SlideShare a Scribd company logo

arm

•
•
Pratik Gohel
Pratik Gohel

This document provides an overview of the ARM processor architecture. It discusses key aspects of ARM including: - ARM's RISC load/store architecture with fixed-length 32-bit instructions. - Its pipeline structure which breaks instructions into stages to allow for parallel execution. - Operating modes like user, system, fast interrupt, and interrupt request that determine privileges. - Support for exceptions and interrupts. - Instruction sets including the main 32-bit ARM set and compressed 16-bit Thumb set. - Popular ARM processor families and cores like ARM7, ARM9, ARM11, Cortex-A, Cortex-M, and features between versions.

1 of 48
Download to read offline
A PRESENTATION BY EDUTECHLEARNERS ARM Advance RISC Machine http://www.edutechlearners.com
ARM Application Apple iPod Nano Ford Sync In-Car Comm & Entertainment System Sony Playstation 3 (60GB) Nokia N93
ARM Partenship
ARM Advantage
Why ARM ??? ARM is one of the most licensed and thus widespread processor cores in the world. Used especially in portable devices due to low power consumption and reasonable performance Several interesting extension available like THUMB instruction set and Jazelle Java Machine
Computer Architecture Describes Users View of the Computer Eg. Instruction Set Visible Registers Memory Management Table Structure Exception Handling Models etc.
Computer Organization Describes User Invisible Implementation of the Architecture Eg. Pipeline Struture Transparent Cache Translation Look Aside Buffers etc
RISC vs. CISC Architecture RISC CISC Fixed width Instructions Variable length instructions Few Formats of Instructions Several formats of instructions Load/Store Architecture Memory Values can be used as operands in instructions Large Register Banks Small Register Bank Instructions are pipelinable Pipelining is complex Single Cycle execution of all instructions Multi cycle execution on instructions
RISC Advantages A small Die Size A Shorter Development Time Higher Performance Smaller things have higher natural frequencies.
RISC Disadvantages Generally poor code density (Fixed Length Instruction)
ARM History ARM – Acron RISC Machine(1983-1985) Acron Computers Limited ,Cambridge, England. ARM – Advanced RISC Machine 1990 ARM Limited ,1990 ARM has been licensed to many semiconductor manufacturers
Architecture Revisions 1998 2000 2002 2004 time version ARMv5 ARMv6 1994 1996 2006 V4 StrongARM® ARM926EJ-S™ XScaleTM ARM102xE ARM1026EJ-S™ ARM9x6E ARM92xT ARM1136JF-S™ ARM7TDMI-S™ ARM720T™ XScale is a trademark of Intel Corporation ARMv7 SC100™ SC200 ™ ARM1176JZF-S™ ARM1156T2F-S™
Features used from RISC A Load/Store Architecture Fixed Length 32 bit Instructions 3-Address Instruction Formats
Load Store Architecture Memory can be accessed only through two dedicated instructions LDR ; Move word from memory to register STR ; Move word from register to memory All other instructions have to work on registers only
3 Address Instruction Format Function Dest. Addr. Op2 Addr. Op1 Addr. f bits n bits n bits n bits Example Add d, s1, s2 ; d =s1+s2
Pipelining Break instructions into steps Work on instructions like in an assembly line Allows for more instructions to be executed in less time A n-stage pipeline is n times faster than a non pipeline processor (in theory)
MISC/RISC Pipeline Stages Fetch instruction Decode instruction Execute instruction Access operand Write result  Note: Slight variations depending on processor
Without Pipelining Normally, you would peform the fetch, decode, execute, operate, and write steps of an instruction and then move on to the next instruction
Without Pipelining Instr 1 Instr 2 Clock Cycle 1 2 3 4 5 6 7 8 9 10
With Pipelining The processor is able to perform each stage simultaneously. If the processor is decoding an instruction, it may also fetch another instruction at the same time.
