Download to read offline
![Instruction Set
Architecture
â... the attributes of a [computing] system as seen by
the programmer, i.e. the conceptual structure and
functional behavior, as distinct from the organization
of the data flows and controls the logic design, and
the physical implementation.â
â Amdahl, Blaauw, and Brooks, 1964
SOFTWARE
SOFTWARE
-- Organization of Programmable
Storage
-- Data Types & Data Structures:
Encodings & Representations
-- Instruction Formats
-- Instruction (or Operation Code) Set
-- Modes of Addressing and Accessing Data Items and Instructions
-- Exceptional Conditions](https://image.slidesharecdn.com/lecture1-250813050437-df8450a4/85/basics-of-computer-architecture-and-introduction-ppt-9-320.jpg)
![Instruction Set
Architecture
â... the attributes of a [computing] system as seen by
the programmer, i.e. the conceptual structure and
functional behavior, as distinct from the organization
of the data flows and controls the logic design, and
the physical implementation.â
â Amdahl, Blaauw, and Brooks, 1964
SOFTWARE
SOFTWARE
-- Organization of Programmable
Storage
-- Data Types & Data Structures:
Encodings & Representations
-- Instruction Formats
-- Instruction (or Operation Code) Set
-- Modes of Addressing and Accessing Data Items and Instructions
-- Exceptional Conditions](https://image.slidesharecdn.com/lecture1-250813050437-df8450a4/75/basics-of-computer-architecture-and-introduction-ppt-9-2048.jpg)
basics of computer architecture and introduction.ppt
- 1. CS 5513: ComputerArchitecture Lecture 1: Introduction Daniel A. JimĂŠnez The University of Texas at San Antonio http://www.cs.utsa.edu/~dj http://www.cs.utsa.edu/~dj/cs5513
- 2. Outline ⢠Computer Scienceat a Crossroads ⢠Computer Architecture v. Instruction Set Arch. ⢠What Computer Architecture brings to table
- 3. ⢠Old ConventionalWisdom: Power is free, Transistors expensive ⢠New Conventional Wisdom: âPower wallâ Power expensive, Xtors free (Can put more on chip than can afford to turn on) ⢠Old CW: Sufficiently increasing Instruction Level Parallelism via compilers, innovation (Out-of-order, speculation, VLIW, âŚ) ⢠New CW: âILP wallâ law of diminishing returns on more HW for ILP ⢠Old CW: Multiplies are slow, Memory access is fast ⢠New CW: âMemory wallâ Memory slow, multiplies fast (200 clock cycles to DRAM memory, 4 clocks for multiply) ⢠Old CW: Uniprocessor performance 2X / 1.5 yrs ⢠New CW: Power Wall + ILP Wall + Memory Wall = Brick Wall â Uniprocessor performance now 2X / 5(?) yrs ď Sea change in chip design: multiple âcoresâ (2X processors per chip / ~ 2 years) Âť More simpler processors are more power efficient Crossroads: Conventional Wisdom in Comp. Arch
- 4. 1 10 100 1000 10000 1978 1980 19821984 1986 1988 1990 1992 1994 1996 1998 2000 2002 2004 2006 Performance (vs. VAX-11/780) 25%/year 52%/year ??%/year Crossroads: Uniprocessor Performance ⢠VAX : 25%/year 1978 to 1986 ⢠RISC + x86: 52%/year 1986 to 2002 ⢠RISC + x86: 18%/year 2002 to 2008 From Hennessy and Patterson, Computer Architecture: A Quantitative Approach, 4th edition, October, 2006
- 5. Sea Change inChip Design ⢠Intel 4004 (1971): 4-bit processor, 2312 transistors, 0.4 MHz, 10 micron PMOS, 11 mm2 chip ⢠Processor is the new transistor? ⢠RISC II (1983): 32-bit, 5 stage pipeline, 40,760 transistors, 3 MHz, 3 micron NMOS, 60 mm2 chip ⢠125 mm2 chip, 0.065 micron CMOS = 2312 RISC II+FPU+Icache+Dcache â RISC II shrinks to ~ 0.02 mm2 at 65 nm â Caches via DRAM or 1 transistor SRAM?
