- •Contents
- •List of Tables
- •List of Figures
- •Preface
- •About this document
- •Intended audience
- •Using this manual
- •Typographical conventions
- •Timing diagram conventions
- •Further reading
- •ARM publications
- •Other publications
- •Feedback
- •Feedback on the ARM7TDMI core
- •Feedback on this document
- •Introduction
- •1.1 About the ARM7TDMI core
- •1.1.1 The instruction pipeline
- •1.1.2 Memory access
- •1.1.3 Memory interface
- •1.1.4 EmbeddedICE Logic
- •1.2 Architecture
- •1.2.1 Instruction compression
- •1.2.2 The Thumb instruction set
- •1.3 Block, core, and functional diagrams
- •1.4 Instruction set summary
- •1.4.1 Format summary
- •1.4.2 ARM instruction summary
- •1.4.3 Thumb instruction summary
- •Programmer’s Model
- •2.1 About the programmer’s model
- •2.2 Processor operating states
- •2.2.1 Switching state
- •2.3 Memory formats
- •2.3.1 Little-endian
- •2.3.2 Big-Endian
- •2.4 Data types
- •2.5 Operating modes
- •2.6 Registers
- •2.6.4 Accessing high registers in Thumb state
- •2.7 The program status registers
- •2.7.1 Condition code flags
- •2.7.2 Control bits
- •2.7.3 Reserved bits
- •2.8 Exceptions
- •2.8.1 Exception entry and exit summary
- •2.8.2 Entering an exception
- •2.8.3 Leaving an exception
- •2.8.4 Fast interrupt request
- •2.8.5 Interrupt request
- •2.8.6 Abort
- •2.8.7 Software interrupt instruction
- •2.8.8 Undefined instruction
- •2.8.9 Exception vectors
- •2.8.10 Exception priorities
- •2.9 Interrupt latencies
- •2.9.1 Maximum interrupt latencies
- •2.9.2 Minimum interrupt latencies
- •2.10 Reset
- •Memory Interface
- •3.1 About the memory interface
- •3.2 Bus interface signals
- •3.3 Bus cycle types
- •3.3.1 Nonsequential cycles
- •3.3.2 Sequential cycles
- •3.3.3 Internal cycles
- •3.3.4 Merged IS cycles
- •3.3.5 Coprocessor register transfer cycles
- •3.3.6 Summary of ARM memory cycle timing
- •3.4 Addressing signals
- •3.4.4 nOPC
- •3.4.5 nTRANS
- •3.4.6 LOCK
- •3.4.7 TBIT
- •3.5 Address timing
- •3.6 Data timed signals
- •3.6.1 D[31:0], DOUT[31:0], and DIN[31:0]
- •3.6.2 ABORT
- •3.6.3 Byte latch enables
- •3.6.4 Byte and halfword accesses
- •3.7 Stretching access times
- •3.7.1 Modulating MCLK
- •3.7.2 Use of nWAIT to control bus cycles
- •3.8 Action of ARM7TDMI core in debug state
- •3.9 Privileged mode access
- •3.10 Reset sequence after power up
- •Coprocessor Interface
- •4.1 About coprocessors
- •4.1.1 Coprocessor availability
- •4.2 Coprocessor interface signals
- •4.3 Pipeline following signals
- •4.4 Coprocessor interface handshaking
- •4.4.1 The coprocessor
- •4.4.2 The ARM7TDMI processor
- •4.4.3 Coprocessor signaling
- •4.4.5 Coprocessor register transfer instructions
- •4.4.6 Coprocessor data operations
- •4.4.7 Coprocessor load and store operations
- •4.5 Connecting coprocessors
- •4.5.1 Connecting a single coprocessor
- •4.5.2 Connecting multiple coprocessors
- •4.6 If you are not using an external coprocessor
- •4.7 Undefined instructions
- •4.8 Privileged instructions
- •Debug Interface
- •5.1 About the debug interface
- •5.1.1 Stages of debug
- •5.1.2 Clocks
- •5.2 Debug systems
- •5.2.1 Debug host
- •5.2.2 Protocol converter
- •5.2.3 Debug target
- •5.3 Debug interface signals
- •5.3.1 Entry into debug state
- •5.3.2 Action of the processor in debug state
- •5.4 ARM7TDMI core clock domains
- •5.4.1 Clock switch during debug
- •5.4.2 Clock switch during test
- •5.5 Determining the core and system state
- •5.6 About EmbeddedICE Logic
- •5.7 Disabling EmbeddedICE
- •5.8 Debug Communications Channel
- •5.8.1 DCC registers
- •5.8.2 Communications through the DCC
- •Instruction Cycle Timings
- •6.1 About the instruction cycle timing tables
