@@ -3273,6 +3273,11 @@ static inline bool isar_feature_aa32_vcma(const ARMISARegisters *id)
return FIELD_EX32(id->id_isar5, ID_ISAR5, VCMA) != 0;
}
+static inline bool isar_feature_aa32_jscvt(const ARMISARegisters *id)
+{
+ return FIELD_EX32(id->id_isar6, ID_ISAR6, JSCVT) != 0;
+}
+
static inline bool isar_feature_aa32_dp(const ARMISARegisters *id)
{
return FIELD_EX32(id->id_isar6, ID_ISAR6, DP) != 0;
@@ -3351,6 +3356,11 @@ static inline bool isar_feature_aa64_dp(const ARMISARegisters *id)
return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, DP) != 0;
}
+static inline bool isar_feature_aa64_jscvt(const ARMISARegisters *id)
+{
+ return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, JSCVT) != 0;
+}
+
static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id)
{
return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0;
@@ -218,6 +218,9 @@ DEF_HELPER_FLAGS_2(rintd_exact, TCG_CALL_NO_RWG, f64, f64, ptr)
DEF_HELPER_FLAGS_2(rints, TCG_CALL_NO_RWG, f32, f32, ptr)
DEF_HELPER_FLAGS_2(rintd, TCG_CALL_NO_RWG, f64, f64, ptr)
+DEF_HELPER_FLAGS_2(vjcvt, TCG_CALL_NO_RWG, i32, f64, env)
+DEF_HELPER_FLAGS_2(fjcvtzs, TCG_CALL_NO_RWG, i64, f64, ptr)
+
/* neon_helper.c */
DEF_HELPER_FLAGS_3(neon_qadd_u8, TCG_CALL_NO_RWG, i32, env, i32, i32)
DEF_HELPER_FLAGS_3(neon_qadd_s8, TCG_CALL_NO_RWG, i32, env, i32, i32)
@@ -2001,6 +2001,7 @@ static void arm_max_initfn(Object *obj)
cpu->isar.id_isar5 = t;
t = cpu->isar.id_isar6;
+ t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1);
t = FIELD_DP32(t, ID_ISAR6, DP, 1);
cpu->isar.id_isar6 = t;
@@ -311,6 +311,7 @@ static void aarch64_max_initfn(Object *obj)
cpu->isar.id_aa64isar0 = t;
t = cpu->isar.id_aa64isar1;
+ t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 1);
t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1);
t = FIELD_DP64(t, ID_AA64ISAR1, APA, 1); /* PAuth, architected only */
t = FIELD_DP64(t, ID_AA64ISAR1, API, 0);
@@ -344,6 +345,7 @@ static void aarch64_max_initfn(Object *obj)
cpu->isar.id_isar5 = u;
u = cpu->isar.id_isar6;
+ u = FIELD_DP32(u, ID_ISAR6, JSCVT, 1);
u = FIELD_DP32(u, ID_ISAR6, DP, 1);
cpu->isar.id_isar6 = u;
@@ -6526,6 +6526,24 @@ static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof)
}
}
+static void handle_fjcvtzs(DisasContext *s, int rd, int rn)
+{
+ TCGv_i64 t = read_fp_dreg(s, rn);
+ TCGv_ptr fpstatus = get_fpstatus_ptr(false);
+
+ gen_helper_fjcvtzs(t, t, fpstatus);
+
+ tcg_temp_free_ptr(fpstatus);
+
+ tcg_gen_ext32u_i64(cpu_reg(s, rd), t);
+ tcg_gen_extrh_i64_i32(cpu_ZF, t);
+ tcg_gen_movi_i32(cpu_CF, 0);
+ tcg_gen_movi_i32(cpu_NF, 0);
+ tcg_gen_movi_i32(cpu_VF, 0);
+
+ tcg_temp_free_i64(t);
+}
+
/* Floating point <-> integer conversions
* 31 30 29 28 24 23 22 21 20 19 18 16 15 10 9 5 4 0
* +----+---+---+-----------+------+---+-------+-----+-------------+----+----+
@@ -6601,6 +6619,14 @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn)
handle_fmov(s, rd, rn, type, itof);
break;
+ case 0b00111110: /* FJCVTZS */
+ if (!dc_isar_feature(aa64_jscvt, s)) {
+ goto do_unallocated;
+ } else if (fp_access_check(s)) {
+ handle_fjcvtzs(s, rd, rn);
+ }
+ break;
+
default:
do_unallocated:
unallocated_encoding(s);
@@ -3718,6 +3718,13 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn)
rm_is_dp = false;
break;
+ case 0x13: /* vjcvt */
+ if (!dp || !dc_isar_feature(aa32_jscvt, s)) {
+ return 1;
+ }
+ rd_is_dp = false;
+ break;
+
default:
return 1;
}
@@ -4088,6 +4095,9 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn)
case 17: /* fsito */
gen_vfp_sito(dp, 0);
break;
+ case 19: /* vjcvt */
+ gen_helper_vjcvt(cpu_F0s, cpu_F0d, cpu_env);
+ break;
case 20: /* fshto */
gen_vfp_shto(dp, 16 - rm, 0);
break;
@@ -1086,3 +1086,91 @@ int arm_rmode_to_sf(int rmode)
}
return rmode;
}
+
+/*
+ * Implement float64 to int32_t conversion without saturation;
+ * the result is supplied modulo 2^32.