With Pipelining Clock Cycle 1 2 3 4 5 6 7 8 9 Instr 1 Instr 2 Instr 3 Instr 4 Instr 5
Pipeline (cont.) Length of pipeline depends on the longest step Thus in RISC, all instructions were made to be the same length Each stage takes 1 clock cycle In theory, an instruction should be finished each clock cycle
Pipeline changes for ARM9TDMI Instruction Fetch Shift + ALU Memory Access Reg Write Reg Read Reg Decode FETCH DECODE EXECUTE MEMORY WRITE ARM9TDMI ARM or Thumb Inst Decode Reg Select Reg Read Shift ALU Reg Writ e Thumb→ Α RM decompress ARM decode Instruction Fetch FETCH DECODE EXECUTE ARM7TDMI
ARM10 vs. ARM11 Pipelines ARM11 Fetch 1 Fetch 2 Decode Issue Shift ALU Saturate Write back MAC 1 MAC 2 MAC 3 Address Data Cache 1 Data Cache 2 Shift + ALU Memory Access Reg Write FETCH DECODE EXECUTE MEMORY WRITE Reg Read Multiply Branch Prediction Instruction Fetch ISSUE ARM or Thumb Instruction Decode Multipl y Add ARM10
ARM Design Policy ARM core uses RISC Architecture  Reduced Instruction Set  Load Store Architecture  Large No of General Purpose Registers.  Parallel execution with Pipelines But some differences from RISC  Enhanced instructions for  DSP instructions  THUMB State  Conditional Execution Instructions  32 bit Barrel Shifter
Registers ARM has Load Store Architecture General Purpose Registers can hold data or address Total of 37 Registers each of 32 bit There are 17 or 18 active registers 16 data registers 2 status registers
Registers Registers R0-R12 are General Purpose Registers R13 is used as Stack Pointer(SP) R14 is used as Link Register(LR) R15 is used as Program Counter(PC) CPSR is Current Program Status Register SPSR is Saved Program Status Register R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R13 R14 R15
CPSR N Z C V J U n d e f i n e d I F T M o d e hold information about the most recently performed ALU operation set the processor operating mode • Condition code flags – N = Negative result from ALU – Z = Zero result from ALU – C = ALU operation Carried out – V = ALU operation overflowed • Interrupt Disable bits. – I = 1: Disables the IRQ. – F = 1: Disables the FIQ. • T Bit – Architecture xT only – T = 0: Processor in ARM state – T = 1: Processor in Thumb state • Mode bits – Specify the processor mode • J bit – Architecture 5TEJ only – J = 1: Processor in Jazelle state
Operation Modes Mode Registers CPSR[4:0] User User 10000 FIQ _fiq 10001 IRQ _irq 10010 Supervisor Mode _svc 10011 Abort _abt 10111 Undefined Instruction _und 11011 System User 11111
Processor Modes
Processor Modes Processor modes are execution modes which determines active registers and privileges List of Modes  Abort  Fast Interrupt  Interrupt  Supervisor  System  Undefined  User All except user mode are privileged  User mode is for normal execution of programs and applications  Privileged modes allow full Read/Write to CPSR.
Processor Modes User Unprivileged mode for most applications to run FIQ Fast Interrupt Routine IRQ Interrupt Request Supervisor Entered on reset an when there is a exception Abort Entered when data or instruction prefetch aborted Undefined When an undefined instructions is executed System Privileged user mode for operating system
ARM Exceptions ARM supports range of Interrupts, Traps, Supervisor Calls, all grouped under General Exceptions
Exceptions Generated by internal and external events Support 7 types of exceptions  Reset - Only in Supervisor Mode  Software Interrupt – in Supervisor Mode  IRQ – on IRQ interrupt  FIQ – on FIQ interrupt  Data Abort – in Abort Mode  Undefined Instruction – in Undefined Mode  Prefetch Abort – in Abort Mode
Exception Priorities 1 Reset (Highest Priority) 2 Data Abort 3 FIQ 4 IRQ 5 Prefetch Abort 6 SWI,Undefined
ARM Processor • ARM7 Family – ARM7EJ-S – ARM7TDMI – ARM7TDMI-S – ARM720T • ARM9/9E Families – ARM920T – ARM922T – ARM926EJ-S – ARM940T – ARM946E-S – ARM966E-S – ARM968E-S • Vector Floating Point Families – VFP10 • ARM10 Family – ARM1020E – ARM1022E – ARM1026EJ-S • ARM11 Family - ARM1136J-S - ARM1136JF-S - ARM1156T2(F)-S - ARM1176JZ(F)-S - ARM11 MPCore • Cortex Family - Cortex-A8 - Cortex-M1 - Cortex-M3 - Cortex-R4 • Other Processors/ Microarchitectures - StrongARM (DEC-Intel) - Xscale (Intel- Marvell Tech) - Other
ARM Processor Families Naming Convention ARM[x][y][z][T][D][M][I][E][J][F][S]  X – Family  Y - Memory management /protection  Z – Cache  T - Thumb Mode  D – JTAG Debugging  M – Multiplier  I – Embedded ICE Macrocell  E – Enhanced Instruction (implies TDMI)  J – Jazelle hardware accelerated java  F – Floating point unit  S – Synthesizable Version
Instruction Set Architecture Architecture Thumb DSP Jazelle TrustZone Thumb2 v4T * v5TE * * v5TEJ * * * V6 * * * * v6Z * * * * * v6T2 * * * * *
Introduction to ARM7TDMI Version 4 Von Neumann Architecture  32 bit data bus  Data size can be byte , half word or word  Word : 4 bytes aligned  Half Word : 2 byte aligned Supports  Thumb : 16 bit compressed instruction set  Debug: On chip debug support  Enhanced Multiply : Higher performance ,Long multiply  Embedded ICE Hardware
Cortex Family ARM Cortex family comprises three series, which all implement the Thumb2 instruction set to address the increasing demands of various markets: 1 ARM Cortex – A Series: application processors for complex OS and user applications 2 ARM Cortex – R Series : embedded processors for real time systems 3 ARM Cortex – M Series : deeply embedded processors optimized for cost sensitive applications, as Mobile Devices.
