Encoding:

POOL32A

000000

rt

rs

PRECEQU.PH.QBRA

1001001100

POOL32Axf

111100

6

5

5

10

6

SPECIAL3

011111

0

00000

rt

rd

PRECEQU.PH.QBRA

00111

ABSQ_S.PH

010010

6

5

5

5

5

6

Format:

PRECEQU.PH.QBRA rdt, rts

microMIPSDSP

Precision Expand two Unsigned Bytes to Fractional Halfword Values

Purpose:

Precision Expand two Unsigned Bytes to Fractional Halfword Values

Expand the precision of two unsigned byte values taken from the two right-alternate aligned elements of a quad byte vector to create two Q15 fractional halfword values.

Description:

rdt = sign_extend(expand_prec(rts23..16) || expand_prec(rts7..0))

The two right-alternate aligned unsigned integer byte values from the four right-most byte elements in register rts are expanded to create two Q15 fractional values that are then written to destination register rdt. The precision expansion is achieved by pre-pending a single zero bit (for positive sign) to the original byte value and appending seven least-significant zeros to generate each 16-bit fractional value.

The sign of the left-most result is extended into the 32 most-significant bits of the destination register.

Restrictions:

No data-dependent exceptions are possible.

The operands must be values in the specified format. If they are not, the results are UNPREDICTABLE and the values of the operand vectors become UNPREDICTABLE.

Operation:

tempB15..0 = 01 || GPR[rts]23..16 || 07 
tempA15..0 = 01 || GPR[rts]7..0 || 07 
GPR[rdt]63..0 = (tempB15)32 || tempB15..0 || tempA15..0

Exceptions:

Reserved Instruction, DSP Disabled