@@ -494,3 +494,37 @@ LD_mult 0 . 001100 . 1 0 ..... 0110 .. ..... ..... @ldst_mult rpt=3 sele
LD_mult 0 . 001100 . 1 0 ..... 0111 .. ..... ..... @ldst_mult rpt=1 selem=1
LD_mult 0 . 001100 . 1 0 ..... 1000 .. ..... ..... @ldst_mult rpt=1 selem=2
LD_mult 0 . 001100 . 1 0 ..... 1010 .. ..... ..... @ldst_mult rpt=2 selem=1
+
+# Load/store single structure
+&ldst_single rm rn rt p selem index scale
+
+%ldst_single_selem 13:1 21:1 !function=plus_1
+
+%ldst_single_index_b 30:1 10:3
+%ldst_single_index_h 30:1 11:2
+%ldst_single_index_s 30:1 12:1
+
+@ldst_single_b .. ...... p:1 .. rm:5 ...... rn:5 rt:5 \
+ &ldst_single scale=0 selem=%ldst_single_selem \
+ index=%ldst_single_index_b
+@ldst_single_h .. ...... p:1 .. rm:5 ...... rn:5 rt:5 \
+ &ldst_single scale=1 selem=%ldst_single_selem \
+ index=%ldst_single_index_h
+@ldst_single_s .. ...... p:1 .. rm:5 ...... rn:5 rt:5 \
+ &ldst_single scale=2 selem=%ldst_single_selem \
+ index=%ldst_single_index_s
+@ldst_single_d . index:1 ...... p:1 .. rm:5 ...... rn:5 rt:5 \
+ &ldst_single scale=3 selem=%ldst_single_selem
+
+ST_single 0 . 001101 . 0 . ..... 00 . ... ..... ..... @ldst_single_b
+ST_single 0 . 001101 . 0 . ..... 01 . ..0 ..... ..... @ldst_single_h
+ST_single 0 . 001101 . 0 . ..... 10 . .00 ..... ..... @ldst_single_s
+ST_single 0 . 001101 . 0 . ..... 10 . 001 ..... ..... @ldst_single_d
+
+LD_single 0 . 001101 . 1 . ..... 00 . ... ..... ..... @ldst_single_b
+LD_single 0 . 001101 . 1 . ..... 01 . ..0 ..... ..... @ldst_single_h
+LD_single 0 . 001101 . 1 . ..... 10 . .00 ..... ..... @ldst_single_s
+LD_single 0 . 001101 . 1 . ..... 10 . 001 ..... ..... @ldst_single_d
+
+# Replicating load case
+LD_single_repl 0 q:1 001101 p:1 1 . rm:5 11 . 0 scale:2 rn:5 rt:5 selem=%ldst_single_selem
@@ -3584,141 +3584,129 @@ static bool trans_ST_mult(DisasContext *s, arg_ldst_mult *a)
return true;
}
-/* AdvSIMD load/store single structure
- *
- * 31 30 29 23 22 21 20 16 15 13 12 11 10 9 5 4 0
- * +---+---+---------------+-----+-----------+-----+---+------+------+------+
- * | 0 | Q | 0 0 1 1 0 1 0 | L R | 0 0 0 0 0 | opc | S | size | Rn | Rt |
- * +---+---+---------------+-----+-----------+-----+---+------+------+------+
- *
- * AdvSIMD load/store single structure (post-indexed)
- *
- * 31 30 29 23 22 21 20 16 15 13 12 11 10 9 5 4 0
- * +---+---+---------------+-----+-----------+-----+---+------+------+------+
- * | 0 | Q | 0 0 1 1 0 1 1 | L R | Rm | opc | S | size | Rn | Rt |
- * +---+---+---------------+-----+-----------+-----+---+------+------+------+
- *
- * Rt: first (or only) SIMD&FP register to be transferred
- * Rn: base address or SP
- * Rm (post-index only): post-index register (when !31) or size dependent #imm
- * index = encoded in Q:S:size dependent on size
- *
- * lane_size = encoded in R, opc
- * transfer width = encoded in opc, S, size
- */
-static void disas_ldst_single_struct(DisasContext *s, uint32_t insn)
+static bool trans_ST_single(DisasContext *s, arg_ldst_single *a)
{
- int rt = extract32(insn, 0, 5);
- int rn = extract32(insn, 5, 5);
- int rm = extract32(insn, 16, 5);
- int size = extract32(insn, 10, 2);
- int S = extract32(insn, 12, 1);
- int opc = extract32(insn, 13, 3);
- int R = extract32(insn, 21, 1);
- int is_load = extract32(insn, 22, 1);
- int is_postidx = extract32(insn, 23, 1);
- int is_q = extract32(insn, 30, 1);
-
- int scale = extract32(opc, 1, 2);
- int selem = (extract32(opc, 0, 1) << 1 | R) + 1;
- bool replicate = false;
- int index = is_q << 3 | S << 2 | size;
- int xs, total;
+ int xs, total, rt;
TCGv_i64 clean_addr, tcg_rn, tcg_ebytes;
MemOp mop;
- if (extract32(insn, 31, 1)) {
- unallocated_encoding(s);
- return;
+ if (!a->p && a->rm != 0) {
+ return false;
}
- if (!is_postidx && rm != 0) {
- unallocated_encoding(s);
- return;
- }
-
- switch (scale) {
- case 3:
- if (!is_load || S) {
- unallocated_encoding(s);
- return;
- }
- scale = size;
- replicate = true;
- break;
- case 0:
- break;
- case 1:
- if (extract32(size, 0, 1)) {
- unallocated_encoding(s);
- return;
- }
- index >>= 1;
- break;
- case 2:
- if (extract32(size, 1, 1)) {
- unallocated_encoding(s);
- return;
- }