Provide hardware support for two separate address spaces i.e. code executing in the non secure world cannot gain access to any address space marked as secure A new mode ‘Secure Monitor’ within the core acts as a gatekeeper and reliably switches the system between secure and no secure states Protection of on and off chip memory and peripherals from software attack Services such as network virus protection, m-commerce transactions and the protection of user secrets such as keys
Operating States Supports 2 Instruction Sets ARM – 32 bit instruction set Thumb – 16 bit instruction set
Thumb State Subset of the ARM instructions Higher code density (35% reduction) Better performance than 16 bit processors Suitable for use with 16 bit memory devices(160 % better performance) Transparently decompressed to 32 bit instructions
ARM State Able to access more large memories efficiently 32 bit integer arithmetic in a single cycle More number of instructions Better performance
Switching States ARM to Thumb Execute the BX instruction with state bit=1 Thumb to ARM Execute the BX instruction with state bit =0 An interrupt or exception cccurs
Which State to Use Low memory system : use thumb 16 bit memory : use thumb Performance is critical :use ARM Example : in execution of interrupt routines Performance is critical and Memory is low : use both ARM and thumb Example : In interrupt routines
ARM Debug Architecture ARM core ETM TAP controller Trace Port JTAG port Ethernet Debugger (+ optional trace tools)  EmbeddedICE Logic  Provides breakpoints and processor/system access  JTAG interface (ICE)  Converts debugger commands to JTAG signals  Embedded trace Macrocell (ETM)  Compresses real-time instruction and data access trace  Contains ICE features (trigger & filter logic)  Trace port analyzer (TPA)  Captures trace in a deep buffer EmbeddedICE Logic
Thanks…........

More Related Content

arm

  • 2. ARM Application Apple iPod Nano Ford Sync In-Car Comm & Entertainment System Sony Playstation 3 (60GB) Nokia N93
  • 5. Why ARM ??? ARM is one of the most licensed and thus widespread processor cores in the world. Used especially in portable devices due to low power consumption and reasonable performance Several interesting extension available like THUMB instruction set and Jazelle Java Machine
  • 6. Computer Architecture Describes Users View of the Computer Eg. Instruction Set Visible Registers Memory Management Table Structure Exception Handling Models etc.
  • 7. Computer Organization Describes User Invisible Implementation of the Architecture Eg. Pipeline Struture Transparent Cache Translation Look Aside Buffers etc
  • 8. RISC vs. CISC Architecture RISC CISC Fixed width Instructions Variable length instructions Few Formats of Instructions Several formats of instructions Load/Store Architecture Memory Values can be used as operands in instructions Large Register Banks Small Register Bank Instructions are pipelinable Pipelining is complex Single Cycle execution of all instructions Multi cycle execution on instructions
  • 9. RISC Advantages A small Die Size A Shorter Development Time Higher Performance Smaller things have higher natural frequencies.
