1. Introduction 1 Introduction

2. 2 Why Programmable Logic ?  Custom logic without NRE —needed for product differentiation  Fast time to market —shorter design life in a competitive world  In-system programmability —simpler manufacturing logistics —easy field upgrade —feature swapping

3. Introduction 3 Users Expect  Logic capacity —50,000 to a million gates  Clock speed —100 MHz and above  Cost —reasonable premium over ASICs  Design effort and time —powerful synthesis, fast compile times  Power consumption —must stay within limits

4. Introduction 4 Recent Developments  Deep submicron arrived unexpectedly early —0.5µ-0.35µ-0.25µ-0.18µ-?  Deep submicron technology provides “for free” —speed, density, low cost  But it requires voltage migration —5 V - 3.3 V - 2.5 V - 1.8 V - 1.5 V - ?

5. Introduction 5 Design Alternatives  Microprocessors —Ideal, if fast enough  Gates, MSI, PALs —Outdated, inefficient inflexible  Dedicated Standard Chip Sets —Cheap, but no product differentiation  ASICs —Only for rock-stable, high-volume designs  Programmable Logic —For flexibility and performance

6. Introduction 6 ASICs Are Becoming Less Attractive  Non-recurring engineering cost increases —more masking steps, more expensive masks  Minimum order quantity rises —larger wafers, smaller die  Silicon capability exceeds user requirements  Suppliers are leaving this overly competitive market

7. Introduction 7 1/911/921/931/941/951/961/971/981/99 Year Capacity Speed Price FPGAs Are Gaining Acceptance  > 20x Bigger  > 5x Faster  > 50x Cheaper 1 10 100

8. Introduction 8 FPGAs Are Good Enough  Adequate capacity, performance, price —200,000 gates, 85 MHz in 1998 —1,000,000 gates, 200 MHz in 1999  Standard product advantages —steep learning curve, cost decline —performance gain, speed binning  IC manufacturing is best at mass-production —custom devices have an inherent disadvantage

9. Introduction 9 FPGAs are Good Enough Better  Deep submicron ASIC design is difficult —second-order effects burden the traditional logic abstraction —system designer needs help from EE  Verification is very time consuming  Hardware/software integration is delayed —until a working chip is delivered.

10. Introduction 10 FPGAs Are Better  User can focus on logic, not circuits  Xilinx solves all circuit problems —clock delay and skew —interconnect delay —crosstalk —I/O standards  FPGAs are 100% tested by generic test methods  Easy verification, incremental design  Early hardware/software integration

11. Introduction 11 FPGAs Are Better Vastly Superior  Avoid the ASIC re-spin cost —design error or market change  Avoid the ASIC inventory risk —over- or under-inventory —obsolescence  Reprogrammability —last-minute design modifications —last-step system customization —field hardware upgrades —reconfiguration per application —reconfiguration per task  ASICs will never offer these features

12. Introduction 12 The Programmable Frontier Then: 1998  250k gates  100 MHz  $5 Now: 1999  1 Million gates  170 MHz FIFO  420 MHz frequency counter  $2 95 for SpartanXL —1¢ per Logic Cell  $1 20 for XC9500XL —3¢ per Macrocell Four times bigger and twice as fast at half the price … In ONE year!

13. Introduction 13 CPLDs Complement FPGAs  CPLD strengths —Wide address decoding —Synchronous state machines —Short combinatorial pin-to-pin delays  Ideal for glue logic —Low-cost —Single-chip —Non-volatile —In-System Programmable  Quick and easy to use

14. Introduction 14 The Compelling Conclusion: Programmable is the Way to Go!  FPGAs provide performance and flexibility —The performance of custom-hardware —The ease of design and inherent flexibility of a microprocessor solution  FPGAs avoid the risks of ASICs —The design risk —The time-to-market risk —The inventory risk  CPLDs provide a fast, low-cost alternative —Good for simple designs

15. Introduction 15 Use the web to improve hardware design productivity and enable Internet-reconfigurable applications for YOUR customers Silicon Xpresso  Interactive web-based design tools and support — WebFITTER — software release 1.5i — support.xilinx.com — Internet Team-based Design (ITD)  Internet Reconfigurable Logic —Tools for the end product – Java API for Boundary Scan – JBits —Remote debugging and field upgrades —Internet Appliances

16. Introduction 16 Xilinx Solutions in This Seminar Simple, Low-cost Solutions 100+MHz System Solutions Design Productivity Solutions

17. Introduction 17 You need not be rich or a genius to use our programmable logic Simple, Low-cost Solutions  Xilinx offers low-cost CPLD and FPGA devices and a low-cost Foundation software package  The devices are fast and have systems-oriented features  The software is powerful and easy to use.

18. Introduction 18 You can achieve reliable and predictable performance – automatically 100+MHz System Solutions  The Virtex family provides efficient solutions for: —Electrical and thermal issues —I/O, logic, and memory design  Alliance software provides powerful tools for a variety of design styles

19. Introduction 19 You can create large FPGA designs without having to “re-invent the wheel” Design Productivity Solutions  Designs are getting larger and more complex —Design times are getting shorter —Fast time-to-market is crucial  Xilinx offers design methodologies and well- documented, proven logic cores that increase productivity and reduce risk

20. Introduction 20 Three new Xilinx families  SpartanXL —3.3-V low-cost FPGA —5,000 to 40,000 gates  XC9500XL —3.3-V In-System Programmable CPLD —up to 200 MHz  Virtex —next-generation FPGA with system features —up to a million gates This seminar highlights the applications of these three families

21. Introduction 21 Families Not In This Seminar  XC3000A, XC3100A —for existing designs  XC4000E, ’EX, ’XL, ’XLA, ’XV —the industry’s most successful FPGAs  XC5200 —for existing designs  XC1700 —Serial configuration PROMs for all families

22. Introduction 22 Xilinx Solutions in This Seminar  Simple, Low-cost Solutions  100+MHz System Solutions  Design Productivity Solutions