Lecture 2: Technology Trends Prof. Randy H. Katz Computer Science 252 Spring 1996

Transcription

1 Lecture 2: Technology Trends Prof. Randy H. Katz Computer Science 252 Spring 1996 RHK.S96 1

2 Original Food Chain Picture Big Fishes Eating Little Fishes RHK.S96 2

3 1985 Computer Food Chain Mainframe Workstation Minicomputer PC Supercomputer Minisupercomputer RHK.S96 3

4 Minisupercomputer Minicomputer 1995 Computer Food Chain Mainframe Supercomputer Workstation PC Massively Parallel Processors Now who is eating whom? RHK.S96 4

5 Why Such Change in 10 years? Function Rise of networking/local interconnection technology Performance Technology Advances» CMOS VLSI dominates TTL, ECL in cost & performance Computer architecture advances improves low-end» RISC, superscalar, RAID, Price: Lower costs due to Simpler development» CMOS VLSI: smaller systems, fewer components Higher volumes» CMOS VLSI : same dev. cost 10,000 vs. 100,000 units Lower margins by class of computer, due to fewer services RHK.S96 5

6 1985 Computer Food Chain Technologies ECL TTL MOS Mainframe Supercomputer Minicomputer Minisupercomputer Workstation PC RHK.S96 6

7 Technology Trends: Microprocessor Capacity Graduation Window Transistors i8086 i80286 i80386 i80486 Pentium Pentium Pro: 5.5 million PowerPC 620: 6.9 million Alpha 21164: 9.3 million Sparc Ultra: 5.2 million CMOS improvements: Die size: 2X every 3 yrs Line width: halve / 7 yrs i8080 i Year RHK.S96 7

8 CMOS Improvements Die size 2X every 3 yrs Line widths halve every 7 yrs Ratio to Area in Die size increase plus transistor count increase Transistors Transistor per Unit Count Area 0 Line Die Width SizeImprovement RHK.S96 8

9 Memory Capacity (Single Chip DRAM) size Bits year size cyc time Kb 250 ns Kb 220 ns Mb 190 ns Mb 165 ns Mb 145 ns Mb???? Year RHK.S96 9

10 Moore s Law for Memory 8G 1G Primary memory size of various sized systems in number of chips and memory system price at $50/chip over time $1.6M $200K 1 Gw 1G 128M 8M 1M 128K Number of chips 32K 4K 512 chips 64 $25.6K $3.2K $400 8 chips $6 1 chip 1/8th chip 8K Kbit 4K 16K 64K 256K 1M 4M 16M 64M 256M RHK.S96 10 $50 128M 32M 8M 640K DOS limit

11 Memory Size of Various Systems Over Time 8G 1G 4K chips 512 chips 128M 8M 64 chips workstation 8 chips-pc 1M 128K 1 chip 1/8 chip 640K DOS limit 8K Kbit 4K 16K 64K 256K 1M 4M 16M 64M 256M RHK.S96 11

12 Technology Trends (Summary) Capacity Speed Logic 2x in 3 years 2x in 3 years DRAM 4x in 3 years 1.4x in 10 years Disk 2x in 3 years 1.4x in 10 years RHK.S96 12

13 Processor Performance Trends Supercomputers Mainframes 10 Minicomputers 1 Microprocessors Year RHK.S96 13

14 Performance (VAX 780s) Mhz Performance vs. Time TTL ECL 15%/yr 68K MV10K uvax CMOS CMOS CISC 38%/yr 8600 Mips 25 mhz RISC 60% / yr o MIPS (8 Mhz) 4K Mips (65 Mhz) o 9000 uvax 6K (CMOS) Will RISC continue on a 60%, (x4 / 3 years)? Moore's speed law? RHK.S96 14

15 Processor Performance P e r f o r m a n c e X/yr HP 9000/750 DEC AXP MIPS M/120 Sun-4/260 MIPS M X/yr IBM RS6000/ Year IBM Power 2/590 Sun UltraSparc DEC 21064a RHK.S96 15

16 Performance Trends (Summary) Workstation performance (measured in Spec Marks) improves roughly 50% per year Improvement in cost performance estimated at 70% per year RHK.S96 16