+ */
+uint64_t HELPER(fjcvtzs)(float64 value, void *vstatus)
+{
+ float_status *status = vstatus;
+ uint32_t exp, sign;
+ uint64_t frac;
+ uint32_t inexact = 1; /* !Z */
+
+ sign = extract64(value, 63, 1);
+ exp = extract64(value, 52, 11);
+ frac = extract64(value, 0, 52);
+
+ if (exp == 0) {
+ /* While not inexact for IEEE FP, -0.0 is inexact for JavaScript. */
+ inexact = sign;
+ if (frac != 0) {
+ if (status->flush_inputs_to_zero) {
+ float_raise(float_flag_input_denormal, status);
+ } else {
+ float_raise(float_flag_inexact, status);
+ inexact = 1;
+ }
+ }
+ frac = 0;
+ } else if (exp == 0x7ff) {
+ /* This operation raises Invalid for both NaN and overflow (Inf). */
+ float_raise(float_flag_invalid, status);
+ frac = 0;
+ } else {
+ int true_exp = exp - 1023;
+ int shift = true_exp - 52;
+
+ /* Restore implicit bit. */
+ frac |= 1ull << 52;
+
+ /* Shift the fraction into place. */
+ if (shift >= 0) {
+ /* The number is so large we must shift the fraction left. */
+ if (shift >= 64) {
+ /* The the fraction is shifted out entirely. */
+ frac = 0;
+ } else {
+ frac <<= shift;
+ }
+ } else if (shift > -64) {
+ /* Normal case -- shift right and notice if bits shift out. */
+ inexact = (frac << (64 + shift)) != 0;
+ frac >>= -shift;
+ } else {
+ /* The fraction is shifted out entirely. */
+ frac = 0;
+ }
+
+ /* Notice overflow or inexact exceptions. */
+ if (true_exp > 31 || frac > (sign ? 0x80000000ull : 0x7fffffff)) {
+ /* Overflow, for which this operation raises invalid. */
+ float_raise(float_flag_invalid, status);
+ inexact = 1;
+ } else if (inexact) {
+ float_raise(float_flag_inexact, status);
+ }
+
+ /* Honor the sign. */
+ if (sign) {
+ frac = -frac;
+ }
+ }
+
+ /* Pack the result and the env->ZF representation of Z together. */
+ return deposit64(frac, 32, 32, inexact);
+}
+
+uint32_t HELPER(vjcvt)(float64 value, CPUARMState *env)
+{
+ uint64_t pair = HELPER(fjcvtzs)(value, &env->vfp.fp_status);
+ uint32_t result = pair;
+ uint32_t z = (pair >> 32) == 0;
+
+ /* Store Z, clear NCV, in FPSCR.NZCF. */
+ env->vfp.xregs[ARM_VFP_FPSCR]
+ = (env->vfp.xregs[ARM_VFP_FPSCR] & ~CPSR_NZCV) | (z * CPSR_Z);
+
+ return result;
+}
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v2: Return 0 for NaN v3: Return aa32 flags in FPSCR.NZCV. --- target/arm/cpu.h | 10 +++++ target/arm/helper.h | 3 ++ target/arm/cpu.c | 1 + target/arm/cpu64.c | 2 + target/arm/translate-a64.c | 26 +++++++++++ target/arm/translate.c | 10 +++++ target/arm/vfp_helper.c | 88 ++++++++++++++++++++++++++++++++++++++ 7 files changed, 140 insertions(+) -- 2.17.2