typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64);
typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64);
+typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
+typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
/* initialize TCG globals. */
void a64_translate_init(void)
crn, crm, op0, op1, op2));
if (!ri) {
- /* Unknown register */
+ /* Unknown register; this might be a guest error or a QEMU
+ * unimplemented feature.
+ */
+ qemu_log_mask(LOG_UNIMP, "%s access to unsupported AArch64 "
+ "system register op0:%d op1:%d crn:%d crm:%d op2:%d\n",
+ isread ? "read" : "write", op0, op1, crn, crm, op2);
unallocated_encoding(s);
return;
}
*/
static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn)
{
- unsupported_encoding(s, 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,
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 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;
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();
}
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 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;
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();
}
int fpopcode = opcode | (extract32(size, 1, 1) << 5) | (u << 6);
switch (fpopcode) {
case 0x1b: /* FMULX */
- case 0x1c: /* FCMEQ */
case 0x1f: /* FRECPS */
case 0x3f: /* FRSQRTS */
- case 0x5c: /* FCMGE */
case 0x5d: /* FACGE */
- case 0x7c: /* FCMGT */
case 0x7d: /* FACGT */
- unsupported_encoding(s, insn);
- return;
+ case 0x1c: /* FCMEQ */
+ case 0x5c: /* FCMGE */
+ case 0x7c: /* FCMGT */
case 0x7a: /* FABD */
break;
default:
}
}
+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
* +-----+---+-----------+------+-----------+--------+-----+------+------+
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:
- * + floating point (single and double)
* + 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
}
}
-/* C3.6.13 AdvSIMD scalar x indexed element
- * 31 30 29 28 24 23 22 21 20 19 16 15 12 11 10 9 5 4 0
- * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+
- * | 0 1 | U | 1 1 1 1 1 | size | L | M | Rm | opc | H | 0 | Rn | Rd |
- * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+
- */
-static void disas_simd_scalar_indexed(DisasContext *s, uint32_t insn)
-{
- 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)
tcg_gen_movcond_i32(TCG_COND_LEU, res, op1, op2, op1, op2);
}
-/* Pairwise op subgroup of C3.6.16. */
-static void disas_simd_3same_pair(DisasContext *s, uint32_t insn)
+/* 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)
{
- 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);
+ TCGv_ptr fpst;
int pass;
- if (size == 3 && !is_q) {
- unallocated_encoding(s);
- return;
- }
-
- switch (opcode) {
- case 0x14: /* SMAXP, UMAXP */
- case 0x15: /* SMINP, UMINP */
- if (size == 3) {
- unallocated_encoding(s);
- return;
- }
- break;
- case 0x17:
- if (u) {
- unallocated_encoding(s);
- return;
- }
- break;
- default:
- g_assert_not_reached();
+ /* 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
read_vec_element(s, tcg_op2, passreg, 1, MO_64);
tcg_res[pass] = tcg_temp_new_i64();
- /* The only 64 bit pairwise integer op is ADDP */
- assert(opcode == 0x17);
- tcg_gen_add_i64(tcg_res[pass], tcg_op1, tcg_op2);
+ 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 < maxpass; pass++) {
TCGv_i32 tcg_op1 = tcg_temp_new_i32();
TCGv_i32 tcg_op2 = tcg_temp_new_i32();
- NeonGenTwoOpFn *genfn;
+ NeonGenTwoOpFn *genfn = NULL;
int passreg = pass < (maxpass / 2) ? rn : rm;
int passelt = (is_q && (pass & 1)) ? 2 : 0;
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();
}
- genfn(tcg_res[pass], tcg_op1, tcg_op2);
+ /* 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);
clear_vec_high(s, rd);
}
}
+
+ if (!TCGV_IS_UNUSED_PTR(fpst)) {
+ tcg_temp_free_ptr(fpst);
+ }
}
/* Floating point op subgroup of C3.6.16. */
