Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 1 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Part 7 Instruction.

Präsentation zum Thema: "Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 1 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Part 7 Instruction."—  Präsentation transkript:

1 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 1 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Part 7 Instruction Set Architecture (ISA) Computer Architecture Slide Sets WS 2011/2012 Prof. Dr. Uwe Brinkschulte Prof. Dr. Klaus Waldschmidt

2 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 2 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Programming model The Instruction Set Architecture (ISA) is the programming model which is needed for programming a processor. All details concerning the implementation of the processor are out of focus in the ISA. Therefore the ISA can be regarded as an abstract interface between the compiler and the microarchitecture of the processor.

3 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 3 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Programming model The following key questions lead us to the specification of this interface: How data is represented? Where data is stored? How data is accessed? How instructions are coded? Which instructions are available to process data?

4 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 4 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Programming model Therefore, the ISA defines: machine data types address space organisation register model addressing modes machine instruction set

5 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 5 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Programming model Since the programming model abstracts from implementation details it is realized either in hardware (real processors) or in software (virtual processors). For instance, if the instruction set includes an instruction for multiplication, the CPU of the processor needs a digital combinatorial circuit for multiplication. In this sense, a relation between the abstract ISA and the microarchitecture exists.

6 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 6 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Machine data types A data type is a tuple of values and operations which can be performed on these values. The operations are implemented by the machine instructions. Machine data types (like data types in high level languages) are classified into structured and unstructured data types. An additional class are the primitive data types.

7 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 7 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Primitive machine data types Bit:value set: 0,1 operations: AND, OR, XOR, negation, compare Byte: value set: bit pattern (8 bit) normally smallest addressable unit operations: same as for bit, additionally ADD, SUB, MUL, DIV, SHIFT, ROTATE, … Word: value set: normally a multiple of bytes largest addressable unit (in a single operation) operations: same as for byte (sometimes the following convention is used: Half-Word = 16 Bit Word = 32 Bit Double Word = 64 Bit)

8 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 8 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Examples for more data types 1 - vector (bit) - BCD number (binary coded decimal) - Binary number unsigned - two complement number - floating point number - string n-1 i 0 n = 8,16,32 03210 76543210 8, 16 Bit 32 Bit 31 0 7 0 15 0 n-1 0 n = 8, 16, 32 MSB LSB n-1 0 MSB=sign bit LSB n = 8, 16, 32 biased.expon.sfraction... n = 8, 16, 32 n-1 0 n-1 0 n-1 0 31 23 22 0 (taken from MC680x0)

9 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 9 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Address space organisation Physical organisation: depends on the processor... 7 0 0n0n 8 bit processor... 15 8 7 0 0n0n 16 bit processor... 31 24 23 16 15 8 7 0 0n0n 32 bit processor... n: physical address, n = 2 address bus width

10 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 10 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Address space organisation Locical organisation: byte oriented access for most processor types... 7 0 0123m0123m physical word on a 8 bit processor physical word on a 16 bit processor physical word on a 32 bit processor m: logical address, m = n * bit width / 8

11 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 11 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Address space organisation Physical to logical mapping:... 31 24 23 16 15 8 7 0 0n0n... 0123 45 67 89 10 11 1213 14 15 m-3m-2 m-1 m physical address locical address

12 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 12 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Address space organisation Aligned access: the accessed word is aligned according to its length in the physical address space (logical adress mod length) = 0... 31 24 23 16 15 8 7 0 0n0n... byte bytes to byte boundaries half-word half-words to half-word boundaries word words to word boundaries

13 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 13 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Address space organisation... 31 24 23 16 15 8 7 0 0n0n... half-word -word word Unaligned (misaligned) access: the accessed word is not aligned according to its length in the physical address space (logical adress mod length) 0 half- Some processors do not support unaligned access (e.g. SPARC)

14 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 14 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Byte order in words 8 Bit - byte 16 Bit - word 32 Bit - word 8 Bit - byte 16 Bit - word 32 Bit - word N + 1NN + 2N + 3 N + 1N N NN + 2N + 3 N + 1N N big endian byte ordering little endian byte ordering 31 2423 1615 87 0 31 2423 1615 87 0 Two different formats: N: least significant byte, N + 3: most significant byte Word address is the address of the most significant byte (used e.g. in MC680x0 or SPARC) Word address is the address of the least significant byte (used e.g. in Pentium family)

15 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 15 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Byte order in words N + 1 N N + 2 N + 3 big endian byte ordering Locical (byte oriented) memory organization of a 32 bit word b b+1 b+2 b+3 byte address N + 2 N + 3 N + 1 N little endian byte ordering b b+1 b+2 b+3 byte address

16 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 16 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Register model The number of registers being part of a processor varies between 20 and 200. The advantage of data storage in registers against DRAM or SRAM-memories are: faster access time register addresses could be shorter with respect to the instruction format. An ISA is called Load-Store-ISA if all machine instructions except register load and store instructions operate on the register file only.