- 6. Problems with SeaChange ⢠Algorithms, Programming Languages, Compilers, Operating Systems, Architectures, Libraries, ⌠not ready to supply Thread Level Parallelism or Data Level Parallelism for 1000 CPUs / chip, ⢠Architectures not ready for 1000 CPUs / chip ⢠Unlike Instruction Level Parallelism, cannot be solved by just by computer architects and compiler writers alone, but also cannot be solved without participation of computer architects
- 7. Instruction Set Architecture:Critical Interface instruction set software hardware ⢠Properties of a good abstraction â Lasts through many generations (portability) â Used in many different ways (generality) â Provides convenient functionality to higher levels â Permits an efficient implementation at lower levels
- 8. Example: MIPS 0 r0 r1 ° ° ° r31 PC lo hi Programmable storage 2^32 xbytes 31 x 32-bit GPRs (R0=0) 32 x 32-bit FP regs (paired DP) HI, LO, PC Data types ? Format ? Addressing Modes? Arithmetic logical Add, AddU, Sub, SubU, And, Or, Xor, Nor, SLT, SLTU, AddI, AddIU, SLTI, SLTIU, AndI, OrI, XorI, LUI SLL, SRL, SRA, SLLV, SRLV, SRAV Memory Access LB, LBU, LH, LHU, LW, LWL,LWR SB, SH, SW, SWL, SWR Control J, JAL, JR, JALR BEq, BNE, BLEZ,BGTZ,BLTZ,BGEZ,BLTZAL,BGEZAL 32-bit instructions on word boundary
- 9. Instruction Set Architecture â... theattributes of a [computing] system as seen by the programmer, i.e. the conceptual structure and functional behavior, as distinct from the organization of the data flows and controls the logic design, and the physical implementation.â â Amdahl, Blaauw, and Brooks, 1964 SOFTWARE SOFTWARE -- Organization of Programmable Storage -- Data Types & Data Structures: Encodings & Representations -- Instruction Formats -- Instruction (or Operation Code) Set -- Modes of Addressing and Accessing Data Items and Instructions -- Exceptional Conditions
- 10. ISA vs. ComputerArchitecture ⢠Old definition of computer architecture = instruction set design â Other aspects of computer design called implementation â Insinuates implementation is uninteresting or less challenging ⢠Our view is computer architecture >> ISA ⢠Architectâs job much more than instruction set design; technical hurdles today more challenging than those in instruction set design ⢠Since instruction set design not where action is, some conclude computer architecture (using old definition) is not where action is â We disagree on conclusion â Agree that ISA not where action is
- 11. Comp. Arch. isan Integrated Approach ⢠What really matters is the functioning of the complete system â hardware, runtime system, compiler, operating system, and application ⢠Computer architecture is not just about transistors, individual instructions, or particular implementations â E.g., Original RISC projects replaced complex instructions with a compiler + simple instructions
- 12. Computer Architecture is Designand Analysis Design Analysis Architecture is an iterative process: ⢠Searching the space of possible designs ⢠At all levels of computer systems Creativity Good Ideas Good Ideas Mediocre Ideas Bad Ideas Cost / Performance Analysis
- 13. CS 5513 Administrivia Instructor:Prof. Daniel A. JimĂŠnez Office: SB 4.01.58 Office Hours: By appointment T. A: Xinran Yu Office: Office Hours in Main Lab Office Hours: Monday, 3:00pm to 4:30pm Class: Tuesday/Thursday 5:30pm to 6:45pm, HSS 3.04.28 Text: Hennessy and Patterson, Computer Architecture: A Quantitative Approach, 4th Edition Web page: http://www.cs.utsa.edu/~dj/cs5513 See web page for reading and homework assignments
- 14. CS 5513 CourseFocus Understanding the design techniques, machine structures, technology factors, evaluation methods that will determine the form of computers in 21st Century Technology Programming Languages Operating Systems History Applications Interface Design (ISA) Measurement & Evaluation Parallelism Computer Architecture: ⢠Organization ⢠Hardware/Software Boundary Compilers
- 15. Research Paper Reading â˘As graduate students, you are now researchers ⢠Most information of importance to you will be in research papers ⢠Ability to rapidly scan and understand research papers is key to your success ⢠So: you will read a few papers in this course â The structure of this reading is to be decided ⢠Papers will be on web page
- 16. Related Courses Prerequisites forCS 5513 CS 3733 â Operating Systems (requires CS 3843) CS 4753/CS 3853 â Computer Architecture both of these prerequire: CS 3843 â Computer Organization CS 3823 â Programming Languages knowledge of C/C++/Java and assembly language Classes with CS 5513 as a prerequisite CS 6513 â Advanced Architecture CS 6553 â Performance Evaluation CS 6643 â Parallel Processing CS 6653 â Parallel Algorithms
- 17. Coping with CS5513 ⢠Students without proper prerequisites will have a difficult time in this class. It is often difficult for the graduate studies committee to determine whether a class from another university is equivalent to one of our prerequisites. ⢠We will have an âentrance quizâ to help you determine whether you would like to enroll in a different class. ⢠Will spend a few lectures reviewing material that is also covered in an undergrad computer architecture class.