case 0x5e: /* FMAXP */
case 0x78: /* FMINNMP */
case 0x7e: /* FMINP */
- /* pairwise ops */
- unsupported_encoding(s, insn);
+ 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 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 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:
case 0x17: /* ADDP */
case 0x14: /* SMAXP, UMAXP */
case 0x15: /* SMINP, UMINP */
+ {
/* Pairwise operations */
- disas_simd_3same_pair(s, insn);
+ 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);
return;
}
break;
+ case 0x2c: /* FCMGT (zero) */
+ case 0x2d: /* FCMEQ (zero) */
+ case 0x2e: /* FCMLT (zero) */
+ case 0x6c: /* FCMGE (zero) */
+ case 0x6d: /* FCMLE (zero) */
+ if (size == 3 && !is_q) {
+ unallocated_encoding(s);
+ return;
+ }
+ handle_2misc_fcmp_zero(s, opcode, false, u, is_q, size, rn, rd);
+ return;
case 0x16: /* FCVTN, FCVTN2 */
case 0x17: /* FCVTL, FCVTL2 */
case 0x18: /* FRINTN */
case 0x1b: /* FCVTMS */
case 0x1c: /* FCVTAS */
case 0x1d: /* SCVTF */
- case 0x2c: /* FCMGT (zero) */
- case 0x2d: /* FCMEQ (zero) */
- case 0x2e: /* FCMLT (zero) */
case 0x38: /* FRINTP */
case 0x39: /* FRINTZ */
case 0x3a: /* FCVTPS */
case 0x5b: /* FCVTMU */
case 0x5c: /* FCVTAU */
case 0x5d: /* UCVTF */
- case 0x6c: /* FCMGE (zero) */
- case 0x6d: /* FCMLE (zero) */
case 0x79: /* FRINTI */
case 0x7a: /* FCVTPU */
case 0x7b: /* FCVTZU */
}
}
-/* C3.6.18 AdvSIMD vector x indexed element
+/* C3.6.13 AdvSIMD scalar x indexed element
+ * 31 30 29 28 24 23 22 21 20 19 16 15 12 11 10 9 5 4 0
+ * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+
+ * | 0 1 | U | 1 1 1 1 1 | size | L | M | Rm | opc | H | 0 | Rn | Rd |
+ * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+
+ * C3.6.18 AdvSIMD vector x indexed element
* 31 30 29 28 24 23 22 21 20 19 16 15 12 11 10 9 5 4 0
* +---+---+---+-----------+------+---+---+------+-----+---+---+------+------+
* | 0 | Q | U | 0 1 1 1 1 | size | L | M | Rm | opc | H | 0 | Rn | Rd |
* +---+---+---+-----------+------+---+---+------+-----+---+---+------+------+
*/
-static void disas_simd_indexed_vector(DisasContext *s, uint32_t insn)
+static void disas_simd_indexed(DisasContext *s, uint32_t insn)
{
/* This encoding has two kinds of instruction:
* normal, where we perform elt x idxelt => elt for each
* double the width of the input element
* The long ops have a 'part' specifier (ie come in INSN, INSN2 pairs).
*/
+ bool is_scalar = extract32(insn, 28, 1);
bool is_q = extract32(insn, 30, 1);
bool u = extract32(insn, 29, 1);
int size = extract32(insn, 22, 2);
switch (opcode) {
case 0x0: /* MLA */
case 0x4: /* MLS */
- if (!u) {
+ if (!u || is_scalar) {
unallocated_encoding(s);
return;
}
case 0x2: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
case 0x6: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
case 0xa: /* SMULL, SMULL2, UMULL, UMULL2 */
+ if (is_scalar) {
+ unallocated_encoding(s);
+ return;
+ }
is_long = true;
break;
case 0x3: /* SQDMLAL, SQDMLAL2 */
/* fall through */
case 0xc: /* SQDMULH */
case 0xd: /* SQRDMULH */
- case 0x8: /* MUL */
if (u) {
unallocated_encoding(s);
return;
}
break;
+ case 0x8: /* MUL */
+ if (u || is_scalar) {
+ unallocated_encoding(s);
+ return;
+ }
+ break;
case 0x1: /* FMLA */
case 0x5: /* FMLS */
if (u) {
}
}
- if (is_long) {
- unsupported_encoding(s, insn);
- return;
- }
-
if (is_fp) {
fpst = get_fpstatus_ptr();
} else {
read_vec_element(s, tcg_idx, rm, index, MO_64);
- for (pass = 0; pass < 2; pass++) {
+ for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) {
TCGv_i64 tcg_op = tcg_temp_new_i64();
TCGv_i64 tcg_res = tcg_temp_new_i64();
tcg_temp_free_i64(tcg_res);
}
+ if (is_scalar) {
+ clear_vec_high(s, rd);
+ }
+
tcg_temp_free_i64(tcg_idx);
} else if (!is_long) {
- /* 32 bit floating point, or 16 or 32 bit integer */
+ /* 32 bit floating point, or 16 or 32 bit integer.