17 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 17 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Registers are classified into hidden registers and programmer visible registers. The visible registers are the workplace of the programmer and are often organized as register files. Hidden registers are supply registers needed for the internal functionality of the processing unit (CPU). Both visible and hidden registers are designed for various purpose and functionality. Register model

18 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 18 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt A register model defines which processor registers are visible (addressable) to the programmer. Usually these are the working registers and the state register. The state register monitors the state of the processor through conditional flags. It shows for example whether the processor operates in system or user mode. The state register is mostly read-only Commonly existing hidden registers are the instruction register and the memory interface registers. Register model

19 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 19 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Register implementation clk Q0Q0 D Q D0D0 Q1Q1 D1D1 Q 31 D Q D 31........ 32 bit register with D-Latches Asynchronous counter with D-Latches D Q Q clk D Q Q D Q Q D Q Q Q0Q0 Q2Q2 Q1Q1 Q3Q3.... clk D 31 Q 31 D1D1 D0D0 Q0Q0 Q1Q1 Symbol

20 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 20 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt program counter (PC) - contains the next instruction address state register (SR) - monitors the state of the processor stackpointer (SP) - stores the top of the stack accumulator (ACCU) – stores computation results (in older or simple processors) data registers (DXi) - storing operands for computations address registers (AXi) - storing operand addresses general purpose registers (GPi) - storing either operands or operand addresses Common visible registers

21 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 21 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt instruction register (IR) – contains the currently processed instruction instruction queue (IQ) - contains the next instructions to be processed memory address register (MAR) - buffers the address of a memory access (e.g. to save or load a general purpose register) memory data register (MDR) - buffers the content of a memory access (e.g. to save or load a general purpose register) Common hidden registers

22 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 22 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Program counter register Pointer to the next instruction to be executed Normally incremented Set by a jump, jump subroutine, interrupt, return or return from interrupt instruction Program counter PC N - 4 N N + 4 M … … 31 0 Add A B Jump M …

23 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 23 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Stackpointer register Addresses a location in the memory which is organized as a stack (LIFO). Elements can be pushed (write) and popped (read) only from the top of the stack. Consequence: Data are stored in a subsequent order Used e.g. for jump subroutine/return operation on PC Stackpointer N - 4 N N + 4 … … 31 0 PushX Pop Some processors distinguish between user stackpointer (e.g. for jump subroutine/return) and supervisor stackpointer (e.g. for interrupt/return from interrupt)

24 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 24 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Sampe CISC register set Intel Pentium

25 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 25 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Sampe RISC register set Power PC (extract) The register file of RISC processors has to be much bigger compared to CISC processors. A RISC needs more registers, because the register file is source and destination of all arithmetic or logic instructions.

26 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 26 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Multiple register sets

27 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 27 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Processors with multiple register sets: a step towards multithreaded processors Processor with multiple register sets: Each register set can store the program counter (PC) and the state register (SR) PC and SR exist only once => several contexts can be stored, fast context switching Multithreaded processor: multiple PCs and SRs exist instructions from several threads can be executed at the same time in the pipeline => several contexts can be processed Multiple register sets

28 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 28 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt The registers of a register file are grouped into blocks called windows. These overlapping windows are used by the subroutines of a program. MORS (multiple overlapping register set) Multiple overlapping register sets, register windows Overall register set Register window 1 Register window 2 Register window 3 Register window n jump subroutine return

29 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 29 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Simplifies parameter passing on jumping to subroutines Each subroutine has its own working space within the register file Parameters can be directly passed with no need to copy registers or pass parameters by memory => mainly used in RISC processors Two possible approaches: Fixed size register window Variable size register window Multiple overlapping register sets, register windows

30 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 30 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt preceding window continued global registers r7 r0 current window succeeding window CWP restore save alternative register naming: r31 = i7 r24 = i0 r23 = I7 r16 = I0 r15 = o7 r8 = o0 r7 = g7 r0 = g0 based on SPARC architecture r31 r24 r23 r16 r15 r8 r31 r8 In i+1 Local i+1 Out i+1 In i Local i Out i Out i-1 Local i-1 In i-1 Fixed size window local register

31 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 31 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt In case of the SPARC architecture, a window consists of 32 registers of which the first 8 also belong to the preceding window and the last 8 also belong to the succeeding window. The registers are addressed relative to the current window pointer (CWP). A subroutine call is performed by incrementing the CWP and saving the PC. The parameters are passed through the overlapping registers of the two windows. The content of the program counter is saved (return address) into one of these registers. A time consuming save and reload of registers is omitted. In case of an overflow of the MORS the window contents have to be saved to a stack. Fixed size window

