | type | 0 | rmode | opcode | scale | Rn | Rd |
+ * +----+---+---+-----------+------+---+-------+--------+-------+------+------+
+ */
+static void disas_fp_fixed_conv(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int scale = extract32(insn, 10, 6);
+ int opcode = extract32(insn, 16, 3);
+ int rmode = extract32(insn, 19, 2);
+ int type = extract32(insn, 22, 2);
+ bool sbit = extract32(insn, 29, 1);
+ bool sf = extract32(insn, 31, 1);
+ bool itof;
+
+ if (sbit || (type > 1)
+ || (!sf && scale < 32)) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ switch ((rmode << 3) | opcode) {
+ case 0x2: /* SCVTF */
+ case 0x3: /* UCVTF */
+ itof = true;
+ break;
+ case 0x18: /* FCVTZS */
+ case 0x19: /* FCVTZU */
+ itof = false;
+ break;
+ default:
+ unallocated_encoding(s);
+ return;
+ }
+
+ handle_fpfpcvt(s, rd, rn, opcode, itof, FPROUNDING_ZERO, scale, sf, type);
+}
+
+static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof)
+{
+ /* FMOV: gpr to or from float, double, or top half of quad fp reg,
+ * without conversion.
+ */
+
+ if (itof) {
+ TCGv_i64 tcg_rn = cpu_reg(s, rn);
+
+ switch (type) {
+ case 0:
+ {
+ /* 32 bit */
+ TCGv_i64 tmp = tcg_temp_new_i64();
+ tcg_gen_ext32u_i64(tmp, tcg_rn);
+ tcg_gen_st_i64(tmp, cpu_env, fp_reg_offset(rd, MO_64));
+ tcg_gen_movi_i64(tmp, 0);
+ tcg_gen_st_i64(tmp, cpu_env, fp_reg_hi_offset(rd));
+ tcg_temp_free_i64(tmp);
+ break;
+ }
+ case 1:
+ {
+ /* 64 bit */
+ TCGv_i64 tmp = tcg_const_i64(0);
+ tcg_gen_st_i64(tcg_rn, cpu_env, fp_reg_offset(rd, MO_64));
+ tcg_gen_st_i64(tmp, cpu_env, fp_reg_hi_offset(rd));
+ tcg_temp_free_i64(tmp);
+ break;
+ }
+ case 2:
+ /* 64 bit to top half. */
+ tcg_gen_st_i64(tcg_rn, cpu_env, fp_reg_hi_offset(rd));
+ break;
+ }
+ } else {
+ TCGv_i64 tcg_rd = cpu_reg(s, rd);
+
+ switch (type) {
+ case 0:
+ /* 32 bit */
+ tcg_gen_ld32u_i64(tcg_rd, cpu_env, fp_reg_offset(rn, MO_32));
+ break;
+ case 1:
+ /* 64 bit */
+ tcg_gen_ld_i64(tcg_rd, cpu_env, fp_reg_offset(rn, MO_64));
+ break;
+ case 2:
+ /* 64 bits from top half */
+ tcg_gen_ld_i64(tcg_rd, cpu_env, fp_reg_hi_offset(rn));
+ break;
+ }
+ }
+}
+
+/* C3.6.30 Floating point <-> integer conversions
+ * 31 30 29 28 24 23 22 21 20 19 18 16 15 10 9 5 4 0
+ * +----+---+---+-----------+------+---+-------+-----+-------------+----+----+
+ * | sf | 0 | S | 1 1 1 1 0 | type | 1 | rmode | opc | 0 0 0 0 0 0 | Rn | Rd |
+ * +----+---+---+-----------+------+---+-------+-----+-------------+----+----+
+ */
+static void disas_fp_int_conv(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int opcode = extract32(insn, 16, 3);
+ int rmode = extract32(insn, 19, 2);
+ int type = extract32(insn, 22, 2);
+ bool sbit = extract32(insn, 29, 1);
+ bool sf = extract32(insn, 31, 1);
+
+ if (sbit) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ if (opcode > 5) {
+ /* FMOV */
+ bool itof = opcode & 1;
+
+ if (rmode >= 2) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ switch (sf << 3 | type << 1 | rmode) {
+ case 0x0: /* 32 bit */
+ case 0xa: /* 64 bit */
+ case 0xd: /* 64 bit to top half of quad */
+ break;
+ default:
+ /* all other sf/type/rmode combinations are invalid */
+ unallocated_encoding(s);
+ break;
+ }
+
+ handle_fmov(s, rd, rn, type, itof);
+ } else {
+ /* actual FP conversions */
+ bool itof = extract32(opcode, 1, 1);
+
+ if (type > 1 || (rmode != 0 && opcode > 1)) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ handle_fpfpcvt(s, rd, rn, opcode, itof, rmode, 64, sf, type);
+ }
+}
+
+/* FP-specific subcases of table C3-6 (SIMD and FP data processing)
+ * 31 30 29 28 25 24 0
+ * +---+---+---+---------+-----------------------------+
+ * | | 0 | | 1 1 1 1 | |
+ * +---+---+---+---------+-----------------------------+
+ */
+static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
+{
+ if (extract32(insn, 24, 1)) {
+ /* Floating point data-processing (3 source) */
+ disas_fp_3src(s, insn);
+ } else if (extract32(insn, 21, 1) == 0) {
+ /* Floating point to fixed point conversions */
+ disas_fp_fixed_conv(s, insn);
+ } else {
+ switch (extract32(insn, 10, 2)) {
+ case 1:
+ /* Floating point conditional compare */
+ disas_fp_ccomp(s, insn);
+ break;
+ case 2:
+ /* Floating point data-processing (2 source) */
+ disas_fp_2src(s, insn);
+ break;
+ case 3:
+ /* Floating point conditional select */
+ disas_fp_csel(s, insn);
+ break;
+ case 0:
+ switch (ctz32(extract32(insn, 12, 4))) {
+ case 0: /* [15:12] == xxx1 */
+ /* Floating point immediate */
+ disas_fp_imm(s, insn);
+ break;
+ case 1: /* [15:12] == xx10 */
+ /* Floating point compare */
+ disas_fp_compare(s, insn);
+ break;
+ case 2: /* [15:12] == x100 */
+ /* Floating point data-processing (1 source) */
+ disas_fp_1src(s, insn);
+ break;
+ case 3: /* [15:12] == 1000 */
+ unallocated_encoding(s);
+ break;
+ default: /* [15:12] == 0000 */
+ /* Floating point <-> integer conversions */
+ disas_fp_int_conv(s, insn);
+ break;
+ }
+ break;
+ }
+ }
+}
+
+static void do_ext64(DisasContext *s, TCGv_i64 tcg_left, TCGv_i64 tcg_right,
+ int pos)
+{
+ /* Extract 64 bits from the middle of two concatenated 64 bit
+ * vector register slices left:right. The extracted bits start
+ * at 'pos' bits into the right (least significant) side.
+ * We return the result in tcg_right, and guarantee not to
+ * trash tcg_left.
+ */
+ TCGv_i64 tcg_tmp = tcg_temp_new_i64();
+ assert(pos > 0 && pos < 64);
+
+ tcg_gen_shri_i64(tcg_right, tcg_right, pos);
+ tcg_gen_shli_i64(tcg_tmp, tcg_left, 64 - pos);
+ tcg_gen_or_i64(tcg_right, tcg_right, tcg_tmp);
+
+ tcg_temp_free_i64(tcg_tmp);
+}
+
+/* C3.6.1 EXT
+ * 31 30 29 24 23 22 21 20 16 15 14 11 10 9 5 4 0
+ * +---+---+-------------+-----+---+------+---+------+---+------+------+
+ * | 0 | Q | 1 0 1 1 1 0 | op2 | 0 | Rm | 0 | imm4 | 0 | Rn | Rd |
+ * +---+---+-------------+-----+---+------+---+------+---+------+------+
+ */
+static void disas_simd_ext(DisasContext *s, uint32_t insn)
+{
+ int is_q = extract32(insn, 30, 1);
+ int op2 = extract32(insn, 22, 2);
+ int imm4 = extract32(insn, 11, 4);
+ int rm = extract32(insn, 16, 5);
+ int rn = extract32(insn, 5, 5);
+ int rd = extract32(insn, 0, 5);
+ int pos = imm4 << 3;
+ TCGv_i64 tcg_resl, tcg_resh;
+
+ if (op2 != 0 || (!is_q && extract32(imm4, 3, 1))) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ tcg_resh = tcg_temp_new_i64();
+ tcg_resl = tcg_temp_new_i64();
+
+ /* Vd gets bits starting at pos bits into Vm:Vn. This is
+ * either extracting 128 bits from a 128:128 concatenation, or
+ * extracting 64 bits from a 64:64 concatenation.
+ */
+ if (!is_q) {
+ read_vec_element(s, tcg_resl, rn, 0, MO_64);
+ if (pos != 0) {
+ read_vec_element(s, tcg_resh, rm, 0, MO_64);
+ do_ext64(s, tcg_resh, tcg_resl, pos);
+ }
+ tcg_gen_movi_i64(tcg_resh, 0);
+ } else {
+ TCGv_i64 tcg_hh;
+ typedef struct {
+ int reg;
+ int elt;
+ } EltPosns;
+ EltPosns eltposns[] = { {rn, 0}, {rn, 1}, {rm, 0}, {rm, 1} };
+ EltPosns *elt = eltposns;
+
+ if (pos >= 64) {
+ elt++;
+ pos -= 64;
+ }
+
+ read_vec_element(s, tcg_resl, elt->reg, elt->elt, MO_64);
+ elt++;
+ read_vec_element(s, tcg_resh, elt->reg, elt->elt, MO_64);
+ elt++;
+ if (pos != 0) {
+ do_ext64(s, tcg_resh, tcg_resl, pos);
+ tcg_hh = tcg_temp_new_i64();
+ read_vec_element(s, tcg_hh, elt->reg, elt->elt, MO_64);
+ do_ext64(s, tcg_hh, tcg_resh, pos);
+ tcg_temp_free_i64(tcg_hh);
+ }
+ }
+
+ write_vec_element(s, tcg_resl, rd, 0, MO_64);
+ tcg_temp_free_i64(tcg_resl);
+ write_vec_element(s, tcg_resh, rd, 1, MO_64);
+ tcg_temp_free_i64(tcg_resh);
+}
+
+/* C3.6.2 TBL/TBX
+ * 31 30 29 24 23 22 21 20 16 15 14 13 12 11 10 9 5 4 0
+ * +---+---+-------------+-----+---+------+---+-----+----+-----+------+------+
+ * | 0 | Q | 0 0 1 1 1 0 | op2 | 0 | Rm | 0 | len | op | 0 0 | Rn | Rd |
+ * +---+---+-------------+-----+---+------+---+-----+----+-----+------+------+
+ */
+static void disas_simd_tb(DisasContext *s, uint32_t insn)
+{
+ int op2 = extract32(insn, 22, 2);
+ int is_q = extract32(insn, 30, 1);
+ int rm = extract32(insn, 16, 5);
+ int rn = extract32(insn, 5, 5);
+ int rd = extract32(insn, 0, 5);
+ int is_tblx = extract32(insn, 12, 1);
+ int len = extract32(insn, 13, 2);
+ TCGv_i64 tcg_resl, tcg_resh, tcg_idx;
+ TCGv_i32 tcg_regno, tcg_numregs;
+
+ if (op2 != 0) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ /* This does a table lookup: for every byte element in the input
+ * we index into a table formed from up to four vector registers,
+ * and then the output is the result of the lookups. Our helper
+ * function does the lookup operation for a single 64 bit part of
+ * the input.
+ */
+ tcg_resl = tcg_temp_new_i64();
+ tcg_resh = tcg_temp_new_i64();
+
+ if (is_tblx) {
+ read_vec_element(s, tcg_resl, rd, 0, MO_64);
+ } else {
+ tcg_gen_movi_i64(tcg_resl, 0);
+ }
+ if (is_tblx && is_q) {
+ read_vec_element(s, tcg_resh, rd, 1, MO_64);
+ } else {
+ tcg_gen_movi_i64(tcg_resh, 0);
+ }
+
+ tcg_idx = tcg_temp_new_i64();
+ tcg_regno = tcg_const_i32(rn);
+ tcg_numregs = tcg_const_i32(len + 1);
+ read_vec_element(s, tcg_idx, rm, 0, MO_64);
+ gen_helper_simd_tbl(tcg_resl, cpu_env, tcg_resl, tcg_idx,
+ tcg_regno, tcg_numregs);
+ if (is_q) {
+ read_vec_element(s, tcg_idx, rm, 1, MO_64);
+ gen_helper_simd_tbl(tcg_resh, cpu_env, tcg_resh, tcg_idx,
+ tcg_regno, tcg_numregs);
+ }
+ tcg_temp_free_i64(tcg_idx);
+ tcg_temp_free_i32(tcg_regno);
+ tcg_temp_free_i32(tcg_numregs);
+
+ write_vec_element(s, tcg_resl, rd, 0, MO_64);
+ tcg_temp_free_i64(tcg_resl);
+ write_vec_element(s, tcg_resh, rd, 1, MO_64);
+ tcg_temp_free_i64(tcg_resh);
+}
+
+/* C3.6.3 ZIP/UZP/TRN
+ * 31 30 29 24 23 22 21 20 16 15 14 12 11 10 9 5 4 0
+ * +---+---+-------------+------+---+------+---+------------------+------+
+ * | 0 | Q | 0 0 1 1 1 0 | size | 0 | Rm | 0 | opc | 1 0 | Rn | Rd |
+ * +---+---+-------------+------+---+------+---+------------------+------+
+ */
+static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int rm = extract32(insn, 16, 5);
+ int size = extract32(insn, 22, 2);
+ /* opc field bits [1:0] indicate ZIP/UZP/TRN;
+ * bit 2 indicates 1 vs 2 variant of the insn.