- if (!extract32(size, 0, 1)) {
- index >>= 2;
- } else {
- if (S) {
- unallocated_encoding(s);
- return;
- }
- index >>= 3;
- scale = 3;
- }
- break;
- default:
- g_assert_not_reached();
- }
-
if (!fp_access_check(s)) {
- return;
+ return true;
}
- if (rn == 31) {
+ if (a->rn == 31) {
gen_check_sp_alignment(s);
}
- total = selem << scale;
- tcg_rn = cpu_reg_sp(s, rn);
+ total = a->selem << a->scale;
+ tcg_rn = cpu_reg_sp(s, a->rn);
- mop = finalize_memop_asimd(s, scale);
-
- clean_addr = gen_mte_checkN(s, tcg_rn, !is_load, is_postidx || rn != 31,
+ mop = finalize_memop_asimd(s, a->scale);
+ clean_addr = gen_mte_checkN(s, tcg_rn, true, a->p || a->rn != 31,
total, mop);
- tcg_ebytes = tcg_constant_i64(1 << scale);
- for (xs = 0; xs < selem; xs++) {
- if (replicate) {
- /* Load and replicate to all elements */
- TCGv_i64 tcg_tmp = tcg_temp_new_i64();
-
- tcg_gen_qemu_ld_i64(tcg_tmp, clean_addr, get_mem_index(s), mop);
- tcg_gen_gvec_dup_i64(scale, vec_full_reg_offset(s, rt),
- (is_q + 1) * 8, vec_full_reg_size(s),
- tcg_tmp);
- } else {
- /* Load/store one element per register */
- if (is_load) {
- do_vec_ld(s, rt, index, clean_addr, mop);
- } else {
- do_vec_st(s, rt, index, clean_addr, mop);
- }
- }
+ tcg_ebytes = tcg_constant_i64(1 << a->scale);
+ for (xs = 0, rt = a->rt; xs < a->selem; xs++, rt = (rt + 1) % 32) {
+ do_vec_st(s, rt, a->index, clean_addr, mop);
tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes);
- rt = (rt + 1) % 32;
}
- if (is_postidx) {
- if (rm == 31) {
+ if (a->p) {
+ if (a->rm == 31) {
tcg_gen_addi_i64(tcg_rn, tcg_rn, total);
} else {
- tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm));
+ tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, a->rm));
}
}
+ return true;
+}
+
+static bool trans_LD_single(DisasContext *s, arg_ldst_single *a)
+{
+ int xs, total, rt;
+ TCGv_i64 clean_addr, tcg_rn, tcg_ebytes;
+ MemOp mop;
+
+ if (!a->p && a->rm != 0) {
+ return false;
+ }
+ if (!fp_access_check(s)) {
+ return true;
+ }
+
+ if (a->rn == 31) {
+ gen_check_sp_alignment(s);
+ }
+
+ total = a->selem << a->scale;
+ tcg_rn = cpu_reg_sp(s, a->rn);
+
+ mop = finalize_memop_asimd(s, a->scale);
+ clean_addr = gen_mte_checkN(s, tcg_rn, false, a->p || a->rn != 31,
+ total, mop);
+
+ tcg_ebytes = tcg_constant_i64(1 << a->scale);
+ for (xs = 0, rt = a->rt; xs < a->selem; xs++, rt = (rt + 1) % 32) {
+ do_vec_ld(s, rt, a->index, clean_addr, mop);
+ tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes);
+ }
+
+ if (a->p) {
+ if (a->rm == 31) {
+ tcg_gen_addi_i64(tcg_rn, tcg_rn, total);
+ } else {
+ tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, a->rm));
+ }
+ }
+ return true;
+}
+
+static bool trans_LD_single_repl(DisasContext *s, arg_LD_single_repl *a)
+{
+ int xs, total, rt;
+ TCGv_i64 clean_addr, tcg_rn, tcg_ebytes;
+ MemOp mop;
+
+ if (!a->p && a->rm != 0) {
+ return false;
+ }
+ if (!fp_access_check(s)) {
+ return true;
+ }
+
+ if (a->rn == 31) {
+ gen_check_sp_alignment(s);
+ }
+
+ total = a->selem << a->scale;
+ tcg_rn = cpu_reg_sp(s, a->rn);
+
+ mop = finalize_memop_asimd(s, a->scale);
+ clean_addr = gen_mte_checkN(s, tcg_rn, false, a->p || a->rn != 31,
+ total, mop);
+
+ tcg_ebytes = tcg_constant_i64(1 << a->scale);
+ for (xs = 0, rt = a->rt; xs < a->selem; xs++, rt = (rt + 1) % 32) {
+ /* Load and replicate to all elements */
+ TCGv_i64 tcg_tmp = tcg_temp_new_i64();
+
+ tcg_gen_qemu_ld_i64(tcg_tmp, clean_addr, get_mem_index(s), mop);
+ tcg_gen_gvec_dup_i64(a->scale, vec_full_reg_offset(s, rt),
+ (a->q + 1) * 8, vec_full_reg_size(s), tcg_tmp);
+ tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes);
+ }
+
+ if (a->p) {
+ if (a->rm == 31) {
+ tcg_gen_addi_i64(tcg_rn, tcg_rn, total);
+ } else {
+ tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, a->rm));
+ }
+ }
+ return true;
}
/*
@@ -3934,9 +3922,6 @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn)
static void disas_ldst(DisasContext *s, uint32_t insn)
{
switch (extract32(insn, 24, 6)) {
- case 0x0d: /* AdvSIMD load/store single structure */
- disas_ldst_single_struct(s, insn);
- break;
case 0x19:
if (extract32(insn, 21, 1) != 0) {
disas_ldst_tag(s, insn);