32 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 32 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt In Local Out Local Out preceding current window global registers local registers 0 63 127 0 previous RSP current RSP r0 r1 r0 r1 Variable size window gr0 gr1 gr63 register stack pointer (RSP) r0 r1 r127 r65 r66 r64 based on AMD 29000 architecture

33 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 33 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Register size of processors with 3-address architecture processor/architecture (vendor) # of general purpose registersbit width overall directly accessible register width register address immediate operands instr. Alpha 21364 (Compaq)32 64 Bit5 Bit8 Bit32 Bit Am29000 (AMD)192 32 Bit8 Bit 32 Bit ARM7TDMI (ARM)16 32 Bit4 Bit8 Bit32 Bit Crusoe TM5800 (Transmeta)64 32 Bit6 Bit-- pa-8700 (HP)32 64 Bit5 Bit11 Bit32 Bit Itanium 2 (Intel, HP)128 64 Bit7 Bit8 Bit41 Bit MC88100 (Motorola)32 32 Bit5 Bit16 Bit32 Bit MIPS65 20Kc (MIPS)32 64 Bit5 Bit16 Bit32 Bit Nemesis C (TU Berlin)961632 Bit4 Bit1 Bit16 Bit PowerPC 970 (IBM)32 64 Bit5 Bit16 Bit32 Bit UltraSPARC III Cu (SUN)1603264 Bit5 Bit13 Bit32 Bit

34 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 34 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Register size of processors with 2-address architecture processor (vendor) # of general purpose registersbit width overall directly accessible register width register address immediate operands smallest instr. Athlon (AMD X86-64)16 64 Bit4 Bit8 - 32 Bit8 Bit ColdFire MFC5206 (Motorola)8 + 8 32 Bit3 Bit8 - 32 Bit16 Bit MC680xx (Motorola)8 + 8 32 Bit3 Bit8 - 32 Bit16 Bit Pentium X (Intel X86)8832 Bit3 Bit8 - 32 Bit8 Bit

35 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 35 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Addressing modes Machine instructions normally hold information about the operand addresses. This can either be a physical address, e.g. a register number or the address of a memory location, or it can be an address specification. An address specification defines how to calculate the address. Thus, the address information determines the location of the operand(s) belonging to the instruction using one of many addressing modes.

36 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 36 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Addressing modes Instruction format e.g. arithmetic instruction opcode target source source operands needed for the execution defined by the opcode operand register memory address specification itself number location (dynamic address calculation) The result of the dynamic address calculation is called effective address

37 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 37 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt immediate: The operand is part of the instruction. memory direct and register direct: The instruction contains the operand address. register indirect: The instruction contains a register number pointing to a register holding the address of the operand. In assembler code this addressing mode is typically denoted by register name Addressing modes

38 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 38 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt memory indirect: A register addressed in the instruction contains the address of a memory cell which holds the operand address. register offset: The instruction contains a register number and an offset. The operand address is the sum of the registers content and the offset. implicit: The instruction implicitly targets a single register (like the ACCU) Addressing modes

39 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 39 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Reasons for using dynamic address calculation: Addresses of data structure elements are composed of the first address of the data structure and the offset of the element to the beginning. Often this offset is unknown at compile time, therefore the effective address has to be calculated at runtime. Repeated execution of the same instruction, e.g. in a loop, often accesses successive memory addresses which have to be calculated at runtime. Effective address The address is calculated from several parts found in the instruction and in registers or memory cells at runtime (dynamic address calculation). The calculated address is defined as effective address.

40 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 40 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt An operand address often is unknown at compile time, because it is calculated during program execution. The partitioning of addresses into a base address stored in a register and an offset simplifies the handling of shift able variables and shift able program code. Effective address (cont.)

41 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 41 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt o p e r a n d immediate instruction register memory operand eff. address register direct memory direct Addressing modes 1 e.g. LOAD 8, r1 e.g. LOAD (2000), r1 e.g. LOAD r2, r1

42 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 42 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt o p e r a n d register indirect instruction register instruction register address e f f e c t i v e a d d r e s s register address memory m e m o r y a d d r e s s decrement memory - eff. address register register indirect with predecrement Addressing modes 2 e.g. LOAD (r2), r1 e.g. LOAD -(r2), r1

43 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 43 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt register indirect with displacement (indexed) o p e r a n d instruction register address m e m o r y a d d r e s s memory + + i n d e x register displacement scaling 1, 2 or 4 eff. address Addressing modes 3 e.g. LOAD.B 126(r3)(r2), r1

