cs 211: computer architecture lecture 2 instructor: morris lancaster
TRANSCRIPT
5/7/2010 CS 211 Lecture 2 3
?Design a New High Performance System?
• ISA– What instructions should we include
• Internal Organization– How do the instructions implemented affect the
internal organization (and subsequently performance)
• How best approach this problem?– Understand what a computer and an instruction set
architecture does for us
– Look at current architectures for insight
5/7/2010 CS 211 Lecture 2 4
Classifying ISA’s
• Type of Internal Storage– Stack
– Accumulator
– Set of Registers
5/7/2010 CS 211 Lecture 2 6
Design Decisions
• Instruction Set Architecture Class (Load-Store?)– How Many Registers (more is good)
• How Many Operands in the instruction?
5/7/2010 CS 211 Lecture 2 7
Code Sequences for the 4 Classes
• Since 1980s almost all new designs are load store architectures.– Machines have large register files
– Registers are easier for the compiler to manage (addressed in only one way)
Stack Accumulator Register
(register-memory)
Register
(load store)
Push A Load A Load R1, A Load R1, A
Push B Add B Add R3, R1, B Load R2, B
Add Store C Store R3, C Add R3, R1, R2
Pop C Store R3,C
5/7/2010 CS 211 Lecture 2 8
Number of Memory Addresses
Number of memory
addresses
Maximum number of operands
allowed
Type of Architecture Examples
0 3 Load-Store Alpha, ARM, MIPS, PowerPC, SPARC, SuperH, TM32
1 2 Register-Memory IBM 360/370, Intel 80x86, Motorola 68000, TI TMS320C54x
2 2 Memory – memory VAX (also has 3 operand formats)
3 3 Memory - memory VAX (also has 2 operand formats)
5/7/2010 CS 211 Lecture 2 9
Tradeoffs for the ISA Classes
Type Advantages Disadvantages
Register-register
(0,3)
Simple, fixed length instruction encoding. Simple code generation model. Instructions take similar numbers of clocks to execute.
Higher instruction count than architectures with memory references in the instructions. More instructions and lower instruction density leads to larger programs
Register-memory
(1,2)
Data can be accessed without a separate load instruction first. Instruction format tends to be easy to encode and yields good density
Operands are not equivalent since a source operand is destroyed. Encoding a register number and a memory address in each instruction may restrict the number of registers. Clocks per instruction vary by operand location
Memory-memory
(2,2) or (3,3)
Most compact. Does not waste registers for temporaries.
Large variation in instruction size, especially for three-operand instructions. In addition, large variation in work per instruction. Memory accesses create memory bottleneck. (Not used today)
5/7/2010 CS 211 Lecture 2 10
Memory Addressing(page B9)
• Register Add R4,R3 R4<- R4 + R3• Immediate Add R4,#3 R4<- R4 + 3• Displacement Add R4,100(R1) R4<- R4 + Mem[100+R1]• Register Indirect Add R4,(R1) R4<- R4 + Mem[R1]• Indexed Add R3,(R1+R2) R3<- R3 + Mem[R1+R2]• Direct Add R1, (1001) R1<- R1 + Mem[1001]• Memory Indirect Add R1, @(R3) R1<- R1 +
Mem[Mem[R3]]• AutoIncrement Add R1, (R2)+ R1<- R1 + Mem[R2]
R2<- R2 +d• AutoDecrement Add R1, -(R2) R2<- R2 - d
R1<- R1 + Mem[R2]• Scaled Add R1, 100(R2)[R3] R1<- (R1) +
Mem[100+(R2) + (R3)*d]
5/7/2010 CS 211 Lecture 2 15
Type and Size of Operands
• 8, 16, 32, 64 bits• Alignment• Fetch capability• Encoding type
5/7/2010 CS 211 Lecture 2 17
Control Flow
• Addressing modes• Conditional branch operations• Frequency distributions
5/7/2010 CS 211 Lecture 2 23
Instruction Encoding
• Balance– Desire to have as many registers and addressing modes
as possible
– The impact of the size of the register and addressing mode fields on the average instruction size and hence average program size
– A desire to have instructions encoded into lengths that will be easy to handle in a pipelined implementation
5/7/2010 CS 211 Lecture 2 24
The Role of Compilers
• Structure• Optimizations• Register Allocation (tied with hardware)• Impact of Compiler Technology on Architects
Decisions
5/7/2010 CS 211 Lecture 2 26
Fig 2.26 Change in Instruction Count From Compiler Optimization (SPEC2000)
5/7/2010 CS 211 Lecture 2 27
MIPS Instruction Set
• MIPS 64 has 32 general purpose registers of 64 bits in length (R0…R31)– Value of R0 is always 0
• 32 floating point registers capable of holding 32 or 64 bit floating point numbers
• Instruction formats– I type immediate
– R type register-register
– J type jump
5/7/2010 CS 211 Lecture 2 28
MIPS Instruction Set
• Instruction nomenclature– Opcode
– Registers rs, rd, rt
5/7/2010 CS 211 Lecture 2 30
Fallacies and Pitfalls
• Pitfall – Designing a “high-level” instruction set feature specifically oriented to supporting a high-level language structure.
• Fallacy – There is such a thing as a typical program
• Pitfall – Innovating at the instruction set architecture to reduce code size without accounting for the compiler.
• Fallacy – An architecture with flaws cannot be successful
• Fallacy – You can design a flawless machine