+ */
+ int opcode = extract32(insn, 12, 2);
+ bool part = extract32(insn, 14, 1);
+ bool is_q = extract32(insn, 30, 1);
+ int esize = 8 << size;
+ int i, ofs;
+ int datasize = is_q ? 128 : 64;
+ int elements = datasize / esize;
+ TCGv_i64 tcg_res, tcg_resl, tcg_resh;
+
+ if (opcode == 0 || (size == 3 && !is_q)) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ tcg_resl = tcg_const_i64(0);
+ tcg_resh = tcg_const_i64(0);
+ tcg_res = tcg_temp_new_i64();
+
+ for (i = 0; i < elements; i++) {
+ switch (opcode) {
+ case 1: /* UZP1/2 */
+ {
+ int midpoint = elements / 2;
+ if (i < midpoint) {
+ read_vec_element(s, tcg_res, rn, 2 * i + part, size);
+ } else {
+ read_vec_element(s, tcg_res, rm,
+ 2 * (i - midpoint) + part, size);
+ }
+ break;
+ }
+ case 2: /* TRN1/2 */
+ if (i & 1) {
+ read_vec_element(s, tcg_res, rm, (i & ~1) + part, size);
+ } else {
+ read_vec_element(s, tcg_res, rn, (i & ~1) + part, size);
+ }
+ break;
+ case 3: /* ZIP1/2 */
+ {
+ int base = part * elements / 2;
+ if (i & 1) {
+ read_vec_element(s, tcg_res, rm, base + (i >> 1), size);
+ } else {
+ read_vec_element(s, tcg_res, rn, base + (i >> 1), size);
+ }
+ break;
+ }
+ default:
+ g_assert_not_reached();
+ }
+
+ ofs = i * esize;
+ if (ofs < 64) {
+ tcg_gen_shli_i64(tcg_res, tcg_res, ofs);
+ tcg_gen_or_i64(tcg_resl, tcg_resl, tcg_res);
+ } else {
+ tcg_gen_shli_i64(tcg_res, tcg_res, ofs - 64);
+ tcg_gen_or_i64(tcg_resh, tcg_resh, tcg_res);
+ }
+ }
+
+ tcg_temp_free_i64(tcg_res);
+
+ write_vec_element(s, tcg_resl, rd, 0, MO_64);
+ tcg_temp_free_i64(tcg_resl);
+ write_vec_element(s, tcg_resh, rd, 1, MO_64);
+ tcg_temp_free_i64(tcg_resh);
+}
+
+static void do_minmaxop(DisasContext *s, TCGv_i32 tcg_elt1, TCGv_i32 tcg_elt2,
+ int opc, bool is_min, TCGv_ptr fpst)
+{
+ /* Helper function for disas_simd_across_lanes: do a single precision
+ * min/max operation on the specified two inputs,
+ * and return the result in tcg_elt1.
+ */
+ if (opc == 0xc) {
+ if (is_min) {
+ gen_helper_vfp_minnums(tcg_elt1, tcg_elt1, tcg_elt2, fpst);
+ } else {
+ gen_helper_vfp_maxnums(tcg_elt1, tcg_elt1, tcg_elt2, fpst);
+ }
+ } else {
+ assert(opc == 0xf);
+ if (is_min) {
+ gen_helper_vfp_mins(tcg_elt1, tcg_elt1, tcg_elt2, fpst);
+ } else {
+ gen_helper_vfp_maxs(tcg_elt1, tcg_elt1, tcg_elt2, fpst);
+ }
+ }
+}
+
+/* C3.6.4 AdvSIMD across lanes
+ * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0
+ * +---+---+---+-----------+------+-----------+--------+-----+------+------+
+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 1 0 0 0 | opcode | 1 0 | Rn | Rd |
+ * +---+---+---+-----------+------+-----------+--------+-----+------+------+
+ */
+static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int size = extract32(insn, 22, 2);
+ int opcode = extract32(insn, 12, 5);
+ bool is_q = extract32(insn, 30, 1);
+ bool is_u = extract32(insn, 29, 1);
+ bool is_fp = false;
+ bool is_min = false;
+ int esize;
+ int elements;
+ int i;
+ TCGv_i64 tcg_res, tcg_elt;
+
+ switch (opcode) {
+ case 0x1b: /* ADDV */
+ if (is_u) {
+ unallocated_encoding(s);
+ return;
+ }
+ /* fall through */
+ case 0x3: /* SADDLV, UADDLV */
+ case 0xa: /* SMAXV, UMAXV */
+ case 0x1a: /* SMINV, UMINV */
+ if (size == 3 || (size == 2 && !is_q)) {
+ unallocated_encoding(s);
+ return;
+ }
+ break;
+ case 0xc: /* FMAXNMV, FMINNMV */
+ case 0xf: /* FMAXV, FMINV */
+ if (!is_u || !is_q || extract32(size, 0, 1)) {
+ unallocated_encoding(s);
+ return;
+ }
+ /* Bit 1 of size field encodes min vs max, and actual size is always
+ * 32 bits: adjust the size variable so following code can rely on it
+ */
+ is_min = extract32(size, 1, 1);
+ is_fp = true;
+ size = 2;
+ break;
+ default:
+ unallocated_encoding(s);
+ return;
+ }
+
+ esize = 8 << size;
+ elements = (is_q ? 128 : 64) / esize;
+
+ tcg_res = tcg_temp_new_i64();
+ tcg_elt = tcg_temp_new_i64();
+
+ /* These instructions operate across all lanes of a vector
+ * to produce a single result. We can guarantee that a 64
+ * bit intermediate is sufficient:
+ * + for [US]ADDLV the maximum element size is 32 bits, and
+ * the result type is 64 bits
+ * + for FMAX*V, FMIN*V, ADDV the intermediate type is the
+ * same as the element size, which is 32 bits at most
+ * For the integer operations we can choose to work at 64
+ * or 32 bits and truncate at the end; for simplicity
+ * we use 64 bits always. The floating point
+ * ops do require 32 bit intermediates, though.
+ */
+ if (!is_fp) {
+ read_vec_element(s, tcg_res, rn, 0, size | (is_u ? 0 : MO_SIGN));
+
+ for (i = 1; i < elements; i++) {
+ read_vec_element(s, tcg_elt, rn, i, size | (is_u ? 0 : MO_SIGN));
+
+ switch (opcode) {
+ case 0x03: /* SADDLV / UADDLV */
+ case 0x1b: /* ADDV */
+ tcg_gen_add_i64(tcg_res, tcg_res, tcg_elt);
+ break;
+ case 0x0a: /* SMAXV / UMAXV */
+ tcg_gen_movcond_i64(is_u ? TCG_COND_GEU : TCG_COND_GE,
+ tcg_res,
+ tcg_res, tcg_elt, tcg_res, tcg_elt);
+ break;
+ case 0x1a: /* SMINV / UMINV */
+ tcg_gen_movcond_i64(is_u ? TCG_COND_LEU : TCG_COND_LE,
+ tcg_res,
+ tcg_res, tcg_elt, tcg_res, tcg_elt);
+ break;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ }
+ } else {
+ /* Floating point ops which work on 32 bit (single) intermediates.
+ * Note that correct NaN propagation requires that we do these
+ * operations in exactly the order specified by the pseudocode.
+ */
+ TCGv_i32 tcg_elt1 = tcg_temp_new_i32();
+ TCGv_i32 tcg_elt2 = tcg_temp_new_i32();
+ TCGv_i32 tcg_elt3 = tcg_temp_new_i32();
+ TCGv_ptr fpst = get_fpstatus_ptr();
+
+ assert(esize == 32);
+ assert(elements == 4);
+
+ read_vec_element(s, tcg_elt, rn, 0, MO_32);
+ tcg_gen_trunc_i64_i32(tcg_elt1, tcg_elt);
+ read_vec_element(s, tcg_elt, rn, 1, MO_32);
+ tcg_gen_trunc_i64_i32(tcg_elt2, tcg_elt);
+
+ do_minmaxop(s, tcg_elt1, tcg_elt2, opcode, is_min, fpst);
+
+ read_vec_element(s, tcg_elt, rn, 2, MO_32);
+ tcg_gen_trunc_i64_i32(tcg_elt2, tcg_elt);
+ read_vec_element(s, tcg_elt, rn, 3, MO_32);
+ tcg_gen_trunc_i64_i32(tcg_elt3, tcg_elt);
+
+ do_minmaxop(s, tcg_elt2, tcg_elt3, opcode, is_min, fpst);
+
+ do_minmaxop(s, tcg_elt1, tcg_elt2, opcode, is_min, fpst);
+
+ tcg_gen_extu_i32_i64(tcg_res, tcg_elt1);
+ tcg_temp_free_i32(tcg_elt1);
+ tcg_temp_free_i32(tcg_elt2);
+ tcg_temp_free_i32(tcg_elt3);
+ tcg_temp_free_ptr(fpst);
+ }
+
+ tcg_temp_free_i64(tcg_elt);
+
+ /* Now truncate the result to the width required for the final output */
+ if (opcode == 0x03) {
+ /* SADDLV, UADDLV: result is 2*esize */
+ size++;
+ }
+
+ switch (size) {
+ case 0:
+ tcg_gen_ext8u_i64(tcg_res, tcg_res);
+ break;
+ case 1:
+ tcg_gen_ext16u_i64(tcg_res, tcg_res);
+ break;
+ case 2:
+ tcg_gen_ext32u_i64(tcg_res, tcg_res);
+ break;
+ case 3:
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ write_fp_dreg(s, rd, tcg_res);
+ tcg_temp_free_i64(tcg_res);
+}
+
+/* C6.3.31 DUP (Element, Vector)
+ *
+ * 31 30 29 21 20 16 15 10 9 5 4 0
+ * +---+---+-------------------+--------+-------------+------+------+
+ * | 0 | Q | 0 0 1 1 1 0 0 0 0 | imm5 | 0 0 0 0 0 1 | Rn | Rd |
+ * +---+---+-------------------+--------+-------------+------+------+
+ *
+ * size: encoded in imm5 (see ARM ARM LowestSetBit())
+ */
+static void handle_simd_dupe(DisasContext *s, int is_q, int rd, int rn,
+ int imm5)
+{
+ int size = ctz32(imm5);
+ int esize = 8 << size;
+ int elements = (is_q ? 128 : 64) / esize;
+ int index, i;
+ TCGv_i64 tmp;
+
+ if (size > 3 || (size == 3 && !is_q)) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ index = imm5 >> (size + 1);
+
+ tmp = tcg_temp_new_i64();
+ read_vec_element(s, tmp, rn, index, size);
+
+ for (i = 0; i < elements; i++) {
+ write_vec_element(s, tmp, rd, i, size);
+ }
+
+ if (!is_q) {
+ clear_vec_high(s, rd);
+ }
+
+ tcg_temp_free_i64(tmp);
+}
+
+/* C6.3.31 DUP (element, scalar)
+ * 31 21 20 16 15 10 9 5 4 0
+ * +-----------------------+--------+-------------+------+------+
+ * | 0 1 0 1 1 1 1 0 0 0 0 | imm5 | 0 0 0 0 0 1 | Rn | Rd |
+ * +-----------------------+--------+-------------+------+------+
+ */
+static void handle_simd_dupes(DisasContext *s, int rd, int rn,
+ int imm5)
+{
+ int size = ctz32(imm5);
+ int index;
+ TCGv_i64 tmp;
+
+ if (size > 3) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ index = imm5 >> (size + 1);
+
+ /* This instruction just extracts the specified element and
+ * zero-extends it into the bottom of the destination register.
+ */
+ tmp = tcg_temp_new_i64();
+ read_vec_element(s, tmp, rn, index, size);
+ write_fp_dreg(s, rd, tmp);
+ tcg_temp_free_i64(tmp);
+}
+
+/* C6.3.32 DUP (General)
+ *
+ * 31 30 29 21 20 16 15 10 9 5 4 0
+ * +---+---+-------------------+--------+-------------+------+------+
+ * | 0 | Q | 0 0 1 1 1 0 0 0 0 | imm5 | 0 0 0 0 1 1 | Rn | Rd |
+ * +---+---+-------------------+--------+-------------+------+------+
+ *
+ * size: encoded in imm5 (see ARM ARM LowestSetBit())
+ */
+static void handle_simd_dupg(DisasContext *s, int is_q, int rd, int rn,
+ int imm5)
+{
+ int size = ctz32(imm5);
+ int esize = 8 << size;
+ int elements = (is_q ? 128 : 64)/esize;
+ int i = 0;
+
+ if (size > 3 || ((size == 3) && !is_q)) {
+ unallocated_encoding(s);
+ return;
+ }
+ for (i = 0; i < elements; i++) {
+ write_vec_element(s, cpu_reg(s, rn), rd, i, size);
+ }
+ if (!is_q) {
+ clear_vec_high(s, rd);
+ }
+}
+
+/* C6.3.150 INS (Element)
+ *
+ * 31 21 20 16 15 14 11 10 9 5 4 0
+ * +-----------------------+--------+------------+---+------+------+
+ * | 0 1 1 0 1 1 1 0 0 0 0 | imm5 | 0 | imm4 | 1 | Rn | Rd |
+ * +-----------------------+--------+------------+---+------+------+
+ *
+ * size: encoded in imm5 (see ARM ARM LowestSetBit())
+ * index: encoded in imm5<4:size+1>
+ */
+static void handle_simd_inse(DisasContext *s, int rd, int rn,
+ int imm4, int imm5)
+{
+ int size = ctz32(imm5);
+ int src_index, dst_index;
+ TCGv_i64 tmp;
+
+ if (size > 3) {
+ unallocated_encoding(s);
+ return;
+ }
+ dst_index = extract32(imm5, 1+size, 5);
+ src_index = extract32(imm4, size, 4);
+
+ tmp = tcg_temp_new_i64();
+
+ read_vec_element(s, tmp, rn, src_index, size);
+ write_vec_element(s, tmp, rd, dst_index, size);
+
+ tcg_temp_free_i64(tmp);
+}
+
+
+/* C6.3.151 INS (General)
+ *
+ * 31 21 20 16 15 10 9 5 4 0
+ * +-----------------------+--------+-------------+------+------+
+ * | 0 1 0 0 1 1 1 0 0 0 0 | imm5 | 0 0 0 1 1 1 | Rn | Rd |
+ * +-----------------------+--------+-------------+------+------+
+ *
+ * size: encoded in imm5 (see ARM ARM LowestSetBit())
+ * index: encoded in imm5<4:size+1>
+ */
+static void handle_simd_insg(DisasContext *s, int rd, int rn, int imm5)
+{
+ int size = ctz32(imm5);
+ int idx;
+
+ if (size > 3) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ idx = extract32(imm5, 1 + size, 4 - size);
+ write_vec_element(s, cpu_reg(s, rn), rd, idx, size);
+}
+
+/*
+ * C6.3.321 UMOV (General)
+ * C6.3.237 SMOV (General)
+ *
+ * 31 30 29 21 20 16 15 12 10 9 5 4 0
+ * +---+---+-------------------+--------+-------------+------+------+
+ * | 0 | Q | 0 0 1 1 1 0 0 0 0 | imm5 | 0 0 1 U 1 1 | Rn | Rd |
+ * +---+---+-------------------+--------+-------------+------+------+
+ *
+ * U: unsigned when set
+ * size: encoded in imm5 (see ARM ARM LowestSetBit())
+ */
+static void handle_simd_umov_smov(DisasContext *s, int is_q, int is_signed,
+ int rn, int rd, int imm5)
+{
+ int size = ctz32(imm5);
+ int element;
+ TCGv_i64 tcg_rd;
+
+ /* Check for UnallocatedEncodings */
+ if (is_signed) {
+ if (size > 2 || (size == 2 && !is_q)) {
+ unallocated_encoding(s);
+ return;
+ }
+ } else {
+ if (size > 3
+ || (size < 3 && is_q)
+ || (size == 3 && !is_q)) {
+ unallocated_encoding(s);
+ return;
+ }
+ }
+ element = extract32(imm5, 1+size, 4);
+
+ tcg_rd = cpu_reg(s, rd);
+ read_vec_element(s, tcg_rd, rn, element, size | (is_signed ? MO_SIGN : 0));
+ if (is_signed && !is_q) {
+ tcg_gen_ext32u_i64(tcg_rd, tcg_rd);
+ }
+}
+
+/* C3.6.5 AdvSIMD copy
+ * 31 30 29 28 21 20 16 15 14 11 10 9 5 4 0
+ * +---+---+----+-----------------+------+---+------+---+------+------+
+ * | 0 | Q | op | 0 1 1 1 0 0 0 0 | imm5 | 0 | imm4 | 1 | Rn | Rd |
+ * +---+---+----+-----------------+------+---+------+---+------+------+
+ */
+static void disas_simd_copy(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int imm4 = extract32(insn, 11, 4);
+ int op = extract32(insn, 29, 1);
+ int is_q = extract32(insn, 30, 1);
+ int imm5 = extract32(insn, 16, 5);
+
+ if (op) {
+ if (is_q) {
+ /* INS (element) */
+ handle_simd_inse(s, rd, rn, imm4, imm5);
+ } else {
+ unallocated_encoding(s);
+ }
+ } else {
+ switch (imm4) {
+ case 0:
+ /* DUP (element - vector) */
+ handle_simd_dupe(s, is_q, rd, rn, imm5);
+ break;
+ case 1:
+ /* DUP (general) */
+ handle_simd_dupg(s, is_q, rd, rn, imm5);
+ break;
+ case 3:
+ if (is_q) {
+ /* INS (general) */
+ handle_simd_insg(s, rd, rn, imm5);
+ } else {
+ unallocated_encoding(s);
+ }
+ break;
+ case 5:
+ case 7:
+ /* UMOV/SMOV (is_q indicates 32/64; imm4 indicates signedness) */
+ handle_simd_umov_smov(s, is_q, (imm4 == 5), rn, rd, imm5);
+ break;
+ default:
+ unallocated_encoding(s);
+ break;
+ }
+ }
+}
+
+/* C3.6.6 AdvSIMD modified immediate
+ * 31 30 29 28 19 18 16 15 12 11 10 9 5 4 0
+ * +---+---+----+---------------------+-----+-------+----+---+-------+------+
+ * | 0 | Q | op | 0 1 1 1 1 0 0 0 0 0 | abc | cmode | o2 | 1 | defgh | Rd |
+ * +---+---+----+---------------------+-----+-------+----+---+-------+------+
+ *
+ * There are a number of operations that can be carried out here:
+ * MOVI - move (shifted) imm into register
+ * MVNI - move inverted (shifted) imm into register
+ * ORR - bitwise OR of (shifted) imm with register
+ * BIC - bitwise clear of (shifted) imm with register
+ */
+static void disas_simd_mod_imm(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int cmode = extract32(insn, 12, 4);
+ int cmode_3_1 = extract32(cmode, 1, 3);
+ int cmode_0 = extract32(cmode, 0, 1);
+ int o2 = extract32(insn, 11, 1);
+ uint64_t abcdefgh = extract32(insn, 5, 5) | (extract32(insn, 16, 3) << 5);
+ bool is_neg = extract32(insn, 29, 1);
+ bool is_q = extract32(insn, 30, 1);
+ uint64_t imm = 0;
+ TCGv_i64 tcg_rd, tcg_imm;
+ int i;
+
+ if (o2 != 0 || ((cmode == 0xf) && is_neg && !is_q)) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ /* See AdvSIMDExpandImm() in ARM ARM */
+ switch (cmode_3_1) {
+ case 0: /* Replicate(Zeros(24):imm8, 2) */
+ case 1: /* Replicate(Zeros(16):imm8:Zeros(8), 2) */
+ case 2: /* Replicate(Zeros(8):imm8:Zeros(16), 2) */
+ case 3: /* Replicate(imm8:Zeros(24), 2) */
+ {
+ int shift = cmode_3_1 * 8;
+ imm = bitfield_replicate(abcdefgh << shift, 32);
+ break;
+ }
+ case 4: /* Replicate(Zeros(8):imm8, 4) */
+ case 5: /* Replicate(imm8:Zeros(8), 4) */
+ {
+ int shift = (cmode_3_1 & 0x1) * 8;
+ imm = bitfield_replicate(abcdefgh << shift, 16);
+ break;
+ }
+ case 6:
+ if (cmode_0) {
+ /* Replicate(Zeros(8):imm8:Ones(16), 2) */
+ imm = (abcdefgh << 16) | 0xffff;
+ } else {
+ /* Replicate(Zeros(16):imm8:Ones(8), 2) */
+ imm = (abcdefgh << 8) | 0xff;
+ }
+ imm = bitfield_replicate(imm, 32);
+ break;
+ case 7:
+ if (!cmode_0 && !is_neg) {
+ imm = bitfield_replicate(abcdefgh, 8);
+ } else if (!cmode_0 && is_neg) {
+ int i;
+ imm = 0;
+ for (i = 0; i < 8; i++) {
+ if ((abcdefgh) & (1 << i)) {
+ imm |= 0xffULL << (i * 8);
+ }
+ }
+ } else if (cmode_0) {
+ if (is_neg) {
+ imm = (abcdefgh & 0x3f) << 48;
+ if (abcdefgh & 0x80) {
+ imm |= 0x8000000000000000ULL;
+ }
+ if (abcdefgh & 0x40) {
+ imm |= 0x3fc0000000000000ULL;
+ } else {
+ imm |= 0x4000000000000000ULL;
+ }
+ } else {
+ imm = (abcdefgh & 0x3f) << 19;
+ if (abcdefgh & 0x80) {
+ imm |= 0x80000000;
+ }
+ if (abcdefgh & 0x40) {
+ imm |= 0x3e000000;
+ } else {
+ imm |= 0x40000000;
+ }
+ imm |= (imm << 32);
+ }
+ }
+ break;
+ }
+
+ if (cmode_3_1 != 7 && is_neg) {
+ imm = ~imm;
+ }
+
+ tcg_imm = tcg_const_i64(imm);
+ tcg_rd = new_tmp_a64(s);
+
+ for (i = 0; i < 2; i++) {
+ int foffs = i ? fp_reg_hi_offset(rd) : fp_reg_offset(rd, MO_64);
+
+ if (i == 1 && !is_q) {
+ /* non-quad ops clear high half of vector */
+ tcg_gen_movi_i64(tcg_rd, 0);
+ } else if ((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9) {
+ tcg_gen_ld_i64(tcg_rd, cpu_env, foffs);
+ if (is_neg) {
+ /* AND (BIC) */
+ tcg_gen_and_i64(tcg_rd, tcg_rd, tcg_imm);
+ } else {
+ /* ORR */
+ tcg_gen_or_i64(tcg_rd, tcg_rd, tcg_imm);
+ }
+ } else {
+ /* MOVI */
+ tcg_gen_mov_i64(tcg_rd, tcg_imm);
+ }
+ tcg_gen_st_i64(tcg_rd, cpu_env, foffs);
+ }
+
+ tcg_temp_free_i64(tcg_imm);
+}
+
+/* C3.6.7 AdvSIMD scalar copy
+ * 31 30 29 28 21 20 16 15 14 11 10 9 5 4 0
+ * +-----+----+-----------------+------+---+------+---+------+------+
+ * | 0 1 | op | 1 1 1 1 0 0 0 0 | imm5 | 0 | imm4 | 1 | Rn | Rd |
+ * +-----+----+-----------------+------+---+------+---+------+------+
+ */
+static void disas_simd_scalar_copy(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int imm4 = extract32(insn, 11, 4);
+ int imm5 = extract32(insn, 16, 5);
+ int op = extract32(insn, 29, 1);
+
+ if (op != 0 || imm4 != 0) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ /* DUP (element, scalar) */
+ handle_simd_dupes(s, rd, rn, imm5);
+}
+
+/* C3.6.8 AdvSIMD scalar pairwise
+ * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0
+ * +-----+---+-----------+------+-----------+--------+-----+------+------+
+ * | 0 1 | U | 1 1 1 1 0 | size | 1 1 0 0 0 | opcode | 1 0 | Rn | Rd |
+ * +-----+---+-----------+------+-----------+--------+-----+------+------+
+ */
+static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn)
+{
+ int u = extract32(insn, 29, 1);
+ int size = extract32(insn, 22, 2);
+ int opcode = extract32(insn, 12, 5);
+ int rn = extract32(insn, 5, 5);
+ int rd = extract32(insn, 0, 5);
+ TCGv_ptr fpst;
+
+ /* For some ops (the FP ones), size[1] is part of the encoding.
+ * For ADDP strictly it is not but size[1] is always 1 for valid
+ * encodings.
+ */
+ opcode |= (extract32(size, 1, 1) << 5);
+
+ switch (opcode) {
+ case 0x3b: /* ADDP */
+ if (u || size != 3) {
+ unallocated_encoding(s);
+ return;
+ }
+ TCGV_UNUSED_PTR(fpst);
+ break;
+ case 0xc: /* FMAXNMP */
+ case 0xd: /* FADDP */
+ case 0xf: /* FMAXP */
+ case 0x2c: /* FMINNMP */
+ case 0x2f: /* FMINP */
+ /* FP op, size[0] is 32 or 64 bit */
+ if (!u) {
+ unallocated_encoding(s);
+ return;
+ }
+ size = extract32(size, 0, 1) ? 3 : 2;
+ fpst = get_fpstatus_ptr();
+ break;
+ default:
+ unallocated_encoding(s);
+ return;
+ }
+
+ if (size == 3) {
+ TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+ TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+ TCGv_i64 tcg_res = tcg_temp_new_i64();
+
+ read_vec_element(s, tcg_op1, rn, 0, MO_64);
+ read_vec_element(s, tcg_op2, rn, 1, MO_64);
+
+ switch (opcode) {
+ case 0x3b: /* ADDP */
+ tcg_gen_add_i64(tcg_res, tcg_op1, tcg_op2);
+ break;
+ case 0xc: /* FMAXNMP */
+ gen_helper_vfp_maxnumd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0xd: /* FADDP */
+ gen_helper_vfp_addd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0xf: /* FMAXP */
+ gen_helper_vfp_maxd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x2c: /* FMINNMP */
+ gen_helper_vfp_minnumd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x2f: /* FMINP */
+ gen_helper_vfp_mind(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ write_fp_dreg(s, rd, tcg_res);
+
+ tcg_temp_free_i64(tcg_op1);
+ tcg_temp_free_i64(tcg_op2);
+ tcg_temp_free_i64(tcg_res);
+ } else {
+ TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+ TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+ TCGv_i32 tcg_res = tcg_temp_new_i32();
+
+ read_vec_element_i32(s, tcg_op1, rn, 0, MO_32);
+ read_vec_element_i32(s, tcg_op2, rn, 1, MO_32);
+
+ switch (opcode) {
+ case 0xc: /* FMAXNMP */
+ gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0xd: /* FADDP */
+ gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0xf: /* FMAXP */
+ gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x2c: /* FMINNMP */
+ gen_helper_vfp_minnums(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x2f: /* FMINP */
+ gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ write_fp_sreg(s, rd, tcg_res);
+
+ tcg_temp_free_i32(tcg_op1);
+ tcg_temp_free_i32(tcg_op2);
+ tcg_temp_free_i32(tcg_res);
+ }
+
+ if (!TCGV_IS_UNUSED_PTR(fpst)) {
+ tcg_temp_free_ptr(fpst);
+ }
+}
+
+/*
+ * Common SSHR[RA]/USHR[RA] - Shift right (optional rounding/accumulate)
+ *
+ * This code is handles the common shifting code and is used by both
+ * the vector and scalar code.
