Chapter 12 Processor Structure and Function RICARFENS AUGUSTIN JARED COELLO OSVALDO QUINONES CPU Structure Processor main functions: Fetch instructions : The processor reads an instruction from memory (register, cache , or main memory). Interpret instructions : Instruction are decoded to determine what action is required. Fetch data : While an instruction is executed, data may need to be read from memory or an I/O module. Process data : An instruction may require to perform some arithmetic or logical operation with the data. Write data : Data resulting from the execution of an instruction may need to be stored in memory . CPU With Systems Bus CPU Internal Structure ALU does the actual computation or processing of data. Control Unit controls the movements of data and instructions into and out of the processor and control operation of the ALU. The internal processor bus is needed to transfer data between the various registers and the ALU; because the ALU in fact only operates on data in the internal processor memory. Register Organizations Computer systems employs a memory hierarchy. At higher level of the hierarchy memory is faster, smaller and more expensive per bit. Within the processor there is a set of registers that function as a level of memory above main memory and cache in the hierarchy. Registers in the processor perform two roles: User visible-registers: Enables the machine or assembly language programmers to minimize main memory references by optimizing use of registers. Control and Status registers: Used by the control unit to control the operation of the processor and by priviledge operating systems programs to control the execution of programs. User Visible Registers General Purpose Data Address Condition Codes General Purpose Registers Can be assigned to a variety of functions by the programmer May be true general purpose May be restricted to an specific function. May be used for data or addressing Data Accumulator Addressing Segment Pointers Data Registers The simplest type of registers are data registers, which are used for the temporary storage of data. In its simplest form, it consists of a set of D flip flops, all sharing a common clock. All of the digits in the N bit data word are connected to the data register by an N line ``data bus''. Data registers may be used only to hold data and can not be used for the calculation of an operand address. Address Registers May be themselves general-purpose registers, or may be devoted to a particular addressing mode. Example of address registers: Segment pointers: In machines with segmented addresses, it holds the address of the base of the segment. Index registers: They are used for indexed addressing and may be auto indexed. Stack pointers: It points to the top of the stack. This allow implicit addressing Condition Code Registers Is the least partially visible to the user. They are bit set by the processor hardware as a result of operations. CCR bits are collected into one or more registers. Sets of individual bits e.g. result of last operation was zero Can be read (implicitly) by programs e.g. Jump if zero Can not (usually) be set by programs Design issues (1) Use of completely general-purposed register vs specialized use. General purpose register increase flexibility and program options. In addition, it increase instruction size & complexity. Specialized registers are design to execute smaller instructions making then faster. However, there is less flexibility . 2. Number of register to be used must be between 8 and 32 registers. Fewer = more memory references. The use of more registers may not reduce significantly the # of memory references and takes up processor real estate. 3. Use of Reduction Instructions Set Computers (RISC). A new approach that fallows the do less for best performance idea (more registers) vs Complex Instructions set Computers (CISC), which have long and complex instructions to perform several actions (less registers). 1. Design issues Data registers should be: Large enough to hold full address. Large enough to hold full word. Flexible to combine two data registers C programming double int a; long int a; (2) Design Issues (CCR ) (2) Advantages Since conditions codes are set by normal arithmetic and data movements instructions, they should reduce the numbers of COMPARE and TEST needed. Conditional instructions such as BRANCH are simplified relative to composite instructions such as TEST and BRANCH Conditions codes facilitate multi-way branches. For example, a TEST instruction can be fallowed by two BRANCHES, one less than or equal to Zero and one greater than Zero Disadvantages Conditions codes add complexity , both to the hardware and software. Conditions code bits are often modified in different way by different instructions, making life more difficult for the microprogrammer and compiler writer. Conditions codes are irregular, they are typically not part of the main data path, so they require extra hardware connections. Often conditions codes machines must add special non-condition-codes instructions for special situations, such as bit checking, loop control , and atomic semaphore operation. In a pipeline implementation, condition codes required special synchronization to avoid conflicts. Control & Status Registers (1) There are a variety of processor registers that are employed to control the operation of the processor. Some of them may be visible to machine instructions executed in a control or operation system code Each machine will have different register organization and use different terminology. Control & Status Registers (2) Program Counter: Contains the address of an instruction to be fetched. Instruction Decoding Register: Contains the instruction most recently fetched. Memory Address Register: Contains the address of a memory location. Memory Buffer Register: Contains a word of data to be written to memory or the word most recently read. Program Status Word (1) Many processors designs include a register or a set of registers, often known as Program Status Word (PSW), that contains status information of operation executed by the Arithmetic Logic Unit Program Status Word (2) Some common field or flags include the following: Zero: Set when the result is 0. Sign: Contains the sign bit of the result of the last arithmetic operation. Carry: Set if an operation resulted in a carry or borrow. Used for multiword arithmetic operations. Equal: Set if a logical compare result is equality. Overflow: Used to indicate arithmetic overflow. Interrupt enable/disable: Used to enable or disable interrupts. Supervisor: Indicates whether the processor is executing in supervisor or user mode. Supervisor Mode Protection ring zero Also known as Kernel mode Allows privileged instructions to execute Used by operating system Not available to user programs Computer operating systems provide different levels of access to resources. A protection ring is one of two or more hierarchical levels or layers of privilege within the architecture of a computer systems. Example Register Organizations •Every register is special purpose. •32-bit processor registers • 4•MC68000 ,16-bit data32-bit registers addressable in a •Uses 32-bit registers •8 data registers 9 address registers. 