- 18. Grading ⢠15% Homeworks â˘25% Midterm Exam(s) ⢠25% Second Exam ⢠25% Project â Transition from undergrad to grad student â We want you to succeed, but you need to show initiative â pick topic (more on this later) â meet with faculty to gauge progress â written report like conference paper â work in groups â Opportunity to do âresearch in the smallâ to help make transition from good student to research colleague ⢠10% Class Participation â Contribute to the class discussion
- 19. Outline ⢠Computer Scienceat a Crossroads ⢠Computer Architecture v. Instruction Set Arch. ⢠What Computer Architecture brings to table
- 20. What Computer Architecturebrings to Table ⢠Other fields often borrow ideas from architecture ⢠Quantitative Principles of Design 1. Take Advantage of Parallelism 2. Principle of Locality 3. Focus on the Common Case 4. Amdahlâs Law 5. The Processor Performance Equation ⢠Careful, quantitative comparisons â Define, quantity, and summarize relative performance â Define and quantity relative cost â Define and quantity dependability â Define and quantity power ⢠Culture of anticipating and exploiting advances in technology ⢠Culture of well-defined interfaces that are carefully implemented and thoroughly checked
- 21. 1) Taking Advantageof Parallelism ⢠Increasing throughput of server computer via multiple processors or multiple disks ⢠Detailed HW design â Carry lookahead adders uses parallelism to speed up computing sums from linear to logarithmic in number of bits per operand â Multiple memory banks searched in parallel in set-associative caches ⢠Pipelining: overlap instruction execution to reduce the total time to complete an instruction sequence. â Not every instruction depends on immediate predecessor ď executing instructions completely/partially in parallel possible â Classic 5-stage pipeline: 1) Instruction Fetch (Ifetch), 2) Register Read (Reg), 3) Execute (ALU), 4) Data Memory Access (Dmem), 5) Register Write (Reg)
- 22. Pipelined Instruction Execution I n s t r. O r d e r Time(clock cycles) Reg ALU DMem Ifetch Reg Reg ALU DMem Ifetch Reg Reg ALU DMem Ifetch Reg Reg ALU DMem Ifetch Reg Cycle 1 Cycle 2 Cycle 3 Cycle 4 Cycle 6 Cycle 7 Cycle 5
- 23. Limits to pipelining â˘Hazards prevent next instruction from executing during its designated clock cycle â Structural hazards: attempt to use the same hardware to do two different things at once â Data hazards: Instruction depends on result of prior instruction still in the pipeline â Control hazards: Caused by delay between the fetching of instructions and decisions about changes in control flow (branches and jumps). I n s t r. O r d e r Time (clock cycles) Reg ALU DMem Ifetch Reg Reg ALU DMem Ifetch Reg Reg ALU DMem Ifetch Reg Reg ALU DMem Ifetch Reg
- 24. 2) The Principleof Locality ⢠The Principle of Locality: â Program access a relatively small portion of the address space at any instant of time. ⢠Two Different Types of Locality: â Temporal Locality (Locality in Time): If an item is referenced, it will tend to be referenced again soon (e.g., loops, reuse) â Spatial Locality (Locality in Space): If an item is referenced, items whose addresses are close by tend to be referenced soon (e.g., straight-line code, array access) ⢠Last 30 years, HW relied on locality for memory perf. P MEM $
- 25. Levels of theMemory Hierarchy CPU Registers 100s Bytes 300 â 500 ps (0.3-0.5 ns) L1 and L2 Cache 10s-100s K Bytes ~1 ns - ~10 ns $1000s/ GByte Main Memory G Bytes 80ns- 200ns ~ $100/ GByte Disk 10s T Bytes, 10 ms (10,000,000 ns) ~ $1 / GByte Capacity Access Time Cost Tape infinite sec-min ~$1 / GByte Registers L1 Cache Memory Disk Tape Instr. Operands Blocks Pages Files Staging Xfer Unit prog./compiler 1-8 bytes cache cntl 32-64 bytes OS 4K-8K bytes user/operator Mbytes Upper Level Lower Level faster Larger L2 Cache cache cntl 64-128 bytes Blocks
- 26. 3) Focus onthe Common Case ⢠Common sense guides computer design â Since its engineering, common sense is valuable ⢠In making a design trade-off, favor the frequent case over the infrequent case â E.g., Instruction fetch and decode unit used more frequently than multiplier, so optimize it 1st â E.g., If database server has 50 disks / processor, storage dependability dominates system dependability, so optimize it 1st ⢠Frequent case is often simpler and can be done faster than the infrequent case â E.g., overflow is rare when adding 2 numbers, so improve performance by optimizing more common case of no overflow â May slow down overflow, but overall performance improved by optimizing for the normal case ⢠What is frequent case and how much performance improved by making case faster => Amdahlâs Law
- 27. 4) Amdahlâs Law ď¨ďŠ enhanced enhanced enhanced new old overall Speedup Fraction Fraction 1 ExTime ExTime Speedup ďŤ ď ď˝ ď˝ 1 Best you could ever hope to do: ď¨ ďŠ enhanced maximum Fraction - 1 1 Speedup ď˝ ď¨ ďŠ ďş ďť ďš ďŞ ďŤ ďŠ ďŤ ď ď´ ď˝ enhanced enhanced enhanced old new Speedup Fraction Fraction ExTime ExTime 1
- 28. Amdahlâs Law example â˘New CPU 10X faster ⢠I/O bound server, so 60% time waiting for I/O ď¨ ďŠ ď¨ ďŠ 56 . 1 64 . 0 1 10 0.4 0.4 1 1 Speedup Fraction Fraction 1 1 Speedup enhanced enhanced enhanced overall ď˝ ď˝ ďŤ ď ď˝ ďŤ ď ď˝ â˘ Apparently, its human nature to be attracted by 10X faster, vs. keeping in perspective its just 1.6X faster
- 29. 5) Processor performanceequation CPU time = Seconds = Instructions x Cycles x Seconds Program Program Instruction Cycle Inst Count CPI Clock Rate Program X Compiler X (X) Inst. Set. X X Organization X X Technology X inst count CPI Cycle time
- 30. Whatâs a ClockCycle? ⢠Old days: 10 levels of gates ⢠Today: determined by numerous time-of-flight issues + gate delays â clock propagation, wire lengths, drivers Latch or register combinational logic
- 31. And in conclusion⌠⢠Computer Architecture >> instruction sets ⢠Computer Architecture skill sets are different â 5 Quantitative principles of design â Quantitative approach to design â Solid interfaces that really work â Technology tracking and anticipation ⢠CS 5513 to learn new skills, transition to research ⢠Computer Science at the crossroads from sequential to parallel computing â Salvation requires innovation in many fields, including computer architecture ⢠Read Chapter 1, then Appendices A & B.
Editor's Notes
- #13Â This slide is for the 3-min class administrative matters. Make sure we update Handout #1 so it is consistent with this slide.
- #24Â The principle of locality states that programs access a relatively small portion of the address space at any instant of time. This is kind of like in real life, we all have a lot of friends. But at any given time most of us can only keep in touch with a small group of them. There are two different types of locality: Temporal and Spatial. Temporal locality is the locality in time which says if an item is referenced, it will tend to be referenced again soon. This is like saying if you just talk to one of your friends, it is likely that you will talk to him or her again soon. This makes sense. For example, if you just have lunch with a friend, you may say, letâs go to the ball game this Sunday. So you will talk to him again soon. Spatial locality is the locality in space. It says if an item is referenced, items whose addresses are close by tend to be referenced soon. Once again, using our analogy. We can usually divide our friends into groups. Like friends from high school, friends from work, friends from home. Letâs say you just talk to one of your friends from high school and she may say something like: âSo did you hear so and so just won the lottery.â You probably will say NO, I better give him a call and find out more. So this is an example of spatial locality. You just talked to a friend from your high school days. As a result, you end up talking to another high school friend. Or at least in this case, you hope he still remember you are his friend. +3 = 10 min. (X:50)