+ */
+static void handle_shri_with_rndacc(TCGv_i64 tcg_res, TCGv_i64 tcg_src,
+ TCGv_i64 tcg_rnd, bool accumulate,
+ bool is_u, int size, int shift)
+{
+ bool extended_result = false;
+ bool round = !TCGV_IS_UNUSED_I64(tcg_rnd);
+ int ext_lshift = 0;
+ TCGv_i64 tcg_src_hi;
+
+ if (round && size == 3) {
+ extended_result = true;
+ ext_lshift = 64 - shift;
+ tcg_src_hi = tcg_temp_new_i64();
+ } else if (shift == 64) {
+ if (!accumulate && is_u) {
+ /* result is zero */
+ tcg_gen_movi_i64(tcg_res, 0);
+ return;
+ }
+ }
+
+ /* Deal with the rounding step */
+ if (round) {
+ if (extended_result) {
+ TCGv_i64 tcg_zero = tcg_const_i64(0);
+ if (!is_u) {
+ /* take care of sign extending tcg_res */
+ tcg_gen_sari_i64(tcg_src_hi, tcg_src, 63);
+ tcg_gen_add2_i64(tcg_src, tcg_src_hi,
+ tcg_src, tcg_src_hi,
+ tcg_rnd, tcg_zero);
+ } else {
+ tcg_gen_add2_i64(tcg_src, tcg_src_hi,
+ tcg_src, tcg_zero,
+ tcg_rnd, tcg_zero);
+ }
+ tcg_temp_free_i64(tcg_zero);
+ } else {
+ tcg_gen_add_i64(tcg_src, tcg_src, tcg_rnd);
+ }
+ }
+
+ /* Now do the shift right */
+ if (round && extended_result) {
+ /* extended case, >64 bit precision required */
+ if (ext_lshift == 0) {
+ /* special case, only high bits matter */
+ tcg_gen_mov_i64(tcg_src, tcg_src_hi);
+ } else {
+ tcg_gen_shri_i64(tcg_src, tcg_src, shift);
+ tcg_gen_shli_i64(tcg_src_hi, tcg_src_hi, ext_lshift);
+ tcg_gen_or_i64(tcg_src, tcg_src, tcg_src_hi);
+ }
+ } else {
+ if (is_u) {
+ if (shift == 64) {
+ /* essentially shifting in 64 zeros */
+ tcg_gen_movi_i64(tcg_src, 0);
+ } else {
+ tcg_gen_shri_i64(tcg_src, tcg_src, shift);
+ }
+ } else {
+ if (shift == 64) {
+ /* effectively extending the sign-bit */
+ tcg_gen_sari_i64(tcg_src, tcg_src, 63);
+ } else {
+ tcg_gen_sari_i64(tcg_src, tcg_src, shift);
+ }
+ }
+ }
+
+ if (accumulate) {
+ tcg_gen_add_i64(tcg_res, tcg_res, tcg_src);
+ } else {
+ tcg_gen_mov_i64(tcg_res, tcg_src);
+ }
+
+ if (extended_result) {
+ tcg_temp_free_i64(tcg_src_hi);
+ }
+}
+
+/* Common SHL/SLI - Shift left with an optional insert */
+static void handle_shli_with_ins(TCGv_i64 tcg_res, TCGv_i64 tcg_src,
+ bool insert, int shift)
+{
+ if (insert) { /* SLI */
+ tcg_gen_deposit_i64(tcg_res, tcg_res, tcg_src, shift, 64 - shift);
+ } else { /* SHL */
+ tcg_gen_shli_i64(tcg_res, tcg_src, shift);
+ }
+}
+
+/* SSHR[RA]/USHR[RA] - Scalar shift right (optional rounding/accumulate) */
+static void handle_scalar_simd_shri(DisasContext *s,
+ bool is_u, int immh, int immb,
+ int opcode, int rn, int rd)
+{
+ const int size = 3;
+ int immhb = immh << 3 | immb;
+ int shift = 2 * (8 << size) - immhb;
+ bool accumulate = false;
+ bool round = false;
+ TCGv_i64 tcg_rn;
+ TCGv_i64 tcg_rd;
+ TCGv_i64 tcg_round;
+
+ if (!extract32(immh, 3, 1)) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ switch (opcode) {
+ case 0x02: /* SSRA / USRA (accumulate) */
+ accumulate = true;
+ break;
+ case 0x04: /* SRSHR / URSHR (rounding) */
+ round = true;
+ break;
+ case 0x06: /* SRSRA / URSRA (accum + rounding) */
+ accumulate = round = true;
+ break;
+ }
+
+ if (round) {
+ uint64_t round_const = 1ULL << (shift - 1);
+ tcg_round = tcg_const_i64(round_const);
+ } else {
+ TCGV_UNUSED_I64(tcg_round);
+ }
+
+ tcg_rn = read_fp_dreg(s, rn);
+ tcg_rd = accumulate ? read_fp_dreg(s, rd) : tcg_temp_new_i64();
+
+ handle_shri_with_rndacc(tcg_rd, tcg_rn, tcg_round,
+ accumulate, is_u, size, shift);
+
+ write_fp_dreg(s, rd, tcg_rd);
+
+ tcg_temp_free_i64(tcg_rn);
+ tcg_temp_free_i64(tcg_rd);
+ if (round) {
+ tcg_temp_free_i64(tcg_round);
+ }
+}
+
+/* SHL/SLI - Scalar shift left */
+static void handle_scalar_simd_shli(DisasContext *s, bool insert,
+ int immh, int immb, int opcode,
+ int rn, int rd)
+{
+ int size = 32 - clz32(immh) - 1;
+ int immhb = immh << 3 | immb;
+ int shift = immhb - (8 << size);
+ TCGv_i64 tcg_rn = new_tmp_a64(s);
+ TCGv_i64 tcg_rd = new_tmp_a64(s);
+
+ if (!extract32(immh, 3, 1)) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ tcg_rn = read_fp_dreg(s, rn);
+ tcg_rd = insert ? read_fp_dreg(s, rd) : tcg_temp_new_i64();
+
+ handle_shli_with_ins(tcg_rd, tcg_rn, insert, shift);
+
+ write_fp_dreg(s, rd, tcg_rd);
+
+ tcg_temp_free_i64(tcg_rn);
+ tcg_temp_free_i64(tcg_rd);
+}
+
+/* C3.6.9 AdvSIMD scalar shift by immediate
+ * 31 30 29 28 23 22 19 18 16 15 11 10 9 5 4 0
+ * +-----+---+-------------+------+------+--------+---+------+------+
+ * | 0 1 | U | 1 1 1 1 1 0 | immh | immb | opcode | 1 | Rn | Rd |
+ * +-----+---+-------------+------+------+--------+---+------+------+
+ *
+ * This is the scalar version so it works on a fixed sized registers
+ */
+static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int opcode = extract32(insn, 11, 5);
+ int immb = extract32(insn, 16, 3);
+ int immh = extract32(insn, 19, 4);
+ bool is_u = extract32(insn, 29, 1);
+
+ switch (opcode) {
+ case 0x00: /* SSHR / USHR */
+ case 0x02: /* SSRA / USRA */
+ case 0x04: /* SRSHR / URSHR */
+ case 0x06: /* SRSRA / URSRA */
+ handle_scalar_simd_shri(s, is_u, immh, immb, opcode, rn, rd);
+ break;
+ case 0x0a: /* SHL / SLI */
+ handle_scalar_simd_shli(s, is_u, immh, immb, opcode, rn, rd);
+ break;
+ default:
+ unsupported_encoding(s, insn);
+ break;
+ }
+}
+
+/* C3.6.10 AdvSIMD scalar three different
+ * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0
+ * +-----+---+-----------+------+---+------+--------+-----+------+------+
+ * | 0 1 | U | 1 1 1 1 0 | size | 1 | Rm | opcode | 0 0 | Rn | Rd |
+ * +-----+---+-----------+------+---+------+--------+-----+------+------+
+ */
+static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn)
+{
+ bool is_u = extract32(insn, 29, 1);
+ int size = extract32(insn, 22, 2);
+ int opcode = extract32(insn, 12, 4);
+ int rm = extract32(insn, 16, 5);
+ int rn = extract32(insn, 5, 5);
+ int rd = extract32(insn, 0, 5);
+
+ if (is_u) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ switch (opcode) {
+ case 0x9: /* SQDMLAL, SQDMLAL2 */
+ case 0xb: /* SQDMLSL, SQDMLSL2 */
+ case 0xd: /* SQDMULL, SQDMULL2 */
+ if (size == 0 || size == 3) {
+ unallocated_encoding(s);
+ return;
+ }
+ break;
+ default:
+ unallocated_encoding(s);
+ return;
+ }
+
+ if (size == 2) {
+ TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+ TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+ TCGv_i64 tcg_res = tcg_temp_new_i64();
+
+ read_vec_element(s, tcg_op1, rn, 0, MO_32 | MO_SIGN);
+ read_vec_element(s, tcg_op2, rm, 0, MO_32 | MO_SIGN);
+
+ tcg_gen_mul_i64(tcg_res, tcg_op1, tcg_op2);
+ gen_helper_neon_addl_saturate_s64(tcg_res, cpu_env, tcg_res, tcg_res);
+
+ switch (opcode) {
+ case 0xd: /* SQDMULL, SQDMULL2 */
+ break;
+ case 0xb: /* SQDMLSL, SQDMLSL2 */
+ tcg_gen_neg_i64(tcg_res, tcg_res);
+ /* fall through */
+ case 0x9: /* SQDMLAL, SQDMLAL2 */
+ read_vec_element(s, tcg_op1, rd, 0, MO_64);
+ gen_helper_neon_addl_saturate_s64(tcg_res, cpu_env,
+ tcg_res, tcg_op1);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ write_fp_dreg(s, rd, tcg_res);
+
+ tcg_temp_free_i64(tcg_op1);
+ tcg_temp_free_i64(tcg_op2);
+ tcg_temp_free_i64(tcg_res);
+ } else {
+ TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+ TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+ TCGv_i64 tcg_res = tcg_temp_new_i64();
+
+ read_vec_element_i32(s, tcg_op1, rn, 0, MO_16);
+ read_vec_element_i32(s, tcg_op2, rm, 0, MO_16);
+
+ gen_helper_neon_mull_s16(tcg_res, tcg_op1, tcg_op2);
+ gen_helper_neon_addl_saturate_s32(tcg_res, cpu_env, tcg_res, tcg_res);
+
+ switch (opcode) {
+ case 0xd: /* SQDMULL, SQDMULL2 */
+ break;
+ case 0xb: /* SQDMLSL, SQDMLSL2 */
+ gen_helper_neon_negl_u32(tcg_res, tcg_res);
+ /* fall through */
+ case 0x9: /* SQDMLAL, SQDMLAL2 */
+ {
+ TCGv_i64 tcg_op3 = tcg_temp_new_i64();
+ read_vec_element(s, tcg_op3, rd, 0, MO_32);
+ gen_helper_neon_addl_saturate_s32(tcg_res, cpu_env,
+ tcg_res, tcg_op3);
+ tcg_temp_free_i64(tcg_op3);
+ break;
+ }
+ default:
+ g_assert_not_reached();
+ }
+
+ tcg_gen_ext32u_i64(tcg_res, tcg_res);
+ write_fp_dreg(s, rd, tcg_res);
+
+ tcg_temp_free_i32(tcg_op1);
+ tcg_temp_free_i32(tcg_op2);
+ tcg_temp_free_i64(tcg_res);
+ }
+}
+
+static void handle_3same_64(DisasContext *s, int opcode, bool u,
+ TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, TCGv_i64 tcg_rm)
+{
+ /* Handle 64x64->64 opcodes which are shared between the scalar
+ * and vector 3-same groups. We cover every opcode where size == 3
+ * is valid in either the three-reg-same (integer, not pairwise)
+ * or scalar-three-reg-same groups. (Some opcodes are not yet
+ * implemented.)
+ */
+ TCGCond cond;
+
+ switch (opcode) {
+ case 0x1: /* SQADD */
+ if (u) {
+ gen_helper_neon_qadd_u64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_qadd_s64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ }
+ break;
+ case 0x5: /* SQSUB */
+ if (u) {
+ gen_helper_neon_qsub_u64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_qsub_s64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ }
+ break;
+ case 0x6: /* CMGT, CMHI */
+ /* 64 bit integer comparison, result = test ? (2^64 - 1) : 0.
+ * We implement this using setcond (test) and then negating.
+ */
+ cond = u ? TCG_COND_GTU : TCG_COND_GT;
+ do_cmop:
+ tcg_gen_setcond_i64(cond, tcg_rd, tcg_rn, tcg_rm);
+ tcg_gen_neg_i64(tcg_rd, tcg_rd);
+ break;
+ case 0x7: /* CMGE, CMHS */
+ cond = u ? TCG_COND_GEU : TCG_COND_GE;
+ goto do_cmop;
+ case 0x11: /* CMTST, CMEQ */
+ if (u) {
+ cond = TCG_COND_EQ;
+ goto do_cmop;
+ }
+ /* CMTST : test is "if (X & Y != 0)". */
+ tcg_gen_and_i64(tcg_rd, tcg_rn, tcg_rm);
+ tcg_gen_setcondi_i64(TCG_COND_NE, tcg_rd, tcg_rd, 0);
+ tcg_gen_neg_i64(tcg_rd, tcg_rd);
+ break;
+ case 0x8: /* SSHL, USHL */
+ if (u) {
+ gen_helper_neon_shl_u64(tcg_rd, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_shl_s64(tcg_rd, tcg_rn, tcg_rm);
+ }
+ break;
+ case 0x9: /* SQSHL, UQSHL */
+ if (u) {
+ gen_helper_neon_qshl_u64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_qshl_s64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ }
+ break;
+ case 0xa: /* SRSHL, URSHL */
+ if (u) {
+ gen_helper_neon_rshl_u64(tcg_rd, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_rshl_s64(tcg_rd, tcg_rn, tcg_rm);
+ }
+ break;
+ case 0xb: /* SQRSHL, UQRSHL */
+ if (u) {
+ gen_helper_neon_qrshl_u64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ } else {
+ gen_helper_neon_qrshl_s64(tcg_rd, cpu_env, tcg_rn, tcg_rm);
+ }
+ break;
+ case 0x10: /* ADD, SUB */
+ if (u) {
+ tcg_gen_sub_i64(tcg_rd, tcg_rn, tcg_rm);
+ } else {
+ tcg_gen_add_i64(tcg_rd, tcg_rn, tcg_rm);
+ }
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
+/* Handle the 3-same-operands float operations; shared by the scalar
+ * and vector encodings. The caller must filter out any encodings
+ * not allocated for the encoding it is dealing with.