17 Instructions/Second/$ vs. Time Instructions/second/$ PC Workstation Super-mini Mainframe RHK.S

18 Processor Perspective Putting performance growth in perspective: IBM POWER2 Cray YMP Workstation Supercomputer Year MIPS > 200 MIPS < 50 MIPS Linpack 140 MFLOPS 160 MFLOPS Cost $120,000 $1M ($1.6M in 1994$) Clock 71.5 MHz 167 MHz Cache 256 KB 0.25 KB Memory 512 MB 256 MB 1988 supercomputer in 1993 server! RHK.S96 18

19 1995 Computer Food Chain Technologies ECL Workstation Minisupercomputer Minicomputer CMOS Mainframe Supercomputer PC Massively Parallel Processors Endangered Species?? RHK.S96 19

20 Where Has This Performance Improvement Come From? Technology? Organization? Instruction Set Architecture? Software? Some combination of all of the above? RHK.S96 20

21 Performance Trends Revisited (Architectural Innovation) Supercomputers Mainframes 10 1 Minicomputers Microprocessors CISC/RISC Year RHK.S96 21

22 Performance Trends Revisited (Technology Advances) Logic Speed: Logic Capacity: 2x per 3 years 2x per 3 years Leads to: Computing capacity:4x per 3 years If can keep all the transistors busy all the time Actual: 3.3x per 3 years RHK.S96 22

23 Performance Trends Revisited (Microprocessor Organization) Transistors i4004 i8080 i8086 i80286 i80386 r3010 r4400 r Bit Level Parallelism Pipelining Caches Instruction Level Parallelism Out-of-order Xeq Speculation... Year RHK.S96 23

24 What is Ahead? Greater instruction level parallelism? Bigger caches? Multiple processors per chip? Complete systems on a chip? (Portable Systems) High performance LAN, Interface, and Interconnect RHK.S96 24

25 Hardware Technology Memory chips 64 K 4 M 256 M-1 G Speed /4 in. disks 40 M 1 G 20 G Floppies.256 M 1.5 M 500-2,000 G LAN (Switch) 2-10 Mbits 10 (100) (ATM) Busses 2-20 Mbytes RHK.S96 25

26 Software Technology Languages C, FORTRAN C++, HPF object stuff?? Op. System proprietary +DUM* +DUM+NT User I/F glass Teletype WIMP* stylus, voice, audio,video,?? Comp. Styles T/S, PC Client/Server agents*mobile New things PC & WS parallel proc. appliances Capabilities WP, SS WP,SS, mail video,?? DUM = DOS, n-unixes, MAC WIMP = Windows, Icons, Mouse, Pull-down menus Agents = robots that work on information RHK.S96 26

27 Computing 2001 Continue quadrupling memory every 3 years 1K chip in 72 becomes 1 gigabit chip (128 Mbyte) in 2002 On-line Gigabytes; $10 1-Gbyte floppies & CDs Micros increase at 60% per year... parallelism 100 Radio links for untethered computing RHK.S96 27

28 Computing 2001 Telephone, fax, radio, television, camera, house,... Real personal (watch, wallet,notepad) computers We should be able to simulate: Nearly everything we make and their factories Much of the universe from the nucleus to galaxies Performance implies: voice and visual Ease of use. Agents! RHK.S96 28

29 Applications: Unlimited Opportunities Office agents: phone/fax/comm; files/paper handling Untethered computing: fully distributed offices?? Integration of video, communication, and computing: desktop video publishing, conferencing, & mail Large, commercial transaction processing systems Encapsulate knowledge in a computer: scientific & engineering simulation (e.g. planetarium, wind tunnel,... ) RHK.S96 29

30 Applications: Unlimited Opportunities Generic mathematics; visualization & virtual reality Computational chemistry e.g biochemistry and matterials Mechanical engineering without prototypes Image/signal processing: medicine, maps, surveillance. Personal computers in 2001 are today's supercomputers Integration of the PC & TV => TC RHK.S96 30

31 Challenges for 1990s Platforms 64-bit computers & 16 Mbit (2Mbyte DRAM): video, voice, communication, any really new apps? Increasingly large, complex systems and environments Usability? Plethora of non-portable, distributed, incompatible, non-interoperable computers: Usability? Scalable parallel computers can provide commodity supercomputing : Markets and trained users? RHK.S96 31

32 Challenges for 1990s Platforms Apps to fuel and support a chubby industry: communications, paper/office, and digital video Computer commoditization & eventual disappearance (true ubiquitous computing!) The true portable, wireless communication computer Truly personal card, pencil, pocket, wallet computer Networks continue to limit: WAN, ISDN, and ATM? RHK.S96 32