Reconfigurable Systems Emerge

Nick Tredennick, Editor

Gilder Technology Report
bozo@computer.org
2 November 2017 Nick Tredennick
 Overview
Major trends affecting the microprocessor
market
Value PC
Value transistor
Emerging economies
Microprocessors
Computer microprocessors
Embedded microprocessors
Configurable microprocessors
PLD microprocessors

2 November 2017 Nick Tredennick

 Moores Law

2 November 2017 Nick Tredennick

 Top View: Field-Effect Transistor

2 November 2017 Nick Tredennick

 The Microprocessor
10 years of Moores-law progress led to
the microprocessor
The second generic component
Raised engineers productivity
Problem-solving became programming
Grew to billions of units/year
Stalled progress in design methods for
thirty years

2 November 2017 Nick Tredennick

 The Personal Computer
10 years of microprocessor progress led
to the PC
Dominated the industry for 20 years
Supply of performance grows with
Moores law
Demand grows more slowly
Diverging growth in supply and demand
leads to the value PC

2 November 2017 Nick Tredennick

 The PC Is Good Enough

2 November 2017 Nick Tredennick

 The Path To The Value Transistor

2 November 2017 Nick Tredennick

 Transistors Are Good Enough

2 November 2017 Nick Tredennick

 Foundries: Adoption Rate By Process

Modeled after: TSMC http://www.tsmc.com/english/technology/t0203.htm

2 November 2017 Nick Tredennick
 Semiconductors: Industry In Transition
Causes
The transistor is good enough
The PC is good enough
Effects
Shift from tethered to mobile systems
Changes design emphasis
From: cost-performance
To: cost-performance-per-watt
Non-volatile memory will emerge
Wafer stacking will emerge
MEMS will emerge
2 November 2017 Nick Tredennick
 Design Alternatives
What Value Who
Microprocessors $40B Programmers
ASICs $30B Logic designers
FPGAs $3B Logic designers

FPGAs and microprocessors are

usurping a declining ASIC market.
Microprocessors (and their derivatives)
will win.
2 November 2017 Nick Tredennick
 Programmers And Logic Designers

Programmers optimize software

Languages
OS
Compilers
The Users Manual Applications
is the Programmers
(problematic)
bridge
Logic designers optimize hardware
Microprocessors
Memory

Logic designers
2 November 2017 Nick Tredennick
 Microprocessors
Microprocessor advantages
Flexibility
High-volume production
Usable by programmers
Microprocessor limitations
Too slow
Too much power

2 November 2017 Nick Tredennick

 Microprocessors Are Unsuitable

2 November 2017 Nick Tredennick

 Application-Specific Integrated Circuits
ASIC advantages
Best performance
Smallest chip
The benchmark for function efficiency
ASIC limitations
Inflexible
Expensive to design
High fixed costs require large production
runs
Requires logic design

2 November 2017 Nick Tredennick

 Programmable Logic Devices
PLD advantages
Flexibility
High-volume production
PLD limitations
Chips too expensive
Too slow
Requires logic design

2 November 2017 Nick Tredennick

 ASICs and PLDs (FPGAs)
ASICs and PLDs are competing in a
$30-billion market
This competition will not cross into the
microprocessor market because designs
require logic designers

2 November 2017 Nick Tredennick

 Supply and Demand: ASICs & PLDs

2 November 2017 Nick Tredennick

 Microprocessors and ASICs

Microprocessor

For the ultimate in flexibility,

programmers map the application
Application

onto a general-purpose
microprocessor.
Programmers

For the ultimate in performance, logic

designers map the application into a
custom circuit.

ASIC
Logic designers
2 November 2017 Nick Tredennick
 Microprocessor Evolution
Dynamically
reconfigurable
microprocessor
Run-time
reconfigurable Ascenium
microprocessor
Microprocessor Stretch
Design-time Programmers
configurable
microprocessor
ARC
MIPS
Tensilica

ASIC

FPGA
Logic designers
2 November 2017 Nick Tredennick
 Design-Time Configurable Microprocessor

Most of the
application runs as
execution of
general-purpose
Profile the instructions
application
Application

Programmers

Create custom Design-time

hardware and configurable
instructions to microprocessor
accelerate critical
application sections

Logic designers
2 November 2017 Nick Tredennick
 Design-Time Configurable Microprocessor
Profile the application
Create custom instructions for critical code sections
Build specialized execution units
Can be 10 to100 times faster than a general-purpose
microprocessor on the target algorithm
Examples: ARC and Tensilica
Customized microprocessor limitations
Requires logic designers
Creates an application-specific, limited-function
microprocessor
Accelerates only critical sections