+ */
+static void handle_3same_float(DisasContext *s, int size, int elements,
+ int fpopcode, int rd, int rn, int rm)
+{
+ int pass;
+ TCGv_ptr fpst = get_fpstatus_ptr();
+
+ for (pass = 0; pass < elements; pass++) {
+ if (size) {
+ /* Double */
+ TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+ TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+ TCGv_i64 tcg_res = tcg_temp_new_i64();
+
+ read_vec_element(s, tcg_op1, rn, pass, MO_64);
+ read_vec_element(s, tcg_op2, rm, pass, MO_64);
+
+ switch (fpopcode) {
+ case 0x39: /* FMLS */
+ /* As usual for ARM, separate negation for fused multiply-add */
+ gen_helper_vfp_negd(tcg_op1, tcg_op1);
+ /* fall through */
+ case 0x19: /* FMLA */
+ read_vec_element(s, tcg_res, rd, pass, MO_64);
+ gen_helper_vfp_muladdd(tcg_res, tcg_op1, tcg_op2,
+ tcg_res, fpst);
+ break;
+ case 0x18: /* FMAXNM */
+ gen_helper_vfp_maxnumd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1a: /* FADD */
+ gen_helper_vfp_addd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1b: /* FMULX */
+ gen_helper_vfp_mulxd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1c: /* FCMEQ */
+ gen_helper_neon_ceq_f64(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1e: /* FMAX */
+ gen_helper_vfp_maxd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1f: /* FRECPS */
+ gen_helper_recpsf_f64(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x38: /* FMINNM */
+ gen_helper_vfp_minnumd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x3a: /* FSUB */
+ gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x3e: /* FMIN */
+ gen_helper_vfp_mind(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x3f: /* FRSQRTS */
+ gen_helper_rsqrtsf_f64(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5b: /* FMUL */
+ gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5c: /* FCMGE */
+ gen_helper_neon_cge_f64(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5d: /* FACGE */
+ gen_helper_neon_acge_f64(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5f: /* FDIV */
+ gen_helper_vfp_divd(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x7a: /* FABD */
+ gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst);
+ gen_helper_vfp_absd(tcg_res, tcg_res);
+ break;
+ case 0x7c: /* FCMGT */
+ gen_helper_neon_cgt_f64(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x7d: /* FACGT */
+ gen_helper_neon_acgt_f64(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ write_vec_element(s, tcg_res, rd, pass, MO_64);
+
+ tcg_temp_free_i64(tcg_res);
+ tcg_temp_free_i64(tcg_op1);
+ tcg_temp_free_i64(tcg_op2);
+ } else {
+ /* Single */
+ TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+ TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+ TCGv_i32 tcg_res = tcg_temp_new_i32();
+
+ read_vec_element_i32(s, tcg_op1, rn, pass, MO_32);
+ read_vec_element_i32(s, tcg_op2, rm, pass, MO_32);
+
+ switch (fpopcode) {
+ case 0x39: /* FMLS */
+ /* As usual for ARM, separate negation for fused multiply-add */
+ gen_helper_vfp_negs(tcg_op1, tcg_op1);
+ /* fall through */
+ case 0x19: /* FMLA */
+ read_vec_element_i32(s, tcg_res, rd, pass, MO_32);
+ gen_helper_vfp_muladds(tcg_res, tcg_op1, tcg_op2,
+ tcg_res, fpst);
+ break;
+ case 0x1a: /* FADD */
+ gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1b: /* FMULX */
+ gen_helper_vfp_mulxs(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1c: /* FCMEQ */
+ gen_helper_neon_ceq_f32(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1e: /* FMAX */
+ gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1f: /* FRECPS */
+ gen_helper_recpsf_f32(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x18: /* FMAXNM */
+ gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x38: /* FMINNM */
+ gen_helper_vfp_minnums(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x3a: /* FSUB */
+ gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x3e: /* FMIN */
+ gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x3f: /* FRSQRTS */
+ gen_helper_rsqrtsf_f32(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5b: /* FMUL */
+ gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5c: /* FCMGE */
+ gen_helper_neon_cge_f32(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5d: /* FACGE */
+ gen_helper_neon_acge_f32(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5f: /* FDIV */
+ gen_helper_vfp_divs(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x7a: /* FABD */
+ gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst);
+ gen_helper_vfp_abss(tcg_res, tcg_res);
+ break;
+ case 0x7c: /* FCMGT */
+ gen_helper_neon_cgt_f32(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x7d: /* FACGT */
+ gen_helper_neon_acgt_f32(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ if (elements == 1) {
+ /* scalar single so clear high part */
+ TCGv_i64 tcg_tmp = tcg_temp_new_i64();
+
+ tcg_gen_extu_i32_i64(tcg_tmp, tcg_res);
+ write_vec_element(s, tcg_tmp, rd, pass, MO_64);
+ tcg_temp_free_i64(tcg_tmp);
+ } else {
+ write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
+ }
+
+ tcg_temp_free_i32(tcg_res);
+ tcg_temp_free_i32(tcg_op1);
+ tcg_temp_free_i32(tcg_op2);
+ }
+ }
+
+ tcg_temp_free_ptr(fpst);
+
+ if ((elements << size) < 4) {
+ /* scalar, or non-quad vector op */
+ clear_vec_high(s, rd);
+ }
+}
+
+/* C3.6.11 AdvSIMD scalar three same
+ * 31 30 29 28 24 23 22 21 20 16 15 11 10 9 5 4 0
+ * +-----+---+-----------+------+---+------+--------+---+------+------+
+ * | 0 1 | U | 1 1 1 1 0 | size | 1 | Rm | opcode | 1 | Rn | Rd |
+ * +-----+---+-----------+------+---+------+--------+---+------+------+
+ */
+static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int opcode = extract32(insn, 11, 5);
+ int rm = extract32(insn, 16, 5);
+ int size = extract32(insn, 22, 2);
+ bool u = extract32(insn, 29, 1);
+ TCGv_i64 tcg_rd;
+
+ if (opcode >= 0x18) {
+ /* Floating point: U, size[1] and opcode indicate operation */
+ int fpopcode = opcode | (extract32(size, 1, 1) << 5) | (u << 6);
+ switch (fpopcode) {
+ case 0x1b: /* FMULX */
+ case 0x1f: /* FRECPS */
+ case 0x3f: /* FRSQRTS */
+ case 0x5d: /* FACGE */
+ case 0x7d: /* FACGT */
+ case 0x1c: /* FCMEQ */
+ case 0x5c: /* FCMGE */
+ case 0x7c: /* FCMGT */
+ case 0x7a: /* FABD */
+ break;
+ default:
+ unallocated_encoding(s);
+ return;
+ }
+
+ handle_3same_float(s, extract32(size, 0, 1), 1, fpopcode, rd, rn, rm);
+ return;
+ }
+
+ switch (opcode) {
+ case 0x1: /* SQADD, UQADD */
+ case 0x5: /* SQSUB, UQSUB */
+ case 0x9: /* SQSHL, UQSHL */
+ case 0xb: /* SQRSHL, UQRSHL */
+ break;
+ case 0x8: /* SSHL, USHL */
+ case 0xa: /* SRSHL, URSHL */
+ case 0x6: /* CMGT, CMHI */
+ case 0x7: /* CMGE, CMHS */
+ case 0x11: /* CMTST, CMEQ */
+ case 0x10: /* ADD, SUB (vector) */
+ if (size != 3) {
+ unallocated_encoding(s);
+ return;
+ }
+ break;
+ case 0x16: /* SQDMULH, SQRDMULH (vector) */
+ if (size != 1 && size != 2) {
+ unallocated_encoding(s);
+ return;
+ }
+ break;
+ default:
+ unallocated_encoding(s);
+ return;
+ }
+
+ tcg_rd = tcg_temp_new_i64();
+
+ if (size == 3) {
+ TCGv_i64 tcg_rn = read_fp_dreg(s, rn);
+ TCGv_i64 tcg_rm = read_fp_dreg(s, rm);
+
+ handle_3same_64(s, opcode, u, tcg_rd, tcg_rn, tcg_rm);
+ tcg_temp_free_i64(tcg_rn);
+ tcg_temp_free_i64(tcg_rm);
+ } else {
+ /* Do a single operation on the lowest element in the vector.
+ * We use the standard Neon helpers and rely on 0 OP 0 == 0 with
+ * no side effects for all these operations.
+ * OPTME: special-purpose helpers would avoid doing some
+ * unnecessary work in the helper for the 8 and 16 bit cases.
+ */
+ NeonGenTwoOpEnvFn *genenvfn;
+ TCGv_i32 tcg_rn = tcg_temp_new_i32();
+ TCGv_i32 tcg_rm = tcg_temp_new_i32();
+ TCGv_i32 tcg_rd32 = tcg_temp_new_i32();
+
+ read_vec_element_i32(s, tcg_rn, rn, 0, size);
+ read_vec_element_i32(s, tcg_rm, rm, 0, size);
+
+ switch (opcode) {
+ case 0x1: /* SQADD, UQADD */
+ {
+ static NeonGenTwoOpEnvFn * const fns[3][2] = {
+ { gen_helper_neon_qadd_s8, gen_helper_neon_qadd_u8 },
+ { gen_helper_neon_qadd_s16, gen_helper_neon_qadd_u16 },
+ { gen_helper_neon_qadd_s32, gen_helper_neon_qadd_u32 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
+ case 0x5: /* SQSUB, UQSUB */
+ {
+ static NeonGenTwoOpEnvFn * const fns[3][2] = {
+ { gen_helper_neon_qsub_s8, gen_helper_neon_qsub_u8 },
+ { gen_helper_neon_qsub_s16, gen_helper_neon_qsub_u16 },
+ { gen_helper_neon_qsub_s32, gen_helper_neon_qsub_u32 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
+ case 0x9: /* SQSHL, UQSHL */
+ {
+ static NeonGenTwoOpEnvFn * const fns[3][2] = {
+ { gen_helper_neon_qshl_s8, gen_helper_neon_qshl_u8 },
+ { gen_helper_neon_qshl_s16, gen_helper_neon_qshl_u16 },
+ { gen_helper_neon_qshl_s32, gen_helper_neon_qshl_u32 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
+ case 0xb: /* SQRSHL, UQRSHL */
+ {
+ static NeonGenTwoOpEnvFn * const fns[3][2] = {
+ { gen_helper_neon_qrshl_s8, gen_helper_neon_qrshl_u8 },
+ { gen_helper_neon_qrshl_s16, gen_helper_neon_qrshl_u16 },
+ { gen_helper_neon_qrshl_s32, gen_helper_neon_qrshl_u32 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
+ case 0x16: /* SQDMULH, SQRDMULH */
+ {
+ static NeonGenTwoOpEnvFn * const fns[2][2] = {
+ { gen_helper_neon_qdmulh_s16, gen_helper_neon_qrdmulh_s16 },
+ { gen_helper_neon_qdmulh_s32, gen_helper_neon_qrdmulh_s32 },
+ };
+ assert(size == 1 || size == 2);
+ genenvfn = fns[size - 1][u];
+ break;
+ }
+ default:
+ g_assert_not_reached();
+ }
+
+ genenvfn(tcg_rd32, cpu_env, tcg_rn, tcg_rm);
+ tcg_gen_extu_i32_i64(tcg_rd, tcg_rd32);
+ tcg_temp_free_i32(tcg_rd32);
+ tcg_temp_free_i32(tcg_rn);
+ tcg_temp_free_i32(tcg_rm);
+ }
+
+ write_fp_dreg(s, rd, tcg_rd);
+
+ tcg_temp_free_i64(tcg_rd);
+}
+
+static void handle_2misc_64(DisasContext *s, int opcode, bool u,
+ TCGv_i64 tcg_rd, TCGv_i64 tcg_rn)
+{
+ /* Handle 64->64 opcodes which are shared between the scalar and
+ * vector 2-reg-misc groups. We cover every integer opcode where size == 3
+ * is valid in either group and also the double-precision fp ops.
+ */
+ TCGCond cond;
+
+ switch (opcode) {
+ case 0x5: /* NOT */
+ /* This opcode is shared with CNT and RBIT but we have earlier
+ * enforced that size == 3 if and only if this is the NOT insn.
+ */
+ tcg_gen_not_i64(tcg_rd, tcg_rn);
+ break;
+ case 0xa: /* CMLT */
+ /* 64 bit integer comparison against zero, result is
+ * test ? (2^64 - 1) : 0. We implement via setcond(!test) and
+ * subtracting 1.
+ */
+ cond = TCG_COND_LT;
+ do_cmop:
+ tcg_gen_setcondi_i64(cond, tcg_rd, tcg_rn, 0);
+ tcg_gen_neg_i64(tcg_rd, tcg_rd);
+ break;
+ case 0x8: /* CMGT, CMGE */
+ cond = u ? TCG_COND_GE : TCG_COND_GT;
+ goto do_cmop;
+ case 0x9: /* CMEQ, CMLE */
+ cond = u ? TCG_COND_LE : TCG_COND_EQ;
+ goto do_cmop;
+ case 0xb: /* ABS, NEG */
+ if (u) {
+ tcg_gen_neg_i64(tcg_rd, tcg_rn);
+ } else {
+ TCGv_i64 tcg_zero = tcg_const_i64(0);
+ tcg_gen_neg_i64(tcg_rd, tcg_rn);
+ tcg_gen_movcond_i64(TCG_COND_GT, tcg_rd, tcg_rn, tcg_zero,
+ tcg_rn, tcg_rd);
+ tcg_temp_free_i64(tcg_zero);
+ }
+ break;
+ case 0x2f: /* FABS */
+ gen_helper_vfp_absd(tcg_rd, tcg_rn);
+ break;
+ case 0x6f: /* FNEG */
+ gen_helper_vfp_negd(tcg_rd, tcg_rn);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
+static void handle_2misc_fcmp_zero(DisasContext *s, int opcode,
+ bool is_scalar, bool is_u, bool is_q,
+ int size, int rn, int rd)
+{
+ bool is_double = (size == 3);
+ TCGv_ptr fpst = get_fpstatus_ptr();
+
+ if (is_double) {
+ TCGv_i64 tcg_op = tcg_temp_new_i64();
+ TCGv_i64 tcg_zero = tcg_const_i64(0);
+ TCGv_i64 tcg_res = tcg_temp_new_i64();
+ NeonGenTwoDoubleOPFn *genfn;
+ bool swap = false;
+ int pass;
+
+ switch (opcode) {
+ case 0x2e: /* FCMLT (zero) */
+ swap = true;
+ /* fallthrough */
+ case 0x2c: /* FCMGT (zero) */
+ genfn = gen_helper_neon_cgt_f64;
+ break;
+ case 0x2d: /* FCMEQ (zero) */
+ genfn = gen_helper_neon_ceq_f64;
+ break;
+ case 0x6d: /* FCMLE (zero) */
+ swap = true;
+ /* fall through */
+ case 0x6c: /* FCMGE (zero) */
+ genfn = gen_helper_neon_cge_f64;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) {
+ read_vec_element(s, tcg_op, rn, pass, MO_64);
+ if (swap) {
+ genfn(tcg_res, tcg_zero, tcg_op, fpst);
+ } else {
+ genfn(tcg_res, tcg_op, tcg_zero, fpst);
+ }
+ write_vec_element(s, tcg_res, rd, pass, MO_64);
+ }
+ if (is_scalar) {
+ clear_vec_high(s, rd);
+ }
+
+ tcg_temp_free_i64(tcg_res);
+ tcg_temp_free_i64(tcg_zero);
+ tcg_temp_free_i64(tcg_op);
+ } else {
+ TCGv_i32 tcg_op = tcg_temp_new_i32();
+ TCGv_i32 tcg_zero = tcg_const_i32(0);
+ TCGv_i32 tcg_res = tcg_temp_new_i32();
+ NeonGenTwoSingleOPFn *genfn;
+ bool swap = false;
+ int pass, maxpasses;
+
+ switch (opcode) {
+ case 0x2e: /* FCMLT (zero) */
+ swap = true;
+ /* fall through */
+ case 0x2c: /* FCMGT (zero) */
+ genfn = gen_helper_neon_cgt_f32;
+ break;
+ case 0x2d: /* FCMEQ (zero) */
+ genfn = gen_helper_neon_ceq_f32;
+ break;
+ case 0x6d: /* FCMLE (zero) */
+ swap = true;
+ /* fall through */
+ case 0x6c: /* FCMGE (zero) */
+ genfn = gen_helper_neon_cge_f32;
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ if (is_scalar) {
+ maxpasses = 1;
+ } else {
+ maxpasses = is_q ? 4 : 2;
+ }
+
+ for (pass = 0; pass < maxpasses; pass++) {
+ read_vec_element_i32(s, tcg_op, rn, pass, MO_32);
+ if (swap) {
+ genfn(tcg_res, tcg_zero, tcg_op, fpst);
+ } else {
+ genfn(tcg_res, tcg_op, tcg_zero, fpst);
+ }
+ if (is_scalar) {
+ write_fp_sreg(s, rd, tcg_res);
+ } else {
+ write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
+ }
+ }
+ tcg_temp_free_i32(tcg_res);
+ tcg_temp_free_i32(tcg_zero);
+ tcg_temp_free_i32(tcg_op);
+ if (!is_q && !is_scalar) {
+ clear_vec_high(s, rd);
+ }
+ }
+
+ tcg_temp_free_ptr(fpst);
+}
+
+/* C3.6.12 AdvSIMD scalar two reg misc
+ * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0
+ * +-----+---+-----------+------+-----------+--------+-----+------+------+
+ * | 0 1 | U | 1 1 1 1 0 | size | 1 0 0 0 0 | opcode | 1 0 | Rn | Rd |
+ * +-----+---+-----------+------+-----------+--------+-----+------+------+
+ */
+static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int opcode = extract32(insn, 12, 5);
+ int size = extract32(insn, 22, 2);
+ bool u = extract32(insn, 29, 1);
+
+ switch (opcode) {
+ case 0xa: /* CMLT */
+ if (u) {
+ unallocated_encoding(s);
+ return;
+ }
+ /* fall through */
+ case 0x8: /* CMGT, CMGE */
+ case 0x9: /* CMEQ, CMLE */
+ case 0xb: /* ABS, NEG */
+ if (size != 3) {
+ unallocated_encoding(s);
+ return;
+ }
+ break;
+ case 0xc ... 0xf:
+ case 0x16 ... 0x1d:
+ case 0x1f:
+ /* Floating point: U, size[1] and opcode indicate operation;
+ * size[0] indicates single or double precision.
+ */
+ opcode |= (extract32(size, 1, 1) << 5) | (u << 6);
+ size = extract32(size, 0, 1) ? 3 : 2;
+ switch (opcode) {
+ case 0x2c: /* FCMGT (zero) */
+ case 0x2d: /* FCMEQ (zero) */
+ case 0x2e: /* FCMLT (zero) */
+ case 0x6c: /* FCMGE (zero) */
+ case 0x6d: /* FCMLE (zero) */
+ handle_2misc_fcmp_zero(s, opcode, true, u, true, size, rn, rd);
+ return;
+ case 0x1a: /* FCVTNS */
+ case 0x1b: /* FCVTMS */
+ case 0x1c: /* FCVTAS */
+ case 0x1d: /* SCVTF */
+ case 0x3a: /* FCVTPS */
+ case 0x3b: /* FCVTZS */
+ case 0x3d: /* FRECPE */
+ case 0x3f: /* FRECPX */
+ case 0x56: /* FCVTXN, FCVTXN2 */
+ case 0x5a: /* FCVTNU */
+ case 0x5b: /* FCVTMU */
+ case 0x5c: /* FCVTAU */
+ case 0x5d: /* UCVTF */
+ case 0x7a: /* FCVTPU */
+ case 0x7b: /* FCVTZU */
+ case 0x7d: /* FRSQRTE */
+ unsupported_encoding(s, insn);
+ return;
+ default:
+ unallocated_encoding(s);
+ return;
+ }
+ break;
+ default:
+ /* Other categories of encoding in this class:
+ * + SUQADD/USQADD/SQABS/SQNEG : size 8, 16, 32 or 64
+ * + SQXTN/SQXTN2/SQXTUN/SQXTUN2/UQXTN/UQXTN2:
+ * narrowing saturate ops: size 64/32/16 -> 32/16/8
+ */
+ unsupported_encoding(s, insn);
+ return;
+ }
+
+ if (size == 3) {
+ TCGv_i64 tcg_rn = read_fp_dreg(s, rn);
+ TCGv_i64 tcg_rd = tcg_temp_new_i64();
+
+ handle_2misc_64(s, opcode, u, tcg_rd, tcg_rn);
+ write_fp_dreg(s, rd, tcg_rd);
+ tcg_temp_free_i64(tcg_rd);
+ tcg_temp_free_i64(tcg_rn);
+ } else {
+ /* the 'size might not be 64' ops aren't implemented yet */
+ g_assert_not_reached();
+ }
+}
+
+/* SSHR[RA]/USHR[RA] - Vector shift right (optional rounding/accumulate) */
+static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u,
+ int immh, int immb, int opcode, int rn, int rd)
+{
+ int size = 32 - clz32(immh) - 1;
+ int immhb = immh << 3 | immb;
+ int shift = 2 * (8 << size) - immhb;
+ bool accumulate = false;
+ bool round = false;
+ int dsize = is_q ? 128 : 64;
+ int esize = 8 << size;
+ int elements = dsize/esize;
+ TCGMemOp memop = size | (is_u ? 0 : MO_SIGN);
+ TCGv_i64 tcg_rn = new_tmp_a64(s);
+ TCGv_i64 tcg_rd = new_tmp_a64(s);
+ TCGv_i64 tcg_round;
+ int i;
+
+ if (extract32(immh, 3, 1) && !is_q) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ if (size > 3 && !is_q) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ switch (opcode) {
+ case 0x02: /* SSRA / USRA (accumulate) */
+ accumulate = true;
+ break;
+ case 0x04: /* SRSHR / URSHR (rounding) */
+ round = true;
+ break;
+ case 0x06: /* SRSRA / URSRA (accum + rounding) */
+ accumulate = round = true;
+ break;
+ }
+
+ if (round) {
+ uint64_t round_const = 1ULL << (shift - 1);
+ tcg_round = tcg_const_i64(round_const);
+ } else {
+ TCGV_UNUSED_I64(tcg_round);
+ }
+
+ for (i = 0; i < elements; i++) {
+ read_vec_element(s, tcg_rn, rn, i, memop);
+ if (accumulate) {
+ read_vec_element(s, tcg_rd, rd, i, memop);
+ }
+
+ handle_shri_with_rndacc(tcg_rd, tcg_rn, tcg_round,
+ accumulate, is_u, size, shift);
+
+ write_vec_element(s, tcg_rd, rd, i, size);
+ }
+
+ if (!is_q) {
+ clear_vec_high(s, rd);
+ }
+
+ if (round) {
+ tcg_temp_free_i64(tcg_round);
+ }
+}
+
+/* SHL/SLI - Vector shift left */
+static void handle_vec_simd_shli(DisasContext *s, bool is_q, bool insert,
+ int immh, int immb, int opcode, int rn, int rd)
+{
+ int size = 32 - clz32(immh) - 1;
+ int immhb = immh << 3 | immb;
+ int shift = immhb - (8 << size);
+ int dsize = is_q ? 128 : 64;
+ int esize = 8 << size;
+ int elements = dsize/esize;
+ TCGv_i64 tcg_rn = new_tmp_a64(s);
+ TCGv_i64 tcg_rd = new_tmp_a64(s);
+ int i;
+
+ if (extract32(immh, 3, 1) && !is_q) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ if (size > 3 && !is_q) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ for (i = 0; i < elements; i++) {
+ read_vec_element(s, tcg_rn, rn, i, size);
+ if (insert) {
+ read_vec_element(s, tcg_rd, rd, i, size);
+ }
+
+ handle_shli_with_ins(tcg_rd, tcg_rn, insert, shift);
+
+ write_vec_element(s, tcg_rd, rd, i, size);
+ }
+
+ if (!is_q) {
+ clear_vec_high(s, rd);
+ }
+}
+
+/* USHLL/SHLL - Vector shift left with widening */
+static void handle_vec_simd_wshli(DisasContext *s, bool is_q, bool is_u,
+ int immh, int immb, int opcode, int rn, int rd)
+{
+ int size = 32 - clz32(immh) - 1;
+ int immhb = immh << 3 | immb;
+ int shift = immhb - (8 << size);
+ int dsize = 64;
+ int esize = 8 << size;
+ int elements = dsize/esize;
+ TCGv_i64 tcg_rn = new_tmp_a64(s);
+ TCGv_i64 tcg_rd = new_tmp_a64(s);
+ int i;
+
+ if (size >= 3) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ /* For the LL variants the store is larger than the load,
+ * so if rd == rn we would overwrite parts of our input.
+ * So load everything right now and use shifts in the main loop.
+ */
+ read_vec_element(s, tcg_rn, rn, is_q ? 1 : 0, MO_64);
+
+ for (i = 0; i < elements; i++) {
+ tcg_gen_shri_i64(tcg_rd, tcg_rn, i * esize);
+ ext_and_shift_reg(tcg_rd, tcg_rd, size | (!is_u << 2), 0);
+ tcg_gen_shli_i64(tcg_rd, tcg_rd, shift);
+ write_vec_element(s, tcg_rd, rd, i, size + 1);
+ }
+}
+
+
+/* C3.6.14 AdvSIMD shift by immediate
+ * 31 30 29 28 23 22 19 18 16 15 11 10 9 5 4 0
+ * +---+---+---+-------------+------+------+--------+---+------+------+
+ * | 0 | Q | U | 0 1 1 1 1 0 | immh | immb | opcode | 1 | Rn | Rd |
+ * +---+---+---+-------------+------+------+--------+---+------+------+
+ */
+static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int opcode = extract32(insn, 11, 5);
+ int immb = extract32(insn, 16, 3);
+ int immh = extract32(insn, 19, 4);
+ bool is_u = extract32(insn, 29, 1);
+ bool is_q = extract32(insn, 30, 1);
+
+ switch (opcode) {
+ case 0x00: /* SSHR / USHR */
+ case 0x02: /* SSRA / USRA (accumulate) */
+ case 0x04: /* SRSHR / URSHR (rounding) */
+ case 0x06: /* SRSRA / URSRA (accum + rounding) */
+ handle_vec_simd_shri(s, is_q, is_u, immh, immb, opcode, rn, rd);
+ break;
+ case 0x0a: /* SHL / SLI */
+ handle_vec_simd_shli(s, is_q, is_u, immh, immb, opcode, rn, rd);
+ break;
+ case 0x14: /* SSHLL / USHLL */
+ handle_vec_simd_wshli(s, is_q, is_u, immh, immb, opcode, rn, rd);
+ break;
+ default:
+ /* We don't currently implement any of the Narrow or saturating shifts;
+ * nor do we implement the fixed-point conversions in this
+ * encoding group (SCVTF, FCVTZS, UCVTF, FCVTZU).
+ */
+ unsupported_encoding(s, insn);
+ return;
+ }
+}
+
+static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size,
+ int opcode, int rd, int rn, int rm)
+{
+ /* 3-reg-different widening insns: 64 x 64 -> 128 */
+ TCGv_i64 tcg_res[2];
+ int pass, accop;
+
+ tcg_res[0] = tcg_temp_new_i64();
+ tcg_res[1] = tcg_temp_new_i64();
+
+ /* Does this op do an adding accumulate, a subtracting accumulate,
+ * or no accumulate at all?
+ */
+ switch (opcode) {
+ case 5:
+ case 8:
+ case 9:
+ accop = 1;
+ break;
+ case 10:
+ case 11:
+ accop = -1;
+ break;
+ default:
+ accop = 0;
+ break;
+ }
+
+ if (accop != 0) {
+ read_vec_element(s, tcg_res[0], rd, 0, MO_64);
+ read_vec_element(s, tcg_res[1], rd, 1, MO_64);
+ }
+
+ /* size == 2 means two 32x32->64 operations; this is worth special
+ * casing because we can generally handle it inline.