- •6.2 Branch and branch with link
- •6.3 Thumb branch with link
- •6.4 Branch and Exchange
- •6.5 Data operations
- •6.6 Multiply and multiply accumulate
- •6.7 Load register
- •6.8 Store register
- •6.9 Load multiple registers
- •6.10 Store multiple registers
- •6.11 Data swap
- •6.12 Software interrupt and exception entry
- •6.13 Coprocessor data operation
- •6.14 Coprocessor data transfer from memory to coprocessor
- •6.15 Coprocessor data transfer from coprocessor to memory
- •6.16 Coprocessor register transfer, load from coprocessor
- •6.17 Coprocessor register transfer, store to coprocessor
- •6.18 Undefined instructions and coprocessor absent
- •6.19 Unexecuted instructions
- •6.20 Instruction speed summary
- •AC and DC Parameters
- •7.1 Timing diagram information
- •7.2 General timing
- •7.3 Address bus enable control
- •7.4 Bidirectional data write cycle
- •7.5 Bidirectional data read cycle
- •7.6 Data bus control
- •7.8 Unidirectional data write cycle timing
- •7.9 Unidirectional data read cycle timing
- •7.10 Configuration pin timing
- •7.11 Coprocessor timing
- •7.12 Exception timing
- •7.13 Synchronous interrupt timing
- •7.14 Debug timing
- •7.15 Debug communications channel output timing
- •7.16 Breakpoint timing
- •7.17 Test clock and external clock timing
- •7.18 Memory clock timing
- •7.19 Boundary scan general timing
- •7.20 Reset period timing
- •7.21 Output enable and disable times
- •7.22 Address latch enable control
- •7.23 Address pipeline control timing
- •7.24 Notes on AC Parameters
- •7.25 DC parameters
- •Signal Description
- •A.1 Signal description
- •A.1.1 Transistor dimensions
- •A.1.2 Signal types
- •A.1.3 Signals
- •Debug in Depth
- •B.1 Scan chains and JTAG interface
- •B.1.1 Scan chain implementation
- •B.1.2 TAP state machine
- •B.2 Resetting the TAP controller
- •B.3 Pullup resistors
- •B.4 Instruction register
- •B.5 Public instructions
- •B.5.1 EXTEST (0000)
- •B.5.2 SCAN_N (0010)
- •B.5.3 SAMPLE/PRELOAD (0011)
- •B.5.4 RESTART (0100)
- •B.5.5 CLAMP (0101)
- •B.5.6 HIGHZ (0111)
- •B.5.7 CLAMPZ (1001)
- •B.5.8 INTEST (1100)
- •B.5.9 IDCODE (1110)
- •B.5.10 BYPASS (1111)
- •B.6 Test data registers
- •B.6.1 Bypass register
- •B.6.2 ARM7TDMI core device IDentification (ID) code register
- •B.6.5 Scan chains 0, 1, 2, and 3
- •B.7 The ARM7TDMI core clocks
- •B.7.1 Clock switch during debug
- •B.7.2 Clock switch during test
- •B.8 Determining the core and system state
- •B.8.1 Determining the core state
- •B.8.2 Determining system state
- •B.8.3 Exit from debug state
- •B.9 Behavior of the program counter during debug
- •B.9.1 Breakpoints
- •B.9.2 Watchpoints
- •B.9.3 Watchpoint with another exception
- •B.9.4 Debug request
- •B.9.5 System speed access
- •B.9.6 Summary of return address calculations
- •B.10 Priorities and exceptions
- •B.10.1 Breakpoint with Prefetch Abort
- •B.10.2 Interrupts
- •B.10.3 Data Aborts
- •B.11 Scan chain cell data
- •B.11.1 Scan chain 0 cells
- •B.11.2 Scan chain 1 cells
- •B.12 The watchpoint registers
- •B.12.1 Programming and reading watchpoint registers
- •B.12.2 Using the mask registers
- •B.12.3 The control registers
- •B.13 Programming breakpoints
- •B.13.1 Hardware breakpoints
- •B.13.2 Software breakpoints
- •B.14 Programming watchpoints
- •B.15 The debug control register
- •B.16 The debug status register
- •B.17 Coupling breakpoints and watchpoints
- •B.17.1 Breakpoint and watchpoint coupling example
- •B.17.2 RANGEOUT signal
- •B.18 EmbeddedICE timing
- •B.19 Programming Restriction
- •Glossary
- •Index
Chapter 6
Instruction Cycle Timings
This chapter describes the ARM7TDMI processor instruction cycle operations. It contains the following sections:
