fcvt.w.s
Convert single-precision float to integer word to signed 32-bit integer.
This instruction is defined by:
-
F, version >= 0
This instruction is included in the following profiles:
-
RVA20U64 (Mandatory)
-
RVA22U64 (Mandatory)
-
RVI20U32 (Optional)
-
RVI20U64 (Optional)
Synopsis
This instruction must have data-independent timing when extension Zkt is enabled. |
Converts a floating-point number in floating-point register fs1 to a signed 32-bit integer indicates integer register rd.
For XLEN >32, fcvt.w.s sign-extends the 32-bit result to the destination register width.
If the rounded result is not representable as a 32-bit signed integer, it is clipped to the nearest value and the invalid flag is set.
The range of valid inputs and behavior for invalid inputs are:
Value | |
---|---|
Minimum valid input (after rounding) |
|
Maximum valid input (after rounding) |
|
Output for out-of-range negative input |
|
Output for |
|
Output for out-of-range positive input |
|
Output for |
|
All floating-point to integer and integer to floating-point conversion instructions round
according to the rm field.
A floating-point register can be initialized to floating-point positive zero using
fcvt.s.w rd, x0
, which will never set any exception flags.
All floating-point conversion instructions set the Inexact exception flag if the rounded result differs from the operand value and the Invalid exception flag is not set.
Decode Variables
Bits<5> fs1 = $encoding[19:15];
Bits<3> rm = $encoding[14:12];
Bits<5> rd = $encoding[11:7];
Execution
-
IDL
-
Sail
check_f_ok($encoding);
Bits<32> sp_value = f[fs1][31:0];
Bits<1> sign = sp_value[31];
Bits<8> exp = sp_value[30:23];
Bits<23> sig = sp_value[22:0];
RoundingMode rounding_mode = rm_to_mode(rm, $encoding);
if ((exp == 0xff) && (sig != 0)) {
sign = 0;
set_fp_flag(FpFlag::NV);
X[rd] = SP_CANONICAL_NAN;
} else {
if (exp != 0) {
sig = sig | 0x00800000;
}
Bits<64> sig64 = sig << 32;
Bits<16> shift_dist = 0xAA - exp;
if (0 < shift_dist) {
sig64 = softfloat_shiftRightJam64(sig64, shift_dist);
}
X[rd] = softfloat_roundToI32(sign, sig64, rounding_mode);
}
{
assert(sizeof(xlen) >= 64);
let rs1_val_LU = X(rs1)[63..0];
match (select_instr_or_fcsr_rm (rm)) {
None() => { handle_illegal(); RETIRE_FAIL },
Some(rm') => {
let rm_3b = encdec_rounding_mode(rm');
let (fflags, rd_val_S) = riscv_ui64ToF32 (rm_3b, rs1_val_LU);
accrue_fflags(fflags);
F_or_X_S(rd) = rd_val_S;
RETIRE_SUCCESS
}
}
}