+ */
+ if (size == 2) {
+ for (pass = 0; pass < 2; pass++) {
+ TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+ TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+ TCGv_i64 tcg_passres;
+ TCGMemOp memop = MO_32 | (is_u ? 0 : MO_SIGN);
+
+ int elt = pass + is_q * 2;
+
+ read_vec_element(s, tcg_op1, rn, elt, memop);
+ read_vec_element(s, tcg_op2, rm, elt, memop);
+
+ if (accop == 0) {
+ tcg_passres = tcg_res[pass];
+ } else {
+ tcg_passres = tcg_temp_new_i64();
+ }
+
+ switch (opcode) {
+ case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
+ case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
+ {
+ TCGv_i64 tcg_tmp1 = tcg_temp_new_i64();
+ TCGv_i64 tcg_tmp2 = tcg_temp_new_i64();
+
+ tcg_gen_sub_i64(tcg_tmp1, tcg_op1, tcg_op2);
+ tcg_gen_sub_i64(tcg_tmp2, tcg_op2, tcg_op1);
+ tcg_gen_movcond_i64(is_u ? TCG_COND_GEU : TCG_COND_GE,
+ tcg_passres,
+ tcg_op1, tcg_op2, tcg_tmp1, tcg_tmp2);
+ tcg_temp_free_i64(tcg_tmp1);
+ tcg_temp_free_i64(tcg_tmp2);
+ break;
+ }
+ case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
+ case 10: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
+ case 12: /* UMULL, UMULL2, SMULL, SMULL2 */
+ tcg_gen_mul_i64(tcg_passres, tcg_op1, tcg_op2);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ if (accop > 0) {
+ tcg_gen_add_i64(tcg_res[pass], tcg_res[pass], tcg_passres);
+ tcg_temp_free_i64(tcg_passres);
+ } else if (accop < 0) {
+ tcg_gen_sub_i64(tcg_res[pass], tcg_res[pass], tcg_passres);
+ tcg_temp_free_i64(tcg_passres);
+ }
+
+ tcg_temp_free_i64(tcg_op1);
+ tcg_temp_free_i64(tcg_op2);
+ }
+ } else {
+ /* size 0 or 1, generally helper functions */
+ for (pass = 0; pass < 2; pass++) {
+ TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+ TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+ TCGv_i64 tcg_passres;
+ int elt = pass + is_q * 2;
+
+ read_vec_element_i32(s, tcg_op1, rn, elt, MO_32);
+ read_vec_element_i32(s, tcg_op2, rm, elt, MO_32);
+
+ if (accop == 0) {
+ tcg_passres = tcg_res[pass];
+ } else {
+ tcg_passres = tcg_temp_new_i64();
+ }
+
+ switch (opcode) {
+ case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
+ case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
+ if (size == 0) {
+ if (is_u) {
+ gen_helper_neon_abdl_u16(tcg_passres, tcg_op1, tcg_op2);
+ } else {
+ gen_helper_neon_abdl_s16(tcg_passres, tcg_op1, tcg_op2);
+ }
+ } else {
+ if (is_u) {
+ gen_helper_neon_abdl_u32(tcg_passres, tcg_op1, tcg_op2);
+ } else {
+ gen_helper_neon_abdl_s32(tcg_passres, tcg_op1, tcg_op2);
+ }
+ }
+ break;
+ case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
+ case 10: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
+ case 12: /* UMULL, UMULL2, SMULL, SMULL2 */
+ if (size == 0) {
+ if (is_u) {
+ gen_helper_neon_mull_u8(tcg_passres, tcg_op1, tcg_op2);
+ } else {
+ gen_helper_neon_mull_s8(tcg_passres, tcg_op1, tcg_op2);
+ }
+ } else {
+ if (is_u) {
+ gen_helper_neon_mull_u16(tcg_passres, tcg_op1, tcg_op2);
+ } else {
+ gen_helper_neon_mull_s16(tcg_passres, tcg_op1, tcg_op2);
+ }
+ }
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ tcg_temp_free_i32(tcg_op1);
+ tcg_temp_free_i32(tcg_op2);
+
+ if (accop > 0) {
+ if (size == 0) {
+ gen_helper_neon_addl_u16(tcg_res[pass], tcg_res[pass],
+ tcg_passres);
+ } else {
+ gen_helper_neon_addl_u32(tcg_res[pass], tcg_res[pass],
+ tcg_passres);
+ }
+ tcg_temp_free_i64(tcg_passres);
+ } else if (accop < 0) {
+ if (size == 0) {
+ gen_helper_neon_subl_u16(tcg_res[pass], tcg_res[pass],
+ tcg_passres);
+ } else {
+ gen_helper_neon_subl_u32(tcg_res[pass], tcg_res[pass],
+ tcg_passres);
+ }
+ tcg_temp_free_i64(tcg_passres);
+ }
+ }
+ }
+
+ write_vec_element(s, tcg_res[0], rd, 0, MO_64);
+ write_vec_element(s, tcg_res[1], rd, 1, MO_64);
+ tcg_temp_free_i64(tcg_res[0]);
+ tcg_temp_free_i64(tcg_res[1]);
+}
+
+/* C3.6.15 AdvSIMD three different
+ * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0
+ * +---+---+---+-----------+------+---+------+--------+-----+------+------+
+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 | Rm | opcode | 0 0 | Rn | Rd |
+ * +---+---+---+-----------+------+---+------+--------+-----+------+------+
+ */
+static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn)
+{
+ /* Instructions in this group fall into three basic classes
+ * (in each case with the operation working on each element in
+ * the input vectors):
+ * (1) widening 64 x 64 -> 128 (with possibly Vd as an extra
+ * 128 bit input)
+ * (2) wide 64 x 128 -> 128
+ * (3) narrowing 128 x 128 -> 64
+ * Here we do initial decode, catch unallocated cases and
+ * dispatch to separate functions for each class.
+ */
+ int is_q = extract32(insn, 30, 1);
+ int is_u = extract32(insn, 29, 1);
+ int size = extract32(insn, 22, 2);
+ int opcode = extract32(insn, 12, 4);
+ int rm = extract32(insn, 16, 5);
+ int rn = extract32(insn, 5, 5);
+ int rd = extract32(insn, 0, 5);
+
+ switch (opcode) {
+ case 1: /* SADDW, SADDW2, UADDW, UADDW2 */
+ case 3: /* SSUBW, SSUBW2, USUBW, USUBW2 */
+ /* 64 x 128 -> 128 */
+ unsupported_encoding(s, insn);
+ break;
+ case 4: /* ADDHN, ADDHN2, RADDHN, RADDHN2 */
+ case 6: /* SUBHN, SUBHN2, RSUBHN, RSUBHN2 */
+ /* 128 x 128 -> 64 */
+ unsupported_encoding(s, insn);
+ break;
+ case 9:
+ case 11:
+ case 13:
+ case 14:
+ if (is_u) {
+ unallocated_encoding(s);
+ return;
+ }
+ /* fall through */
+ case 0:
+ case 2:
+ unsupported_encoding(s, insn);
+ break;
+ case 5:
+ case 7:
+ case 8:
+ case 10:
+ case 12:
+ /* 64 x 64 -> 128 */
+ if (size == 3) {
+ unallocated_encoding(s);
+ return;
+ }
+ handle_3rd_widening(s, is_q, is_u, size, opcode, rd, rn, rm);
+ break;
+ default:
+ /* opcode 15 not allocated */
+ unallocated_encoding(s);
+ break;
+ }
+}
+
+/* Logic op (opcode == 3) subgroup of C3.6.16. */
+static void disas_simd_3same_logic(DisasContext *s, uint32_t insn)
+{
+ int rd = extract32(insn, 0, 5);
+ int rn = extract32(insn, 5, 5);
+ int rm = extract32(insn, 16, 5);
+ int size = extract32(insn, 22, 2);
+ bool is_u = extract32(insn, 29, 1);
+ bool is_q = extract32(insn, 30, 1);
+ TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+ TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+ TCGv_i64 tcg_res[2];
+ int pass;
+
+ tcg_res[0] = tcg_temp_new_i64();
+ tcg_res[1] = tcg_temp_new_i64();
+
+ for (pass = 0; pass < (is_q ? 2 : 1); pass++) {
+ read_vec_element(s, tcg_op1, rn, pass, MO_64);
+ read_vec_element(s, tcg_op2, rm, pass, MO_64);
+
+ if (!is_u) {
+ switch (size) {
+ case 0: /* AND */
+ tcg_gen_and_i64(tcg_res[pass], tcg_op1, tcg_op2);
+ break;
+ case 1: /* BIC */
+ tcg_gen_andc_i64(tcg_res[pass], tcg_op1, tcg_op2);
+ break;
+ case 2: /* ORR */
+ tcg_gen_or_i64(tcg_res[pass], tcg_op1, tcg_op2);
+ break;
+ case 3: /* ORN */
+ tcg_gen_orc_i64(tcg_res[pass], tcg_op1, tcg_op2);
+ break;
+ }
+ } else {
+ if (size != 0) {
+ /* B* ops need res loaded to operate on */
+ read_vec_element(s, tcg_res[pass], rd, pass, MO_64);
+ }
+
+ switch (size) {
+ case 0: /* EOR */
+ tcg_gen_xor_i64(tcg_res[pass], tcg_op1, tcg_op2);
+ break;
+ case 1: /* BSL bitwise select */
+ tcg_gen_xor_i64(tcg_op1, tcg_op1, tcg_op2);
+ tcg_gen_and_i64(tcg_op1, tcg_op1, tcg_res[pass]);
+ tcg_gen_xor_i64(tcg_res[pass], tcg_op2, tcg_op1);
+ break;
+ case 2: /* BIT, bitwise insert if true */
+ tcg_gen_xor_i64(tcg_op1, tcg_op1, tcg_res[pass]);
+ tcg_gen_and_i64(tcg_op1, tcg_op1, tcg_op2);
+ tcg_gen_xor_i64(tcg_res[pass], tcg_res[pass], tcg_op1);
+ break;
+ case 3: /* BIF, bitwise insert if false */
+ tcg_gen_xor_i64(tcg_op1, tcg_op1, tcg_res[pass]);
+ tcg_gen_andc_i64(tcg_op1, tcg_op1, tcg_op2);
+ tcg_gen_xor_i64(tcg_res[pass], tcg_res[pass], tcg_op1);
+ break;
+ }
+ }
+ }
+
+ write_vec_element(s, tcg_res[0], rd, 0, MO_64);
+ if (!is_q) {
+ tcg_gen_movi_i64(tcg_res[1], 0);
+ }
+ write_vec_element(s, tcg_res[1], rd, 1, MO_64);
+
+ tcg_temp_free_i64(tcg_op1);
+ tcg_temp_free_i64(tcg_op2);
+ tcg_temp_free_i64(tcg_res[0]);
+ tcg_temp_free_i64(tcg_res[1]);
+}
+
+/* Helper functions for 32 bit comparisons */
+static void gen_max_s32(TCGv_i32 res, TCGv_i32 op1, TCGv_i32 op2)
+{
+ tcg_gen_movcond_i32(TCG_COND_GE, res, op1, op2, op1, op2);
+}
+
+static void gen_max_u32(TCGv_i32 res, TCGv_i32 op1, TCGv_i32 op2)
+{
+ tcg_gen_movcond_i32(TCG_COND_GEU, res, op1, op2, op1, op2);
+}
+
+static void gen_min_s32(TCGv_i32 res, TCGv_i32 op1, TCGv_i32 op2)
+{
+ tcg_gen_movcond_i32(TCG_COND_LE, res, op1, op2, op1, op2);
+}
+
+static void gen_min_u32(TCGv_i32 res, TCGv_i32 op1, TCGv_i32 op2)
+{
+ tcg_gen_movcond_i32(TCG_COND_LEU, res, op1, op2, op1, op2);
+}
+
+/* Pairwise op subgroup of C3.6.16.
+ *
+ * This is called directly or via the handle_3same_float for float pairwise
+ * operations where the opcode and size are calculated differently.
+ */
+static void handle_simd_3same_pair(DisasContext *s, int is_q, int u, int opcode,
+ int size, int rn, int rm, int rd)
+{
+ TCGv_ptr fpst;
+ int pass;
+
+ /* Floating point operations need fpst */
+ if (opcode >= 0x58) {
+ fpst = get_fpstatus_ptr();
+ } else {
+ TCGV_UNUSED_PTR(fpst);
+ }
+
+ /* These operations work on the concatenated rm:rn, with each pair of
+ * adjacent elements being operated on to produce an element in the result.
+ */
+ if (size == 3) {
+ TCGv_i64 tcg_res[2];
+
+ for (pass = 0; pass < 2; pass++) {
+ TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+ TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+ int passreg = (pass == 0) ? rn : rm;
+
+ read_vec_element(s, tcg_op1, passreg, 0, MO_64);
+ read_vec_element(s, tcg_op2, passreg, 1, MO_64);
+ tcg_res[pass] = tcg_temp_new_i64();
+
+ switch (opcode) {
+ case 0x17: /* ADDP */
+ tcg_gen_add_i64(tcg_res[pass], tcg_op1, tcg_op2);
+ break;
+ case 0x58: /* FMAXNMP */
+ gen_helper_vfp_maxnumd(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5a: /* FADDP */
+ gen_helper_vfp_addd(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5e: /* FMAXP */
+ gen_helper_vfp_maxd(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x78: /* FMINNMP */
+ gen_helper_vfp_minnumd(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x7e: /* FMINP */
+ gen_helper_vfp_mind(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ tcg_temp_free_i64(tcg_op1);
+ tcg_temp_free_i64(tcg_op2);
+ }
+
+ for (pass = 0; pass < 2; pass++) {
+ write_vec_element(s, tcg_res[pass], rd, pass, MO_64);
+ tcg_temp_free_i64(tcg_res[pass]);
+ }
+ } else {
+ int maxpass = is_q ? 4 : 2;
+ TCGv_i32 tcg_res[4];
+
+ for (pass = 0; pass < maxpass; pass++) {
+ TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+ TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+ NeonGenTwoOpFn *genfn = NULL;
+ int passreg = pass < (maxpass / 2) ? rn : rm;
+ int passelt = (is_q && (pass & 1)) ? 2 : 0;
+
+ read_vec_element_i32(s, tcg_op1, passreg, passelt, MO_32);
+ read_vec_element_i32(s, tcg_op2, passreg, passelt + 1, MO_32);
+ tcg_res[pass] = tcg_temp_new_i32();
+
+ switch (opcode) {
+ case 0x17: /* ADDP */
+ {
+ static NeonGenTwoOpFn * const fns[3] = {
+ gen_helper_neon_padd_u8,
+ gen_helper_neon_padd_u16,
+ tcg_gen_add_i32,
+ };
+ genfn = fns[size];
+ break;
+ }
+ case 0x14: /* SMAXP, UMAXP */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_pmax_s8, gen_helper_neon_pmax_u8 },
+ { gen_helper_neon_pmax_s16, gen_helper_neon_pmax_u16 },
+ { gen_max_s32, gen_max_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x15: /* SMINP, UMINP */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_pmin_s8, gen_helper_neon_pmin_u8 },
+ { gen_helper_neon_pmin_s16, gen_helper_neon_pmin_u16 },
+ { gen_min_s32, gen_min_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ /* The FP operations are all on single floats (32 bit) */
+ case 0x58: /* FMAXNMP */
+ gen_helper_vfp_maxnums(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5a: /* FADDP */
+ gen_helper_vfp_adds(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x5e: /* FMAXP */
+ gen_helper_vfp_maxs(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x78: /* FMINNMP */
+ gen_helper_vfp_minnums(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x7e: /* FMINP */
+ gen_helper_vfp_mins(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+
+ /* FP ops called directly, otherwise call now */
+ if (genfn) {
+ genfn(tcg_res[pass], tcg_op1, tcg_op2);
+ }
+
+ tcg_temp_free_i32(tcg_op1);
+ tcg_temp_free_i32(tcg_op2);
+ }
+
+ for (pass = 0; pass < maxpass; pass++) {
+ write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_32);
+ tcg_temp_free_i32(tcg_res[pass]);
+ }
+ if (!is_q) {
+ clear_vec_high(s, rd);
+ }
+ }
+
+ if (!TCGV_IS_UNUSED_PTR(fpst)) {
+ tcg_temp_free_ptr(fpst);
+ }
+}
+
+/* Floating point op subgroup of C3.6.16. */
+static void disas_simd_3same_float(DisasContext *s, uint32_t insn)
+{
+ /* For floating point ops, the U, size[1] and opcode bits
+ * together indicate the operation. size[0] indicates single
+ * or double.
+ */
+ int fpopcode = extract32(insn, 11, 5)
+ | (extract32(insn, 23, 1) << 5)
+ | (extract32(insn, 29, 1) << 6);
+ int is_q = extract32(insn, 30, 1);
+ int size = extract32(insn, 22, 1);
+ int rm = extract32(insn, 16, 5);
+ int rn = extract32(insn, 5, 5);
+ int rd = extract32(insn, 0, 5);
+
+ int datasize = is_q ? 128 : 64;
+ int esize = 32 << size;
+ int elements = datasize / esize;
+
+ if (size == 1 && !is_q) {
+ unallocated_encoding(s);
+ return;
+ }
+
+ switch (fpopcode) {
+ case 0x58: /* FMAXNMP */
+ case 0x5a: /* FADDP */
+ case 0x5e: /* FMAXP */
+ case 0x78: /* FMINNMP */
+ case 0x7e: /* FMINP */
+ if (size && !is_q) {
+ unallocated_encoding(s);
+ return;
+ }
+ handle_simd_3same_pair(s, is_q, 0, fpopcode, size ? MO_64 : MO_32,
+ rn, rm, rd);
+ return;
+ case 0x1b: /* FMULX */
+ case 0x1f: /* FRECPS */
+ case 0x3f: /* FRSQRTS */
+ case 0x5d: /* FACGE */
+ case 0x7d: /* FACGT */
+ case 0x19: /* FMLA */
+ case 0x39: /* FMLS */
+ case 0x18: /* FMAXNM */
+ case 0x1a: /* FADD */
+ case 0x1c: /* FCMEQ */
+ case 0x1e: /* FMAX */
+ case 0x38: /* FMINNM */
+ case 0x3a: /* FSUB */
+ case 0x3e: /* FMIN */
+ case 0x5b: /* FMUL */
+ case 0x5c: /* FCMGE */
+ case 0x5f: /* FDIV */
+ case 0x7a: /* FABD */
+ case 0x7c: /* FCMGT */
+ handle_3same_float(s, size, elements, fpopcode, rd, rn, rm);
+ return;
+ default:
+ unallocated_encoding(s);
+ return;
+ }
+}
+
+/* Integer op subgroup of C3.6.16. */
+static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
+{
+ int is_q = extract32(insn, 30, 1);
+ int u = extract32(insn, 29, 1);
+ int size = extract32(insn, 22, 2);
+ int opcode = extract32(insn, 11, 5);
+ int rm = extract32(insn, 16, 5);
+ int rn = extract32(insn, 5, 5);
+ int rd = extract32(insn, 0, 5);
+ int pass;
+
+ switch (opcode) {
+ case 0x13: /* MUL, PMUL */
+ if (u && size != 0) {
+ unallocated_encoding(s);
+ return;
+ }
+ /* fall through */
+ case 0x0: /* SHADD, UHADD */
+ case 0x2: /* SRHADD, URHADD */
+ case 0x4: /* SHSUB, UHSUB */
+ case 0xc: /* SMAX, UMAX */
+ case 0xd: /* SMIN, UMIN */
+ case 0xe: /* SABD, UABD */
+ case 0xf: /* SABA, UABA */
+ case 0x12: /* MLA, MLS */
+ if (size == 3) {
+ unallocated_encoding(s);
+ return;
+ }
+ break;
+ case 0x16: /* SQDMULH, SQRDMULH */
+ if (size == 0 || size == 3) {
+ unallocated_encoding(s);
+ return;
+ }
+ break;
+ default:
+ if (size == 3 && !is_q) {
+ unallocated_encoding(s);
+ return;
+ }
+ break;
+ }
+
+ if (size == 3) {
+ for (pass = 0; pass < (is_q ? 2 : 1); pass++) {
+ TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+ TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+ TCGv_i64 tcg_res = tcg_temp_new_i64();
+
+ read_vec_element(s, tcg_op1, rn, pass, MO_64);
+ read_vec_element(s, tcg_op2, rm, pass, MO_64);
+
+ handle_3same_64(s, opcode, u, tcg_res, tcg_op1, tcg_op2);
+
+ write_vec_element(s, tcg_res, rd, pass, MO_64);
+
+ tcg_temp_free_i64(tcg_res);
+ tcg_temp_free_i64(tcg_op1);
+ tcg_temp_free_i64(tcg_op2);
+ }
+ } else {
+ for (pass = 0; pass < (is_q ? 4 : 2); pass++) {
+ TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+ TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+ TCGv_i32 tcg_res = tcg_temp_new_i32();
+ NeonGenTwoOpFn *genfn = NULL;
+ NeonGenTwoOpEnvFn *genenvfn = NULL;
+
+ read_vec_element_i32(s, tcg_op1, rn, pass, MO_32);
+ read_vec_element_i32(s, tcg_op2, rm, pass, MO_32);
+
+ switch (opcode) {
+ case 0x0: /* SHADD, UHADD */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_hadd_s8, gen_helper_neon_hadd_u8 },
+ { gen_helper_neon_hadd_s16, gen_helper_neon_hadd_u16 },
+ { gen_helper_neon_hadd_s32, gen_helper_neon_hadd_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x1: /* SQADD, UQADD */
+ {
+ static NeonGenTwoOpEnvFn * const fns[3][2] = {
+ { gen_helper_neon_qadd_s8, gen_helper_neon_qadd_u8 },
+ { gen_helper_neon_qadd_s16, gen_helper_neon_qadd_u16 },
+ { gen_helper_neon_qadd_s32, gen_helper_neon_qadd_u32 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
+ case 0x2: /* SRHADD, URHADD */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_rhadd_s8, gen_helper_neon_rhadd_u8 },
+ { gen_helper_neon_rhadd_s16, gen_helper_neon_rhadd_u16 },
+ { gen_helper_neon_rhadd_s32, gen_helper_neon_rhadd_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x4: /* SHSUB, UHSUB */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_hsub_s8, gen_helper_neon_hsub_u8 },
+ { gen_helper_neon_hsub_s16, gen_helper_neon_hsub_u16 },
+ { gen_helper_neon_hsub_s32, gen_helper_neon_hsub_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x5: /* SQSUB, UQSUB */
+ {
+ static NeonGenTwoOpEnvFn * const fns[3][2] = {
+ { gen_helper_neon_qsub_s8, gen_helper_neon_qsub_u8 },
+ { gen_helper_neon_qsub_s16, gen_helper_neon_qsub_u16 },
+ { gen_helper_neon_qsub_s32, gen_helper_neon_qsub_u32 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
+ case 0x6: /* CMGT, CMHI */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_cgt_s8, gen_helper_neon_cgt_u8 },
+ { gen_helper_neon_cgt_s16, gen_helper_neon_cgt_u16 },
+ { gen_helper_neon_cgt_s32, gen_helper_neon_cgt_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x7: /* CMGE, CMHS */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_cge_s8, gen_helper_neon_cge_u8 },
+ { gen_helper_neon_cge_s16, gen_helper_neon_cge_u16 },
+ { gen_helper_neon_cge_s32, gen_helper_neon_cge_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x8: /* SSHL, USHL */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_shl_s8, gen_helper_neon_shl_u8 },
+ { gen_helper_neon_shl_s16, gen_helper_neon_shl_u16 },
+ { gen_helper_neon_shl_s32, gen_helper_neon_shl_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x9: /* SQSHL, UQSHL */
+ {
+ static NeonGenTwoOpEnvFn * const fns[3][2] = {
+ { gen_helper_neon_qshl_s8, gen_helper_neon_qshl_u8 },
+ { gen_helper_neon_qshl_s16, gen_helper_neon_qshl_u16 },
+ { gen_helper_neon_qshl_s32, gen_helper_neon_qshl_u32 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
+ case 0xa: /* SRSHL, URSHL */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_rshl_s8, gen_helper_neon_rshl_u8 },
+ { gen_helper_neon_rshl_s16, gen_helper_neon_rshl_u16 },
+ { gen_helper_neon_rshl_s32, gen_helper_neon_rshl_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0xb: /* SQRSHL, UQRSHL */
+ {
+ static NeonGenTwoOpEnvFn * const fns[3][2] = {
+ { gen_helper_neon_qrshl_s8, gen_helper_neon_qrshl_u8 },
+ { gen_helper_neon_qrshl_s16, gen_helper_neon_qrshl_u16 },
+ { gen_helper_neon_qrshl_s32, gen_helper_neon_qrshl_u32 },
+ };
+ genenvfn = fns[size][u];
+ break;
+ }
+ case 0xc: /* SMAX, UMAX */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_max_s8, gen_helper_neon_max_u8 },
+ { gen_helper_neon_max_s16, gen_helper_neon_max_u16 },
+ { gen_max_s32, gen_max_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+
+ case 0xd: /* SMIN, UMIN */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_min_s8, gen_helper_neon_min_u8 },
+ { gen_helper_neon_min_s16, gen_helper_neon_min_u16 },
+ { gen_min_s32, gen_min_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0xe: /* SABD, UABD */
+ case 0xf: /* SABA, UABA */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_abd_s8, gen_helper_neon_abd_u8 },
+ { gen_helper_neon_abd_s16, gen_helper_neon_abd_u16 },
+ { gen_helper_neon_abd_s32, gen_helper_neon_abd_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x10: /* ADD, SUB */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_add_u8, gen_helper_neon_sub_u8 },
+ { gen_helper_neon_add_u16, gen_helper_neon_sub_u16 },
+ { tcg_gen_add_i32, tcg_gen_sub_i32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x11: /* CMTST, CMEQ */
+ {
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_tst_u8, gen_helper_neon_ceq_u8 },
+ { gen_helper_neon_tst_u16, gen_helper_neon_ceq_u16 },
+ { gen_helper_neon_tst_u32, gen_helper_neon_ceq_u32 },
+ };
+ genfn = fns[size][u];
+ break;
+ }
+ case 0x13: /* MUL, PMUL */
+ if (u) {
+ /* PMUL */
+ assert(size == 0);
+ genfn = gen_helper_neon_mul_p8;
+ break;
+ }
+ /* fall through : MUL */
+ case 0x12: /* MLA, MLS */
+ {
+ static NeonGenTwoOpFn * const fns[3] = {
+ gen_helper_neon_mul_u8,
+ gen_helper_neon_mul_u16,
+ tcg_gen_mul_i32,
+ };
+ genfn = fns[size];
+ break;
+ }
+ case 0x16: /* SQDMULH, SQRDMULH */
+ {
+ static NeonGenTwoOpEnvFn * const fns[2][2] = {
+ { gen_helper_neon_qdmulh_s16, gen_helper_neon_qrdmulh_s16 },
+ { gen_helper_neon_qdmulh_s32, gen_helper_neon_qrdmulh_s32 },
+ };
+ assert(size == 1 || size == 2);
+ genenvfn = fns[size - 1][u];
+ break;
+ }
+ default:
+ g_assert_not_reached();
+ }
+
+ if (genenvfn) {
+ genenvfn(tcg_res, cpu_env, tcg_op1, tcg_op2);
+ } else {
+ genfn(tcg_res, tcg_op1, tcg_op2);
+ }
+
+ if (opcode == 0xf || opcode == 0x12) {
+ /* SABA, UABA, MLA, MLS: accumulating ops */
+ static NeonGenTwoOpFn * const fns[3][2] = {
+ { gen_helper_neon_add_u8, gen_helper_neon_sub_u8 },
+ { gen_helper_neon_add_u16, gen_helper_neon_sub_u16 },
+ { tcg_gen_add_i32, tcg_gen_sub_i32 },
+ };
+ bool is_sub = (opcode == 0x12 && u); /* MLS */
+
+ genfn = fns[size][is_sub];
+ read_vec_element_i32(s, tcg_op1, rd, pass, MO_32);
+ genfn(tcg_res, tcg_res, tcg_op1);
+ }
+
+ write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
+
+ tcg_temp_free_i32(tcg_res);
+ tcg_temp_free_i32(tcg_op1);
+ tcg_temp_free_i32(tcg_op2);
+ }
+ }
+
+ if (!is_q) {
+ clear_vec_high(s, rd);
+ }
+}
+
+/* C3.6.16 AdvSIMD three same
+ * 31 30 29 28 24 23 22 21 20 16 15 11 10 9 5 4 0
+ * +---+---+---+-----------+------+---+------+--------+---+------+------+
+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 | Rm | opcode | 1 | Rn | Rd |
+ * +---+---+---+-----------+------+---+------+--------+---+------+------+
+ */
+static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn)
+{
+ int opcode = extract32(insn, 11, 5);
+
+ switch (opcode) {
+ case 0x3: /* logic ops */
+ disas_simd_3same_logic(s, insn);
+ break;
+ case 0x17: /* ADDP */
+ case 0x14: /* SMAXP, UMAXP */
+ case 0x15: /* SMINP, UMINP */
+ {
+ /* Pairwise operations */
+ int is_q = extract32(insn, 30, 1);
+ int u = extract32(insn, 29, 1);
+ int size = extract32(insn, 22, 2);
+ int rm = extract32(insn, 16, 5);
+ int rn = extract32(insn, 5, 5);
+ int rd = extract32(insn, 0, 5);
+ if (opcode == 0x17) {
+ if (u || (size == 3 && !is_q)) {
+ unallocated_encoding(s);
+ return;
+ }
+ } else {
+ if (size == 3) {
+ unallocated_encoding(s);
+ return;
+ }
+ }
+ handle_simd_3same_pair(s, is_q, u, opcode, size, rn, rm, rd);
+ break;
+ }
+ case 0x18 ... 0x31:
+ /* floating point ops, sz[1] and U are part of opcode */
+ disas_simd_3same_float(s, insn);
+ break;
+ default:
+ disas_simd_3same_int(s, insn);
+ break;
+ }
+}
+
+static void handle_2misc_narrow(DisasContext *s, int opcode, bool u, bool is_q,
+ int size, int rn, int rd)
+{
+ /* Handle 2-reg-misc ops which are narrowing (so each 2*size element
+ * in the source becomes a size element in the destination).
+ */
+ int pass;
+ TCGv_i32 tcg_res[2];
+ int destelt = is_q ? 2 : 0;
+
+ for (pass = 0; pass < 2; pass++) {
+ TCGv_i64 tcg_op = tcg_temp_new_i64();
+ NeonGenNarrowFn *genfn = NULL;
+ NeonGenNarrowEnvFn *genenvfn = NULL;
+
+ read_vec_element(s, tcg_op, rn, pass, MO_64);
+ tcg_res[pass] = tcg_temp_new_i32();
+
+ switch (opcode) {
+ case 0x12: /* XTN, SQXTUN */
projects / qemu.git / blobdiff