  • 10. RISC Disadvantages Generally poor code density (Fixed Length Instruction)
  • 11. ARM History ARM – Acron RISC Machine(1983-1985) Acron Computers Limited ,Cambridge, England. ARM – Advanced RISC Machine 1990 ARM Limited ,1990 ARM has been licensed to many semiconductor manufacturers
  • 12. Architecture Revisions 1998 2000 2002 2004 time version ARMv5 ARMv6 1994 1996 2006 V4 StrongARM® ARM926EJ-S™ XScaleTM ARM102xE ARM1026EJ-S™ ARM9x6E ARM92xT ARM1136JF-S™ ARM7TDMI-S™ ARM720T™ XScale is a trademark of Intel Corporation ARMv7 SC100™ SC200 ™ ARM1176JZF-S™ ARM1156T2F-S™
  • 13. Features used from RISC A Load/Store Architecture Fixed Length 32 bit Instructions 3-Address Instruction Formats
  • 14. Load Store Architecture Memory can be accessed only through two dedicated instructions LDR ; Move word from memory to register STR ; Move word from register to memory All other instructions have to work on registers only
  • 15. 3 Address Instruction Format Function Dest. Addr. Op2 Addr. Op1 Addr. f bits n bits n bits n bits Example Add d, s1, s2 ; d =s1+s2
  • 16. Pipelining Break instructions into steps Work on instructions like in an assembly line Allows for more instructions to be executed in less time A n-stage pipeline is n times faster than a non pipeline processor (in theory)
  • 17. MISC/RISC Pipeline Stages Fetch instruction Decode instruction Execute instruction Access operand Write result  Note: Slight variations depending on processor
  • 18. Without Pipelining Normally, you would peform the fetch, decode, execute, operate, and write steps of an instruction and then move on to the next instruction
  • 19. Without Pipelining Instr 1 Instr 2 Clock Cycle 1 2 3 4 5 6 7 8 9 10
  • 20. With Pipelining The processor is able to perform each stage simultaneously. If the processor is decoding an instruction, it may also fetch another instruction at the same time.
  • 21. With Pipelining Clock Cycle 1 2 3 4 5 6 7 8 9 Instr 1 Instr 2 Instr 3 Instr 4 Instr 5
  • 22. Pipeline (cont.) Length of pipeline depends on the longest step Thus in RISC, all instructions were made to be the same length Each stage takes 1 clock cycle In theory, an instruction should be finished each clock cycle
  • 23. Pipeline changes for ARM9TDMI Instruction Fetch Shift + ALU Memory Access Reg Write Reg Read Reg Decode FETCH DECODE EXECUTE MEMORY WRITE ARM9TDMI ARM or Thumb Inst Decode Reg Select Reg Read Shift ALU Reg Writ e Thumb→ Α RM decompress ARM decode Instruction Fetch FETCH DECODE EXECUTE ARM7TDMI
  • 24. ARM10 vs. ARM11 Pipelines ARM11 Fetch 1 Fetch 2 Decode Issue Shift ALU Saturate Write back MAC 1 MAC 2 MAC 3 Address Data Cache 1 Data Cache 2 Shift + ALU Memory Access Reg Write FETCH DECODE EXECUTE MEMORY WRITE Reg Read Multiply Branch Prediction Instruction Fetch ISSUE ARM or Thumb Instruction Decode Multipl y Add ARM10
  • 25. ARM Design Policy ARM core uses RISC Architecture  Reduced Instruction Set  Load Store Architecture  Large No of General Purpose Registers.  Parallel execution with Pipelines But some differences from RISC  Enhanced instructions for  DSP instructions  THUMB State  Conditional Execution Instructions  32 bit Barrel Shifter
  • 26. Registers ARM has Load Store Architecture General Purpose Registers can hold data or address Total of 37 Registers each of 32 bit There are 17 or 18 active registers 16 data registers 2 status registers
  • 27. Registers Registers R0-R12 are General Purpose Registers R13 is used as Stack Pointer(SP) R14 is used as Link Register(LR) R15 is used as Program Counter(PC) CPSR is Current Program Status Register SPSR is Saved Program Status Register R0 R1 R2 R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R13 R14 R15
  • 28. CPSR N Z C V J U n d e f i n e d I F T M o d e hold information about the most recently performed ALU operation set the processor operating mode • Condition code flags – N = Negative result from ALU – Z = Zero result from ALU – C = ALU operation Carried out – V = ALU operation overflowed • Interrupt Disable bits. – I = 1: Disables the IRQ. – F = 1: Disables the FIQ. • T Bit – Architecture xT only – T = 0: Processor in ARM state – T = 1: Processor in Thumb state • Mode bits – Specify the processor mode • J bit – Architecture 5TEJ only – J = 1: Processor in Jazelle state
  • 29. Operation Modes Mode Registers CPSR[4:0] User User 10000 FIQ _fiq 10001 IRQ _irq 10010 Supervisor Mode _svc 10011 Abort _abt 10111 Undefined Instruction _und 11011 System User 11111
  • 31. Processor Modes Processor modes are execution modes which determines active registers and privileges List of Modes  Abort  Fast Interrupt  Interrupt  Supervisor  System  Undefined  User All except user mode are privileged  User mode is for normal execution of programs and applications  Privileged modes allow full Read/Write to CPSR.