44 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 44 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt memory indirect o p e r a n d instruction register address m e m o r y a d d r e s s memory + + displacement1 indirect memory address displacement2eff. address memory Addressing modes 4 e.g. LOAD 28(126(r2)), r1

45 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 45 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt memory indirect (post indexed) o p e r a n d instruction register address m e m o r y a d d r e s s memory + + displacement1 indirect memory address displacement2 eff. address memory i n d e x scaling 1, 2 or 4 + register Addressing modes 5 e.g. LOAD.B 28(r3)(126(r2)), r1

46 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 46 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt memory indirect (preindexed) o p e r a n d instruction register address m e m o r y a d d r e s s memory + + displacement1 indirect memory address displacement2 eff. address memory i n d e x scaling 1, 2 or 4 + register Addressing modes 6 e.g. LOAD.B 28(126(r3)(r2)), r1

47 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 47 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt branch target table access through program counter relative addressing JMP disp (PC)(r n ) memory target 0 target 2 target 1 i n d e x (PC) + + displacement Access to branch target table by PC relative addressing

48 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 48 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Machine instruction set The machine instruction set of a computer normally includes instructions of different formats, e.g. 0-address instructions, 1-address instructions, 2-address instructions and 3-address instructions. An instruction is divided into so called fields. The more address fields an instruction contains the smaller the number of addressable memory cells and/or the number of operations encoded in the opcode field becomes (if we assume a constant instruction length).

49 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 49 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Variable length vs. constant length instruction format Variable length: (e.g. 16 - 256 Bit) mostly used in CISC architectures + flexible instruction format + high code density + long immediate and displacement values Constant length: (e.g. 32 Bit) mostly used in RISC architectures + simple and fast fetch + simple and fast decode + simplified pipelining

50 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 50 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Scheme of basic operations of common processors basic operations unconditional operations conditional operations combinatorial operations control flow operations transport operations arithmetic logic operations simple branches system branches load operations store operations semaphore operations arithmetic operations logic and shift operations state and control operations subroutine branches call return

51 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 51 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Instruction sets are divided into groups combining instructions with similar functionality: Typical instruction groups: transport instructions arithmetic instructions logic instructions shift and rotate instructions bitwise instructions string and array instructions branch instructions system instructions synchronization instructions Instruction classes

52 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 52 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Load store architecture All instructions - except load and store instructions - address registers only. Load and store instructions are needed to transfer data to and from main memory. Mainly used in RISC ISA, combined with pipelining it allows to complete most instructions in one cycle Furthermore, the address fields of instructions becomes shorter as they only have to address a register instead of a memory address. A load store ISA accelerates a machine if there are only small caches or if the caches are completely missing and a big register file is available.

53 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 53 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Example: An arithmetic instruction SUBc r3, r7, r21 binary code 11010 10101 00111 00011 1 0000000000 hexcode D54E3800 31 26 2116 11 0 instruction format: OP: opcode TR: target register SRn: source register c/x: set/do not set condition code Example: A store instruction STORE r24, 126(r5) binary code 00111 11000 00101 00000000001111110 hexcode 3E0A007E 31 26 21 16 0 instruction format: OP: opcode SR: source register BR: base register DP: displacement (signed) Two examples for an instruction format OPTRSR1SR2OPSRBR cxcx DP

54 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 54 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt State register of a RISC processor (based on SPARC-architecture) N Z V C 31 16 15 0 IM IEIE PSPS S CWP SR interrupt mask interrupt enable previous S-bit supervisor/user current window pointer carry overflow zero negative conditional bits

55 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 55 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Conditional codes dependent on conditional bits Z (zero), N (negative), C (carry) und V (overflow). Mnemonics according to Motorolas ColdFire MFC5206 processor. conditional value mnemonicoperationexpressionoperand type equal not equal eq ne = Z independent higher than higher than or same lower than lower than or same ht hs lo ls > < C Z C C Z unsigned greater than greater than or equal less than less than or equal gt ge lt le > < (N = V) Z (N = V) (N V) (N V) Z signed arithmetic overflow arithmetic shortfall negative positive vs vc ne pl V N signed

56 Hier wird Wissen Wirklichkeit Computer Architecture – Part 7 – page 56 of 56 – Prof. Dr. Uwe Brinkschulte, Prof. Dr. Klaus Waldschmidt Multimedia instructions Typical SIMD instructions to process a single operation on a set of data (e.g. changing the brightness of image pixels) Operations can be on packed integers (e.g. MMX on Pentium) or packed floats (e.g. SSE2 on Pentium) Typical operations: arithmetic (saturated or overflow), logic, compare, pack, unpack Example: