-static const TCGTargetOpDef aarch64_op_defs[] = {
- { INDEX_op_exit_tb, { } },
- { INDEX_op_goto_tb, { } },
- { INDEX_op_br, { } },
- { INDEX_op_goto_ptr, { "r" } },
-
- { INDEX_op_ld8u_i32, { "r", "r" } },
- { INDEX_op_ld8s_i32, { "r", "r" } },
- { INDEX_op_ld16u_i32, { "r", "r" } },
- { INDEX_op_ld16s_i32, { "r", "r" } },
- { INDEX_op_ld_i32, { "r", "r" } },
- { INDEX_op_ld8u_i64, { "r", "r" } },
- { INDEX_op_ld8s_i64, { "r", "r" } },
- { INDEX_op_ld16u_i64, { "r", "r" } },
- { INDEX_op_ld16s_i64, { "r", "r" } },
- { INDEX_op_ld32u_i64, { "r", "r" } },
- { INDEX_op_ld32s_i64, { "r", "r" } },
- { INDEX_op_ld_i64, { "r", "r" } },
-
- { INDEX_op_st8_i32, { "rZ", "r" } },
- { INDEX_op_st16_i32, { "rZ", "r" } },
- { INDEX_op_st_i32, { "rZ", "r" } },
- { INDEX_op_st8_i64, { "rZ", "r" } },
- { INDEX_op_st16_i64, { "rZ", "r" } },
- { INDEX_op_st32_i64, { "rZ", "r" } },
- { INDEX_op_st_i64, { "rZ", "r" } },
-
- { INDEX_op_add_i32, { "r", "r", "rA" } },
- { INDEX_op_add_i64, { "r", "r", "rA" } },
- { INDEX_op_sub_i32, { "r", "r", "rA" } },
- { INDEX_op_sub_i64, { "r", "r", "rA" } },
- { INDEX_op_mul_i32, { "r", "r", "r" } },
- { INDEX_op_mul_i64, { "r", "r", "r" } },
- { INDEX_op_div_i32, { "r", "r", "r" } },
- { INDEX_op_div_i64, { "r", "r", "r" } },
- { INDEX_op_divu_i32, { "r", "r", "r" } },
- { INDEX_op_divu_i64, { "r", "r", "r" } },
- { INDEX_op_rem_i32, { "r", "r", "r" } },
- { INDEX_op_rem_i64, { "r", "r", "r" } },
- { INDEX_op_remu_i32, { "r", "r", "r" } },
- { INDEX_op_remu_i64, { "r", "r", "r" } },
- { INDEX_op_and_i32, { "r", "r", "rL" } },
- { INDEX_op_and_i64, { "r", "r", "rL" } },
- { INDEX_op_or_i32, { "r", "r", "rL" } },
- { INDEX_op_or_i64, { "r", "r", "rL" } },
- { INDEX_op_xor_i32, { "r", "r", "rL" } },
- { INDEX_op_xor_i64, { "r", "r", "rL" } },
- { INDEX_op_andc_i32, { "r", "r", "rL" } },
- { INDEX_op_andc_i64, { "r", "r", "rL" } },
- { INDEX_op_orc_i32, { "r", "r", "rL" } },
- { INDEX_op_orc_i64, { "r", "r", "rL" } },
- { INDEX_op_eqv_i32, { "r", "r", "rL" } },
- { INDEX_op_eqv_i64, { "r", "r", "rL" } },
-
- { INDEX_op_neg_i32, { "r", "r" } },
- { INDEX_op_neg_i64, { "r", "r" } },
- { INDEX_op_not_i32, { "r", "r" } },
- { INDEX_op_not_i64, { "r", "r" } },
-
- { INDEX_op_shl_i32, { "r", "r", "ri" } },
- { INDEX_op_shr_i32, { "r", "r", "ri" } },
- { INDEX_op_sar_i32, { "r", "r", "ri" } },
- { INDEX_op_rotl_i32, { "r", "r", "ri" } },
- { INDEX_op_rotr_i32, { "r", "r", "ri" } },
- { INDEX_op_clz_i32, { "r", "r", "rAL" } },
- { INDEX_op_ctz_i32, { "r", "r", "rAL" } },
- { INDEX_op_shl_i64, { "r", "r", "ri" } },
- { INDEX_op_shr_i64, { "r", "r", "ri" } },
- { INDEX_op_sar_i64, { "r", "r", "ri" } },
- { INDEX_op_rotl_i64, { "r", "r", "ri" } },
- { INDEX_op_rotr_i64, { "r", "r", "ri" } },
- { INDEX_op_clz_i64, { "r", "r", "rAL" } },
- { INDEX_op_ctz_i64, { "r", "r", "rAL" } },
-
- { INDEX_op_brcond_i32, { "r", "rA" } },
- { INDEX_op_brcond_i64, { "r", "rA" } },
- { INDEX_op_setcond_i32, { "r", "r", "rA" } },
- { INDEX_op_setcond_i64, { "r", "r", "rA" } },
- { INDEX_op_movcond_i32, { "r", "r", "rA", "rZ", "rZ" } },
- { INDEX_op_movcond_i64, { "r", "r", "rA", "rZ", "rZ" } },
-
- { INDEX_op_qemu_ld_i32, { "r", "l" } },
- { INDEX_op_qemu_ld_i64, { "r", "l" } },
- { INDEX_op_qemu_st_i32, { "lZ", "l" } },
- { INDEX_op_qemu_st_i64, { "lZ", "l" } },
-
- { INDEX_op_bswap16_i32, { "r", "r" } },
- { INDEX_op_bswap32_i32, { "r", "r" } },
- { INDEX_op_bswap16_i64, { "r", "r" } },
- { INDEX_op_bswap32_i64, { "r", "r" } },
- { INDEX_op_bswap64_i64, { "r", "r" } },
-
- { INDEX_op_ext8s_i32, { "r", "r" } },
- { INDEX_op_ext16s_i32, { "r", "r" } },
- { INDEX_op_ext8u_i32, { "r", "r" } },
- { INDEX_op_ext16u_i32, { "r", "r" } },
-
- { INDEX_op_ext8s_i64, { "r", "r" } },
- { INDEX_op_ext16s_i64, { "r", "r" } },
- { INDEX_op_ext32s_i64, { "r", "r" } },
- { INDEX_op_ext8u_i64, { "r", "r" } },
- { INDEX_op_ext16u_i64, { "r", "r" } },
- { INDEX_op_ext32u_i64, { "r", "r" } },
- { INDEX_op_ext_i32_i64, { "r", "r" } },
- { INDEX_op_extu_i32_i64, { "r", "r" } },
-
- { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
- { INDEX_op_deposit_i64, { "r", "0", "rZ" } },
- { INDEX_op_extract_i32, { "r", "r" } },
- { INDEX_op_extract_i64, { "r", "r" } },
- { INDEX_op_sextract_i32, { "r", "r" } },
- { INDEX_op_sextract_i64, { "r", "r" } },
-
- { INDEX_op_add2_i32, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
- { INDEX_op_add2_i64, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
- { INDEX_op_sub2_i32, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
- { INDEX_op_sub2_i64, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
-
- { INDEX_op_muluh_i64, { "r", "r", "r" } },
- { INDEX_op_mulsh_i64, { "r", "r", "r" } },
-
- { INDEX_op_mb, { } },
- { -1 },
-};
+static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
+ unsigned vecl, unsigned vece,
+ const TCGArg *args, const int *const_args)
+{
+ static const AArch64Insn cmp_insn[16] = {
+ [TCG_COND_EQ] = I3616_CMEQ,
+ [TCG_COND_GT] = I3616_CMGT,
+ [TCG_COND_GE] = I3616_CMGE,
+ [TCG_COND_GTU] = I3616_CMHI,
+ [TCG_COND_GEU] = I3616_CMHS,
+ };
+ static const AArch64Insn cmp0_insn[16] = {
+ [TCG_COND_EQ] = I3617_CMEQ0,
+ [TCG_COND_GT] = I3617_CMGT0,
+ [TCG_COND_GE] = I3617_CMGE0,
+ [TCG_COND_LT] = I3617_CMLT0,
+ [TCG_COND_LE] = I3617_CMLE0,
+ };
+
+ TCGType type = vecl + TCG_TYPE_V64;
+ unsigned is_q = vecl;
+ TCGArg a0, a1, a2, a3;
+ int cmode, imm8;
+
+ a0 = args[0];
+ a1 = args[1];
+ a2 = args[2];
+
+ switch (opc) {
+ case INDEX_op_ld_vec:
+ tcg_out_ld(s, type, a0, a1, a2);
+ break;
+ case INDEX_op_st_vec:
+ tcg_out_st(s, type, a0, a1, a2);
+ break;
+ case INDEX_op_dupm_vec:
+ tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
+ break;
+ case INDEX_op_add_vec:
+ tcg_out_insn(s, 3616, ADD, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_sub_vec:
+ tcg_out_insn(s, 3616, SUB, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_mul_vec:
+ tcg_out_insn(s, 3616, MUL, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_neg_vec:
+ tcg_out_insn(s, 3617, NEG, is_q, vece, a0, a1);
+ break;
+ case INDEX_op_abs_vec:
+ tcg_out_insn(s, 3617, ABS, is_q, vece, a0, a1);
+ break;
+ case INDEX_op_and_vec:
+ if (const_args[2]) {
+ is_shimm1632(~a2, &cmode, &imm8);
+ if (a0 == a1) {
+ tcg_out_insn(s, 3606, BIC, is_q, a0, 0, cmode, imm8);
+ return;
+ }
+ tcg_out_insn(s, 3606, MVNI, is_q, a0, 0, cmode, imm8);
+ a2 = a0;
+ }
+ tcg_out_insn(s, 3616, AND, is_q, 0, a0, a1, a2);
+ break;
+ case INDEX_op_or_vec:
+ if (const_args[2]) {
+ is_shimm1632(a2, &cmode, &imm8);
+ if (a0 == a1) {
+ tcg_out_insn(s, 3606, ORR, is_q, a0, 0, cmode, imm8);
+ return;
+ }
+ tcg_out_insn(s, 3606, MOVI, is_q, a0, 0, cmode, imm8);
+ a2 = a0;
+ }
+ tcg_out_insn(s, 3616, ORR, is_q, 0, a0, a1, a2);
+ break;
+ case INDEX_op_andc_vec:
+ if (const_args[2]) {
+ is_shimm1632(a2, &cmode, &imm8);
+ if (a0 == a1) {
+ tcg_out_insn(s, 3606, BIC, is_q, a0, 0, cmode, imm8);
+ return;
+ }
+ tcg_out_insn(s, 3606, MOVI, is_q, a0, 0, cmode, imm8);
+ a2 = a0;
+ }
+ tcg_out_insn(s, 3616, BIC, is_q, 0, a0, a1, a2);
+ break;
+ case INDEX_op_orc_vec:
+ if (const_args[2]) {
+ is_shimm1632(~a2, &cmode, &imm8);
+ if (a0 == a1) {
+ tcg_out_insn(s, 3606, ORR, is_q, a0, 0, cmode, imm8);
+ return;
+ }
+ tcg_out_insn(s, 3606, MVNI, is_q, a0, 0, cmode, imm8);
+ a2 = a0;
+ }
+ tcg_out_insn(s, 3616, ORN, is_q, 0, a0, a1, a2);
+ break;
+ case INDEX_op_xor_vec:
+ tcg_out_insn(s, 3616, EOR, is_q, 0, a0, a1, a2);
+ break;
+ case INDEX_op_ssadd_vec:
+ tcg_out_insn(s, 3616, SQADD, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_sssub_vec:
+ tcg_out_insn(s, 3616, SQSUB, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_usadd_vec:
+ tcg_out_insn(s, 3616, UQADD, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_ussub_vec:
+ tcg_out_insn(s, 3616, UQSUB, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_smax_vec:
+ tcg_out_insn(s, 3616, SMAX, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_smin_vec:
+ tcg_out_insn(s, 3616, SMIN, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_umax_vec:
+ tcg_out_insn(s, 3616, UMAX, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_umin_vec:
+ tcg_out_insn(s, 3616, UMIN, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_not_vec:
+ tcg_out_insn(s, 3617, NOT, is_q, 0, a0, a1);
+ break;
+ case INDEX_op_shli_vec:
+ tcg_out_insn(s, 3614, SHL, is_q, a0, a1, a2 + (8 << vece));
+ break;
+ case INDEX_op_shri_vec:
+ tcg_out_insn(s, 3614, USHR, is_q, a0, a1, (16 << vece) - a2);
+ break;
+ case INDEX_op_sari_vec:
+ tcg_out_insn(s, 3614, SSHR, is_q, a0, a1, (16 << vece) - a2);
+ break;
+ case INDEX_op_shlv_vec:
+ tcg_out_insn(s, 3616, USHL, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_aa64_sshl_vec:
+ tcg_out_insn(s, 3616, SSHL, is_q, vece, a0, a1, a2);
+ break;
+ case INDEX_op_cmp_vec:
+ {
+ TCGCond cond = args[3];
+ AArch64Insn insn;
+
+ if (cond == TCG_COND_NE) {
+ if (const_args[2]) {
+ tcg_out_insn(s, 3616, CMTST, is_q, vece, a0, a1, a1);
+ } else {
+ tcg_out_insn(s, 3616, CMEQ, is_q, vece, a0, a1, a2);
+ tcg_out_insn(s, 3617, NOT, is_q, 0, a0, a0);
+ }
+ } else {
+ if (const_args[2]) {
+ insn = cmp0_insn[cond];
+ if (insn) {
+ tcg_out_insn_3617(s, insn, is_q, vece, a0, a1);
+ break;
+ }
+ tcg_out_dupi_vec(s, type, TCG_VEC_TMP, 0);
+ a2 = TCG_VEC_TMP;
+ }
+ insn = cmp_insn[cond];
+ if (insn == 0) {
+ TCGArg t;
+ t = a1, a1 = a2, a2 = t;
+ cond = tcg_swap_cond(cond);
+ insn = cmp_insn[cond];
+ tcg_debug_assert(insn != 0);
+ }
+ tcg_out_insn_3616(s, insn, is_q, vece, a0, a1, a2);
+ }
+ }
+ break;
+
+ case INDEX_op_bitsel_vec:
+ a3 = args[3];
+ if (a0 == a3) {
+ tcg_out_insn(s, 3616, BIT, is_q, 0, a0, a2, a1);
+ } else if (a0 == a2) {
+ tcg_out_insn(s, 3616, BIF, is_q, 0, a0, a3, a1);
+ } else {
+ if (a0 != a1) {
+ tcg_out_mov(s, type, a0, a1);
+ }
+ tcg_out_insn(s, 3616, BSL, is_q, 0, a0, a2, a3);
+ }
+ break;
+
+ case INDEX_op_mov_vec: /* Always emitted via tcg_out_mov. */
+ case INDEX_op_dupi_vec: /* Always emitted via tcg_out_movi. */
+ case INDEX_op_dup_vec: /* Always emitted via tcg_out_dup_vec. */
+ default:
+ g_assert_not_reached();
+ }
+}
+
+int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
+{
+ switch (opc) {
+ case INDEX_op_add_vec:
+ case INDEX_op_sub_vec:
+ case INDEX_op_and_vec:
+ case INDEX_op_or_vec:
+ case INDEX_op_xor_vec:
+ case INDEX_op_andc_vec:
+ case INDEX_op_orc_vec:
+ case INDEX_op_neg_vec:
+ case INDEX_op_abs_vec:
+ case INDEX_op_not_vec:
+ case INDEX_op_cmp_vec:
+ case INDEX_op_shli_vec:
+ case INDEX_op_shri_vec:
+ case INDEX_op_sari_vec:
+ case INDEX_op_ssadd_vec:
+ case INDEX_op_sssub_vec:
+ case INDEX_op_usadd_vec:
+ case INDEX_op_ussub_vec:
+ case INDEX_op_shlv_vec:
+ case INDEX_op_bitsel_vec:
+ return 1;
+ case INDEX_op_shrv_vec:
+ case INDEX_op_sarv_vec:
+ return -1;
+ case INDEX_op_mul_vec:
+ case INDEX_op_smax_vec:
+ case INDEX_op_smin_vec:
+ case INDEX_op_umax_vec:
+ case INDEX_op_umin_vec:
+ return vece < MO_64;
+
+ default:
+ return 0;
+ }
+}
+
+void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
+ TCGArg a0, ...)
+{
+ va_list va;
+ TCGv_vec v0, v1, v2, t1;
+
+ va_start(va, a0);
+ v0 = temp_tcgv_vec(arg_temp(a0));
+ v1 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg)));
+ v2 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg)));
+
+ switch (opc) {
+ case INDEX_op_shrv_vec:
+ case INDEX_op_sarv_vec:
+ /* Right shifts are negative left shifts for AArch64. */
+ t1 = tcg_temp_new_vec(type);
+ tcg_gen_neg_vec(vece, t1, v2);
+ opc = (opc == INDEX_op_shrv_vec
+ ? INDEX_op_shlv_vec : INDEX_op_aa64_sshl_vec);
+ vec_gen_3(opc, type, vece, tcgv_vec_arg(v0),
+ tcgv_vec_arg(v1), tcgv_vec_arg(t1));
+ tcg_temp_free_vec(t1);
+ break;
+
+ default:
+ g_assert_not_reached();
+ }
+
+ va_end(va);
+}