  • 32. Processor Modes User Unprivileged mode for most applications to run FIQ Fast Interrupt Routine IRQ Interrupt Request Supervisor Entered on reset an when there is a exception Abort Entered when data or instruction prefetch aborted Undefined When an undefined instructions is executed System Privileged user mode for operating system
  • 33. ARM Exceptions ARM supports range of Interrupts, Traps, Supervisor Calls, all grouped under General Exceptions
  • 34. Exceptions Generated by internal and external events Support 7 types of exceptions  Reset - Only in Supervisor Mode  Software Interrupt – in Supervisor Mode  IRQ – on IRQ interrupt  FIQ – on FIQ interrupt  Data Abort – in Abort Mode  Undefined Instruction – in Undefined Mode  Prefetch Abort – in Abort Mode
  • 35. Exception Priorities 1 Reset (Highest Priority) 2 Data Abort 3 FIQ 4 IRQ 5 Prefetch Abort 6 SWI,Undefined
  • 36. ARM Processor • ARM7 Family – ARM7EJ-S – ARM7TDMI – ARM7TDMI-S – ARM720T • ARM9/9E Families – ARM920T – ARM922T – ARM926EJ-S – ARM940T – ARM946E-S – ARM966E-S – ARM968E-S • Vector Floating Point Families – VFP10 • ARM10 Family – ARM1020E – ARM1022E – ARM1026EJ-S • ARM11 Family - ARM1136J-S - ARM1136JF-S - ARM1156T2(F)-S - ARM1176JZ(F)-S - ARM11 MPCore • Cortex Family - Cortex-A8 - Cortex-M1 - Cortex-M3 - Cortex-R4 • Other Processors/ Microarchitectures - StrongARM (DEC-Intel) - Xscale (Intel- Marvell Tech) - Other
  • 37. ARM Processor Families Naming Convention ARM[x][y][z][T][D][M][I][E][J][F][S]  X – Family  Y - Memory management /protection  Z – Cache  T - Thumb Mode  D – JTAG Debugging  M – Multiplier  I – Embedded ICE Macrocell  E – Enhanced Instruction (implies TDMI)  J – Jazelle hardware accelerated java  F – Floating point unit  S – Synthesizable Version
  • 38. Instruction Set Architecture Architecture Thumb DSP Jazelle TrustZone Thumb2 v4T * v5TE * * v5TEJ * * * V6 * * * * v6Z * * * * * v6T2 * * * * *
  • 39. Introduction to ARM7TDMI Version 4 Von Neumann Architecture  32 bit data bus  Data size can be byte , half word or word  Word : 4 bytes aligned  Half Word : 2 byte aligned Supports  Thumb : 16 bit compressed instruction set  Debug: On chip debug support  Enhanced Multiply : Higher performance ,Long multiply  Embedded ICE Hardware
  • 40. Cortex Family ARM Cortex family comprises three series, which all implement the Thumb2 instruction set to address the increasing demands of various markets: 1 ARM Cortex – A Series: application processors for complex OS and user applications 2 ARM Cortex – R Series : embedded processors for real time systems 3 ARM Cortex – M Series : deeply embedded processors optimized for cost sensitive applications, as Mobile Devices.
  • 41. Provide hardware support for two separate address spaces i.e. code executing in the non secure world cannot gain access to any address space marked as secure A new mode ‘Secure Monitor’ within the core acts as a gatekeeper and reliably switches the system between secure and no secure states Protection of on and off chip memory and peripherals from software attack Services such as network virus protection, m-commerce transactions and the protection of user secrets such as keys
  • 42. Operating States Supports 2 Instruction Sets ARM – 32 bit instruction set Thumb – 16 bit instruction set
  • 43. Thumb State Subset of the ARM instructions Higher code density (35% reduction) Better performance than 16 bit processors Suitable for use with 16 bit memory devices(160 % better performance) Transparently decompressed to 32 bit instructions
  • 44. ARM State Able to access more large memories efficiently 32 bit integer arithmetic in a single cycle More number of instructions Better performance
  • 45. Switching States ARM to Thumb Execute the BX instruction with state bit=1 Thumb to ARM Execute the BX instruction with state bit =0 An interrupt or exception cccurs
  • 46. Which State to Use Low memory system : use thumb 16 bit memory : use thumb Performance is critical :use ARM Example : in execution of interrupt routines Performance is critical and Memory is low : use both ARM and thumb Example : In interrupt routines
  • 47. ARM Debug Architecture ARM core ETM TAP controller Trace Port JTAG port Ethernet Debugger (+ optional trace tools)  EmbeddedICE Logic  Provides breakpoints and processor/system access  JTAG interface (ICE)  Converts debugger commands to JTAG signals  Embedded trace Macrocell (ETM)  Compresses real-time instruction and data access trace  Contains ICE features (trigger & filter logic)  Trace port analyzer (TPA)  Captures trace in a deep buffer EmbeddedICE Logic