•About the instruction cycle timing tables on page 6-3
•Branch and branch with link on page 6-4
•Thumb branch with link on page 6-5
•Branch and Exchange on page 6-6
•Data operations on page 6-7
•Multiply and multiply accumulate on page 6-9
•Load register on page 6-12
•Store register on page 6-14
•Load multiple registers on page 6-15
•Store multiple registers on page 6-17
•Data swap on page 6-18
•SSoftware interrupt and exception entry on page 6-19
•Coprocessor data operation on page 6-20
•Coprocessor data transfer from memory to coprocessor on page 6-21
•Coprocessor data transfer from coprocessor to memory on page 6-23
•Coprocessor register transfer, load from coprocessor on page 6-25
ARM DDI 0029G |
Copyright © 1994-2001. All rights reserved. |
6-1 |
Instruction Cycle Timings
•Coprocessor register transfer, store to coprocessor on page 6-26
•Undefined instructions and coprocessor absent on page 6-27
•Unexecuted instructions on page 6-28
•Instruction speed summary on page 6-29.
6-2 |
Copyright © 1994-2001. All rights reserved. |
ARM DDI 0029G |
Instruction Cycle Timings
6.1About the instruction cycle timing tables
In the following tables:
•nMREQ and SEQ, are pipelined up to one cycle ahead of the cycle to which they apply. They are shown in the cycle in which they appear and indicate the next cycle type.
•The address, MAS[1:0], nRW, nOPC, nTRANS, and TBIT signals, that appear up to half a cycle ahead, are shown in the cycle to which they apply. The address is incremented to prefetch instructions in most cases. Because the instruction width is four bytes in ARM state and two bytes in Thumb state, the increment varies accordingly.
•The letter L is used to indicate instruction length:
—four bytes in ARM state
—two bytes in Thumb state.
•The letter i is used to indicate the width of the instruction fetch output by
MAS[1:0]:
—i=2 in ARM state represents word accesses
—i=1 in Thumb state represents halfword accesses.
•Terms placed inside brackets represent the contents of an address.
•The • symbol indicates zero or more cycles.
ARM DDI 0029G |
Copyright © 1994-2001. All rights reserved. |
6-3 |
Instruction Cycle Timings
6.2Branch and branch with link
A branch instruction calculates the branch destination in the first cycle, while performing a prefetch from the current PC. This prefetch is done in all cases because, by the time the decision to take the branch has been reached, it is already too late to prevent the prefetch.
During the second cycle a fetch is performed from the branch destination, and the return address is stored in register 14 if the link bit is set.
The third cycle performs a fetch from the destination +L, refilling the instruction pipeline. If the instruction is a branch with link (R14 is modified) four is subtracted from R14 to simplify the return instruction from SUB PC,R14,#4 to MOV PC,R14. This allows subroutines to push R14 onto the stack and pop directly into PC upon completion.
The cycle timings are listed in Table 6-1 where:
•pc is the address of the branch instruction
•alu is the destination address calculated by the ARM7TDMI core
•(alu) is the contents of that address.
Table 6-1 Branch instruction cycle operations
Cycle |
Address |
MAS[1:0] |
nRW |
Data |
nMREQ |
SEQ |
nOPC |
|
|
|
|
|
|
|
|
1 |
pc+2L |
i |
0 |
(pc+2L) |
0 |
0 |
0 |
|
|
|
|
|
|
|
|
2 |
alu |
i |
0 |
(alu) |
0 |
1 |
0 |
|
|
|
|
|
|
|
|
3 |
alu+L |
i |
0 |
(alu+L) |
0 |
1 |
0 |
|
|
|
|
|
|
|
|
|
alu+2L |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Note
Branch with link is not available in Thumb state.
6-4 |
Copyright © 1994-2001. All rights reserved. |
ARM DDI 0029G |