Intel ITANIUM ARCHITECTURE - SOFTWARE DEVELOPERS MANUAL VOLUME 1 REV 2.3 Manual page 969

fcvt.fx
fcvt.fx — Convert Floating-point to Integer
( ) fcvt.fx.
Format: qp
( ) fcvt.fx.trunc.
qp
( ) fcvt.fxu.
qp
( ) fcvt.fxu.trunc.
qp
FR is treated as a register format floating-point value and converted to a signed
Description:
f
2
(signed_form) or unsigned integer (unsigned_form) using either the rounding mode
specified in the FPSR.sf.rc, or using Round-to-Zero if the trunc_form of the instruction is
used. The result is placed in the 64-bit significand field of FR
is set to the biased exponent for 2.0
f
1
positive (0). If the result of the conversion cannot be represented as a 64-bit integer,
the 64-bit integer indefinite value 0x8000000000000000 is used as the result, if the
IEEE Invalid Operation Floating-point Exception fault is disabled.
If FR is a NaTVal, FR
f
2
The mnemonic values for sf are given in
Operation:
if (PR[qp]) {
fp_check_target_register(f
if (tmp_isrcode = fp_reg_disabled(f
disabled_fp_register_fault(tmp_isrcode, 0);
if (fp_is_natval(FR[f
FR[f
fp_update_psr(f
} else {
tmp_default_result = fcvt_exception_fault_check(f
if (fp_raise_fault(tmp_fp_env))
if (fp_is_nan(tmp_default_result)) {
} else {
}
fp_update_fpsr(sf, tmp_fp_env);
fp_update_psr(f
if (fp_raise_traps(tmp_fp_env))
}
}
3:70
=
sf f f
1 2
=
sf f f
1 2
=
sf f f
1 2
=
sf f f
1 2
is set to NaTVal instead of the computed result.
f
1
])) {
2
] = NATVAL;
1
);
1
fp_exception_fault(fp_decode_fault(tmp_fp_env));
FR[f ].significand = INTEGER_INDEFINITE;
1
FR[f ].exponent = FP_INTEGER_EXP;
1
FR[f ].sign = FP_SIGN_POSITIVE;
1
tmp_res = fp_ieee_rnd_to_int(fp_reg_read(FR[f
if (tmp_res.exponent)
tmp_res.significand = fp_U64_rsh(
tmp_res.significand, (FP_INTEGER_EXP - tmp_res.exponent));
if (signed_form && tmp_res.sign)
tmp_res.significand = (~tmp_res.significand) + 1;
FR[f ].significand = tmp_res.significand;
1
FR[f ].exponent = FP_INTEGER_EXP;
1
FR[f ].sign = FP_SIGN_POSITIVE;
1
);
1
fp_exception_trap(fp_decode_trap(tmp_fp_env));
unsigned_form, trunc_form
63
(0x1003E) and the sign field of FR
Table 2-23 on page
);
1
, f , 0, 0))
1 2
trunc_form, sf, &tmp_fp_env);
signed_form
signed_form, trunc_form
unsigned_form
. The exponent field of FR
f
1
is set to
f
1
3:56.
, signed_form,
2
]), &tmp_fp_env);
2
Volume 3: Instruction Reference
F10
F10
F10
F10