+ * For the 16 bit scalar case we use the usual Neon helpers and
+ * rely on the fact that 0 op 0 == 0 with no side effects.
+ */
TCGv_i32 tcg_idx = tcg_temp_new_i32();
- int pass;
+ int pass, maxpasses;
+
+ if (is_scalar) {
+ maxpasses = 1;
+ } else {
+ maxpasses = is_q ? 4 : 2;
+ }
read_vec_element_i32(s, tcg_idx, rm, index, size);
- if (size == 1) {
+ if (size == 1 && !is_scalar) {
/* The simplest way to handle the 16x16 indexed ops is to duplicate
* the index into both halves of the 32 bit tcg_idx and then use
* the usual Neon helpers.
tcg_gen_deposit_i32(tcg_idx, tcg_idx, tcg_idx, 16, 16);
}
- for (pass = 0; pass < (is_q ? 4 : 2); pass++) {
+ for (pass = 0; pass < maxpasses; pass++) {
TCGv_i32 tcg_op = tcg_temp_new_i32();
TCGv_i32 tcg_res = tcg_temp_new_i32();
- read_vec_element_i32(s, tcg_op, rn, pass, MO_32);
+ read_vec_element_i32(s, tcg_op, rn, pass, is_scalar ? size : MO_32);
switch (opcode) {
case 0x0: /* MLA */
g_assert_not_reached();
}
- write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
+ 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_op);
tcg_temp_free_i32(tcg_res);
}
}
} else {
/* long ops: 16x16->32 or 32x32->64 */
+ TCGv_i64 tcg_res[2];
+ int pass;
+ bool satop = extract32(opcode, 0, 1);
+ TCGMemOp memop = MO_32;
+
+ if (satop || !u) {
+ memop |= MO_SIGN;
+ }
+
+ if (size == 2) {
+ TCGv_i64 tcg_idx = tcg_temp_new_i64();
+
+ read_vec_element(s, tcg_idx, rm, index, memop);
+
+ for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) {
+ TCGv_i64 tcg_op = tcg_temp_new_i64();
+ TCGv_i64 tcg_passres;
+ int passelt;
+
+ if (is_scalar) {
+ passelt = 0;
+ } else {
+ passelt = pass + (is_q * 2);
+ }
+
+ read_vec_element(s, tcg_op, rn, passelt, memop);
+
+ tcg_res[pass] = tcg_temp_new_i64();
+
+ if (opcode == 0xa || opcode == 0xb) {
+ /* Non-accumulating ops */
+ tcg_passres = tcg_res[pass];
+ } else {
+ tcg_passres = tcg_temp_new_i64();
+ }
+
+ tcg_gen_mul_i64(tcg_passres, tcg_op, tcg_idx);
+ tcg_temp_free_i64(tcg_op);
+
+ if (satop) {
+ /* saturating, doubling */
+ gen_helper_neon_addl_saturate_s64(tcg_passres, cpu_env,
+ tcg_passres, tcg_passres);
+ }
+
+ if (opcode == 0xa || opcode == 0xb) {
+ continue;
+ }
+
+ /* Accumulating op: handle accumulate step */
+ read_vec_element(s, tcg_res[pass], rd, pass, MO_64);
+
+ switch (opcode) {
+ case 0x2: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
+ tcg_gen_add_i64(tcg_res[pass], tcg_res[pass], tcg_passres);
+ break;
+ case 0x6: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
+ tcg_gen_sub_i64(tcg_res[pass], tcg_res[pass], tcg_passres);
+ break;
+ case 0x7: /* SQDMLSL, SQDMLSL2 */
+ tcg_gen_neg_i64(tcg_passres, tcg_passres);
+ /* fall through */
+ case 0x3: /* SQDMLAL, SQDMLAL2 */
+ gen_helper_neon_addl_saturate_s64(tcg_res[pass], cpu_env,
+ tcg_res[pass],
+ tcg_passres);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ tcg_temp_free_i64(tcg_passres);
+ }
+ tcg_temp_free_i64(tcg_idx);
+
+ if (is_scalar) {
+ clear_vec_high(s, rd);
+ }
+ } else {
+ TCGv_i32 tcg_idx = tcg_temp_new_i32();
+
+ assert(size == 1);
+ read_vec_element_i32(s, tcg_idx, rm, index, size);
+
+ if (!is_scalar) {
+ /* The simplest way to handle the 16x16 indexed ops is to
+ * duplicate the index into both halves of the 32 bit tcg_idx
+ * and then use the usual Neon helpers.
+ */
+ tcg_gen_deposit_i32(tcg_idx, tcg_idx, tcg_idx, 16, 16);
+ }
+
+ for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) {
+ TCGv_i32 tcg_op = tcg_temp_new_i32();
+ TCGv_i64 tcg_passres;
+
+ if (is_scalar) {
+ read_vec_element_i32(s, tcg_op, rn, pass, size);
+ } else {
+ read_vec_element_i32(s, tcg_op, rn,
+ pass + (is_q * 2), MO_32);
+ }
+
+ tcg_res[pass] = tcg_temp_new_i64();
+
+ if (opcode == 0xa || opcode == 0xb) {
+ /* Non-accumulating ops */
+ tcg_passres = tcg_res[pass];
+ } else {
+ tcg_passres = tcg_temp_new_i64();
+ }
+
+ if (memop & MO_SIGN) {
+ gen_helper_neon_mull_s16(tcg_passres, tcg_op, tcg_idx);
+ } else {
+ gen_helper_neon_mull_u16(tcg_passres, tcg_op, tcg_idx);
+ }
+ if (satop) {
+ gen_helper_neon_addl_saturate_s32(tcg_passres, cpu_env,
+ tcg_passres, tcg_passres);
+ }
+ tcg_temp_free_i32(tcg_op);
+
+ if (opcode == 0xa || opcode == 0xb) {
+ continue;
+ }
+
+ /* Accumulating op: handle accumulate step */
+ read_vec_element(s, tcg_res[pass], rd, pass, MO_64);
+
+ switch (opcode) {
+ case 0x2: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
+ gen_helper_neon_addl_u32(tcg_res[pass], tcg_res[pass],
+ tcg_passres);
+ break;
+ case 0x6: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
+ gen_helper_neon_subl_u32(tcg_res[pass], tcg_res[pass],
+ tcg_passres);
+ break;
+ case 0x7: /* SQDMLSL, SQDMLSL2 */
+ gen_helper_neon_negl_u32(tcg_passres, tcg_passres);
+ /* fall through */
+ case 0x3: /* SQDMLAL, SQDMLAL2 */
+ gen_helper_neon_addl_saturate_s32(tcg_res[pass], cpu_env,
+ tcg_res[pass],
+ tcg_passres);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ tcg_temp_free_i64(tcg_passres);
+ }
+ tcg_temp_free_i32(tcg_idx);
+
+ if (is_scalar) {
+ tcg_gen_ext32u_i64(tcg_res[0], tcg_res[0]);
+ }
+ }
+
+ if (is_scalar) {
+ tcg_res[1] = tcg_const_i64(0);
+ }
+
+ for (pass = 0; pass < 2; pass++) {
+ write_vec_element(s, tcg_res[pass], rd, pass, MO_64);
+ tcg_temp_free_i64(tcg_res[pass]);
+ }
}
if (!TCGV_IS_UNUSED_PTR(fpst)) {
{ 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc },
{ 0x0e300800, 0x9f3e0c00, disas_simd_across_lanes },
{ 0x0e000400, 0x9fe08400, disas_simd_copy },
- { 0x0f000000, 0x9f000400, disas_simd_indexed_vector },
+ { 0x0f000000, 0x9f000400, disas_simd_indexed }, /* vector indexed */
/* simd_mod_imm decode is a subset of simd_shift_imm, so must precede it */
{ 0x0f000400, 0x9ff80400, disas_simd_mod_imm },
{ 0x0f000400, 0x9f800400, disas_simd_shift_imm },
{ 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc },
{ 0x5e300800, 0xdf3e0c00, disas_simd_scalar_pairwise },
{ 0x5e000400, 0xdfe08400, disas_simd_scalar_copy },
- { 0x5f000000, 0xdf000400, disas_simd_scalar_indexed },
+ { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */
{ 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm },
{ 0x4e280800, 0xff3e0c00, disas_crypto_aes },
{ 0x5e000000, 0xff208c00, disas_crypto_three_reg_sha },
projects / qemu.git / blobdiff