RSQRSP Single-Precision Floating-Point Square-Root Reciprocal Approximation

Note:

1)If src2 is SNaN, NaN_out is placed in dst and the INVAL and NAN2 bits are set.

2)If src2 is QNaN, NaN_out is placed in dst and the NAN2 bit is set.

3)If src2 is a negative, nonzero, nondenormalized number, NaN_out is placed in dst and the INVAL bit is set.

4)If src2 is a signed denormalized number, signed infinity is placed in dst and the DIV0, INEX, and DEN2 bits are set.

5)If src2 is signed 0, signed infinity is placed in dst and the DIV0 and INFO bits are set. The Newton-Rhapson approximation cannot be used to calculate the square root of 0 because infinity multiplied by 0 is invalid.

6)If src2 is positive infinity, positive 0 is placed in dst.

Pipeline

 

 

 

 

 

 

 

 

 

Pipeline

E1

 

 

 

 

 

 

Stage

 

 

 

 

 

 

 

 

 

 

 

Read

 

src2

 

 

 

Written

dst

 

 

 

Unit in use

 

.S

 

 

 

 

 

 

 

 

 

Instruction Type

Single-cycle

 

 

 

 

Delay Slots

0

 

 

 

 

 

 

Functional Unit

1

 

 

 

 

 

 

Latency

 

 

 

 

 

 

 

 

See Also

RCPSP, RSQRDP

 

 

 

Example 1

RSQRSP .S1

A1,A2

 

 

 

 

 

Before instruction

 

 

 

 

 

 

 

 

 

 

A1

 

4080 0000h

 

4.0

A1

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

A2

 

xxxx xxxxh

 

 

A2

Example 2

 

 

 

 

RSQRSP .S2X A1,B2

 

 

 

 

 

Before instruction

 

 

 

 

 

 

 

 

 

A1

 

4109 999Ah

 

8.6

A1

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

B2

 

xxxx xxxxh

 

 

B2

 

 

 

 

 

 

 

 

 

1 cycle after instruction

4080 0000h 4.0

3F00 0000h 0.5

1 cycle after instruction

4109

999Ah

8.6

 

 

 

 

 

 

3EAE

8000h

0.34082031

 

 

 

3-204

Instruction Set

SPRU733

Page 264
Image 264
Texas Instruments TMS320C67X/C67X+ DSP manual Rsqrsp .S1