16-bit basis. •Provide upwardand compatibility for 8-,16-,32-bit data operations •4,•Allow 16-bit segment registers. 3 dedicated programs written on earlier machines. to determined by theregister opcode. point to theoriginal segment of the current •Retains organization • 32-bit PC and a 16-bit SR instruction. embeddedpointer in the new organizations. •Instruction of 1-bit status and control flags Instruction Cycle In general has the following subcycles as we know it. Fetch: Read the next instruction from memory into the processor Execute: Interpret the opcode and perform the indicated operation Interrupt: If interrupts are enabled and an interrupt has occurred, save the current process state and service the interrupt Indirect Cycle Can be thought of as additional instruction subcycle May require memory access to fetch operands Indirect addressing requires more memory accesses Instruction Cycle with Indirect Instruction Cycle State Diagram Data Flow (Instruction Fetch) Depends on CPU design In general: Fetch PC contains address of next instruction Address moved to MAR Address placed on address bus Control unit requests memory read Result placed on data bus, copied to MBR, then to IR Meanwhile PC incremented by 1 Data Flow (Fetch Diagram) Data Flow (Data Fetch) After the Fetch cycle is completed IR is examined If indirect addressing, indirect cycle is performed Right most N bits of MBR transferred to MAR Control unit requests memory read Result (address of operand) moved to MBR Instruction Cycle with Indirect Data Flow (Indirect Diagram) Data Flow (Execute) May take many forms Depends on instruction being executed May include Memory read/write Input/Output Register transfers ALU operations Instruction Cycle with Indirect Data Flow (Interrupt) Current PC saved to allow resumption after interrupt Contents of PC copied to MBR Special memory location (e.g. stack pointer) loaded to MAR MBR written to memory PC loaded with address of interrupt handling routine Next instruction (first of interrupt handler) can be fetched Data Flow (Interrupt Diagram) Instruction Pipelining description • The Idea • • • • • Similar to an assembly line. New input is in before the last one ends. Each stage of pipeline does something the each instruction without affecting the other. Works using buffers in each instruction stage The CPU works on multiple instructions at the same time. Two Stage Instruction Pipeline Timing Diagram for six stage Instruction Pipeline Operation Instruction Process Decomposition Fetch instruction(FI) Decode instruction(DI) Calculate operands (CO) Fetch operands(FO) Execute instructions(EI) Write result(WR) Performance of multi-stage pipeline Introduces a level of parallelism in instruction execution. Increases efficiency of CPU Increases overall speed But not doubled Increase speed of 9 instruction from 54 time units to 14. Fetch usually shorter than execution Any jump or branch means that prefetched instructions are not the required instructions Speedup Factors with Instruction Pipelining Set backs….. Overhead of buffer to buffer transfers and preparation operations. Amount of logic require to handle additional stages and memory increases exponentionally Interrupts handling and Branch instructions. The Effect of a Conditional Branch on Instruction Pipeline Operation Branching/no branching comparison Dealing With Branches • Multiple Streams • Prefetch Branch Target • Loop buffer • Branch prediction • Delayed branching Multiple Streams Have two pipelines Prefetch each branch into a separate pipeline Use appropriate pipeline Leads to bus & register contention Multiple branches lead to further pipelines being needed Prefetch Branch Target Target of branch is prefetched in addition to instructions following branch Keep target until branch is executed Used by IBM 360/91 Loop Buffer • Very fast memory • Maintained by fetch stage of • • • • pipeline Check buffer before fetching from memory Very good for small loops or jumps c.f. cache Used by CRAY-1 Branch Prediction (1) Predict never taken Assume that jump will not happen Always fetch next instruction 68020 & VAX 11/780 VAX will not prefetch after branch if a page fault would result (O/S v CPU design) Predict always taken Assume that jump will happen Always fetch target instruction Branch Prediction State Diagram Branch Prediction (2) Predict by Opcode Some instructions are more likely to result in a jump than thers Can get up to 75% success Taken/Not taken switch Based on previous history Good for loops Branch Prediction (3) Delayed Branch Do not take jump until you have to Rearrange instructions Foreground Reading Processor examples Stallings Chapter 12 Manufacturer web sites & specs http://courses.cs.vt.edu/~csonline/MachineArchitec ture/Lessons/CPU/Lesson.html Review Questions What general roles are performed by CPU registers? User –visible registers and control and status registers. What categories of data are commonly supported by user-visible registers? Address, condition codes and general data. What is the function of condition codes? They are used in conditional branch operation to determine which branch to take. What is a program status word? Register or set of registers that contain condition codes and other status information. Why is a two- stage instruction pipeline unlikely to cut the instruction cycle time by half, compared with the use of no pipeline? Because execution cycle is longer so the fetch buffer will have to wait until the next cycle to be empty again. List and briefly explain various ways in which an instruction pipeline can deal with conditional branch instructions? Multiple streams, pre-fetch branch target, loop buffer, branch prediction, delayed branch. How are history bites used for branch prediction? History bytes are used to record the history information about a branch instruction, such as its address and what was the result of the last time it was taken. This information is used to predict the possibility of this branch being taken again.