7 fpu instruction execution times, Fpu instruction execution times -35 – Freescale Semiconductor MCF5480 User Manual

Page 139

Advertising
background image

Instruction Execution Timing

MCF548x Reference Manual, Rev. 3

Freescale Semiconductor

3-35

Execution times for moving the contents of the ACC, ACCext[01,23], MACSR, or MASK into a

destination location <ea>x in this table represent the best-case scenario when the store is executed and no

load, copy, MAC, or MSAC instructions are in the EMAC execution pipeline. In general, these store

operations require only a single cycle for execution, but if preceded immediately by a load, copy, MAC,

or MSAC instruction, the depth of the EMAC pipeline is exposed and the execution time is 4 cycles.

3.7.7

FPU Instruction Execution Times

Table 3-20

specifies the instruction execution times associated with the FPU execute engine.

mulu.l

<ea>y,Dx

4(0/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

mulu.w

<ea>y,Dx

4(0/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

5(1/0)

4(1/0)

4(0/0)

1

Effective address of (d16,PC) not supported.

2

Storing the accumulator requires 1 additional clock cycle when saturation is enabled, or fractional rounding is performed
(MACSR[7:4] = 1---, -11-, --11).

Table 3-20. FPU Instruction Execution Times

1,

2

Opcode

Format

Effective Address <ea>

FPn

Dn

(An)

(An)+

–(An)

(d

16

,An)

(d

16

,PC)

fabs

<ea>y,FPx

1(0/0)

1(0/0)

1(1/0)

1(1/0)

1(1/0)

1(1/0)

1(1/0)

fadd

<ea>y,FPx

4(0/0)

4(0/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

fbcc

<label>

2(0/0) if correct,

9(0/0) if incorrect

fcmp

<ea>y,FPx

4(0/0)

4(0/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

fdiv

<ea>y,FPx

23(0/0)

23(0/0)

23(1/0)

23(1/0)

23(1/0)

23(1/0)

23(1/0)

fint

<ea>y,FPx

4(0/0)

4(0/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

fintrz

<ea>y,FPx

4(0/0)

4(0/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

fmove

<ea>y,FPx

1(0/0)

1(0/0)

1(1/0)

1(1/0)

1(1/0)

1(1/0)

1(1/0)

fmove

FPy,<ea>x

2(0/1)

2(0/1)

2(0/1)

2(0/1)

2(0/1)

fmove

<ea>y,FP*R

6(0/0)

6(1/0)

6(1/0)

6(1/0)

6(1/0)

6(1/0)

fmove

FP*R,<ea>x

1(0/0)

1(0/1)

1(0/1)

1(0/1)

1(0/1)

fmovem

3

<ea>y,#list

2n(2n/0)

2n(2n/0)

2n(2n/0)

fmovem

3,

4

#list,<ea>x

1+2n(0/2n)

1+2n(0/2n)

fmul

<ea>y,FPx

4(0/0)

4(0/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

4(1/0)

fneg

<ea>y,FPx

1(0/0)

1(0/0)

1(1/0)

1(1/0)

1(1/0)

1(1/0)

1(1/0)

fnop

2(0/0)

frestore

<ea>y

6(4/0)

6(4/0)

6(4/0)

Table 3-19. EMAC Instruction Execution Times

Opcode

<ea>y

Effective Address

Rn

(An)

(An)+

–(An)

(d16,An)
(d16,PC)

(d8,An,Xi*SF)

(d8,PC,Xi*SF)

xxx.wl

#xxx

Advertising
This manual is related to the following products: