AArch64DecodeFn *disas_fn;
} AArch64DecodeTable;
+/* Function prototype for gen_ functions for calling Neon helpers */
+typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
+typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
+
/* initialize TCG globals. */
void a64_translate_init(void)
{
}
}
+static void write_vec_element_i32(DisasContext *s, TCGv_i32 tcg_src,
+ int destidx, int element, TCGMemOp memop)
+{
+ int vect_off = vec_reg_offset(destidx, element, memop & MO_SIZE);
+ switch (memop) {
+ case MO_8:
+ tcg_gen_st8_i32(tcg_src, cpu_env, vect_off);
+ break;
+ case MO_16:
+ tcg_gen_st16_i32(tcg_src, cpu_env, vect_off);
+ break;
+ case MO_32:
+ tcg_gen_st_i32(tcg_src, cpu_env, vect_off);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
/* Clear the high 64 bits of a 128 bit vector (in general non-quad
* vector ops all need to do this).
*/
unsupported_encoding(s, insn);
}
+/*
+ * 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)
{
- unsupported_encoding(s, 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
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.
tcg_gen_setcondi_i64(TCG_COND_NE, tcg_rd, tcg_rd, 0);
tcg_gen_neg_i64(tcg_rd, tcg_rd);
break;
- case 0x10: /* ADD, SUB */
+ case 0x8: /* SSHL, USHL */
if (u) {
- tcg_gen_sub_i64(tcg_rd, tcg_rn, tcg_rm);
+ gen_helper_neon_shl_u64(tcg_rd, tcg_rn, tcg_rm);
} else {
- tcg_gen_add_i64(tcg_rd, tcg_rn, tcg_rm);
+ gen_helper_neon_shl_s64(tcg_rd, tcg_rn, tcg_rm);
}
break;
- case 0x1: /* SQADD */
- case 0x5: /* SQSUB */
- case 0x8: /* SSHL, USHL */
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 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 0x1e: /* FMAX */
+ gen_helper_vfp_maxd(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 0x5b: /* FMUL */
+ gen_helper_vfp_muld(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;
+ 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 0x1a: /* FADD */
+ gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst);
+ break;
+ case 0x1e: /* FMAX */
+ gen_helper_vfp_maxs(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 0x5b: /* FMUL */
+ gen_helper_vfp_muls(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;
+ 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
* +-----+---+-----------+------+---+------+--------+---+------+------+
case 0x3f: /* FRSQRTS */
case 0x5c: /* FCMGE */
case 0x5d: /* FACGE */
- case 0x7a: /* FABD */
case 0x7c: /* FCMGT */
case 0x7d: /* FACGT */
unsupported_encoding(s, insn);
return;
+ 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 0x8: /* SSHL, USHL */
- case 0xa: /* SRSHL, URSHL */
unsupported_encoding(s, insn);
return;
+ case 0x8: /* SSHL, USHL */
+ case 0xa: /* SRSHL, URSHL */
case 0x6: /* CMGT, CMHI */
case 0x7: /* CMGE, CMHS */
case 0x11: /* CMTST, CMEQ */
unsupported_encoding(s, insn);
}
+/* 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
* +---+---+---+-------------+------+------+--------+---+------+------+
*/
static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
{
- unsupported_encoding(s, 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,
}
}
+/* 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]);
+}
+
+/* Pairwise op subgroup of C3.6.16. */
+static void disas_simd_3same_pair(DisasContext *s, uint32_t insn)
+{
+ unsupported_encoding(s, insn);
+}
+
+/* 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 */
+ /* pairwise ops */
+ unsupported_encoding(s, insn);
+ return;
+ case 0x1b: /* FMULX */
+ case 0x1c: /* FCMEQ */
+ case 0x1f: /* FRECPS */
+ case 0x3f: /* FRSQRTS */
+ case 0x5c: /* FCMGE */
+ case 0x5d: /* FACGE */
+ case 0x7c: /* FCMGT */
+ case 0x7d: /* FACGT */
+ case 0x19: /* FMLA */
+ case 0x39: /* FMLS */
+ unsupported_encoding(s, insn);
+ return;
+ case 0x18: /* FMAXNM */
+ case 0x1a: /* FADD */
+ case 0x1e: /* FMAX */
+ case 0x38: /* FMINNM */
+ case 0x3a: /* FSUB */
+ case 0x3e: /* FMIN */
+ case 0x5b: /* FMUL */
+ case 0x5f: /* FDIV */
+ case 0x7a: /* FABD */
+ 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;
+ }
+ unsupported_encoding(s, insn);
+ return;
+ case 0x16: /* SQDMULH, SQRDMULH */
+ if (size == 0 || size == 3) {
+ unallocated_encoding(s);
+ return;
+ }
+ unsupported_encoding(s, insn);
+ return;
+ 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 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 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 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;
+ }
+ default:
+ g_assert_not_reached();
+ }
+
+ if (genenvfn) {
+ genenvfn(tcg_res, cpu_env, tcg_op1, tcg_op2);
+ } else {
+ genfn(tcg_res, tcg_op1, tcg_op2);
+ }
+
+ 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
* +---+---+---+-----------+------+---+------+--------+---+------+------+
*/
static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn)
{
- unsupported_encoding(s, 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 */
+ disas_simd_3same_pair(s, insn);
+ 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;
+ }
}
/* C3.6.17 AdvSIMD two reg misc
projects / qemu.git / blobdiff