2 November 2017 Nick Tredennick

 Run-Time Reconfigurable Microprocessor
Most of the
application runs as
execution of
Profile the general-purpose
application instructions
Application

Run-time
Create custom reconfigurable
instructions in an microprocessor
FPGA fabric to
accelerate critical
application sections
Programmers

Logic designers
2 November 2017 Nick Tredennick
 Run-Time Reconfigurable Microprocessor
Build a general-purpose microprocessor with
integrated FPGA fabric
Profile the application
Create custom instructions for critical code sections
Build custom execution units in FPGA fabric
Can be 10 to 100 times faster than a general-purpose
microprocessor on the target application
Example: Stretch
Run-time reconfigurable microprocessor limitations
Accelerates only statically identifiable critical sections
Limited to problems for which profiling works
Profiling is difficult

2 November 2017 Nick Tredennick

 Dynamically Reconfigurable Microprocessor
Application

Dynamically
Create custom reconfigurable
instructions in a microprocessor
custom fabric to
accelerate the
entire application
Programmers

Logic designers
2 November 2017 Nick Tredennick
 Dynamically Reconfigurable Microprocessor
Each cycle creates a new microprocessor
implementation
Each cycle creates a custom circuit (Ascenium instruction)
representing hundreds to thousands of conventional
instructions
Programmed using ANSI-standard programming
languages (e.g., C/C++)
Tens to 100s of times faster than a general-purpose
microprocessor
Dynamically reconfigurable microprocessor
limitations
There are none on the market today
Until Ascenium, no one has figured out how to program a
dynamically reconfigurable circuit
VCs dont understand it

2 November 2017 Nick Tredennick

 Microprocessors
x86 AMD, Intel, Transmeta, Via
ARC ARC
ARM ARM
MicroBlaze Xilinx
MIPS MIPS
Nios Altera
PowerPC IBM, Freescale
SPARC Sun
Tensilica Stretch, Tensilica
Old stuff Everyone

2 November 2017 Nick Tredennick

 Microprocessor Applications
Supercomputers
Workstations and servers
PCs
Embedded systems
Automobiles
Cameras
Cell phones
Game players
MP3 players
Set-top boxes

2 November 2017 Nick Tredennick

 Computer Markets
180

160
Millions of Units

140

120

100

80

60

40

20

0
Windows Servers SuperCs

2 November 2017 Nick Tredennick

 Microprocessor Markets

8000

7000
Millions of Units

6000

5000

4000

3000

2000

1000

0
Embedded PCs Servers

2 November 2017 Nick Tredennick

 Computer Microprocessors
x86
AMD
Intel
Transmeta
Via
Proprietary
IBM
Freescale
Sun

2 November 2017 Nick Tredennick

 Embedded Microprocessors
x86 AMD, Transmeta, Via
ARM ARM
PowerPC IBM, Freescale
Old stuff Everyone
Triscend (Xilinx)

2 November 2017 Nick Tredennick

 Configurable Microprocessors
ARC ARC
Ascenium Ascenium
MIPS MIPS
Nios Altera
Tensilica Stretch, Tensilica

2 November 2017 Nick Tredennick

 PLD Microprocessors
Altera
Nios (soft)
Xilinx
MicroBlaze (soft)
PicoBlaze (soft)
PowerPC (hard)

2 November 2017 Nick Tredennick

 Microprocessor-like
DSPs
Network processors
Specialty processors

2 November 2017 Nick Tredennick

 ASICs & Microprocessors

2 November 2017 Nick Tredennick

 ASICs & Microprocessors

2 November 2017 Nick Tredennick

 ASICs & Microprocessors

2 November 2017 Nick Tredennick

 Semiconductor Trends
Value PCs outsell leading-edge PCs
Mobile applications emerge
Design emphasis shifts from cost
performance to cost-performance-per-watt
Value transistors outsell leading-edge
transistors
Transistor performance overshoots many
applications
Increasing demand in emerging economies
Foundry strength grows

2 November 2017 Nick Tredennick

 Consequences
Rise of mobile applications
New non-volatile memories
Rise of foundries
Rise of soft (IP) cores
Horizontal fragmentation of integrated device
manufacturers
Rise of non-volatile FPGAs
Rise of reconfigurable systems
Growing market for embedded microprocessors
Tethered: traditional role
Mobile: supervisory role

2 November 2017 Nick Tredennick

 Industries in Transition
Automotive
Analog Digital
Mechanical Electrical
Isolated Connected
Telecom
Analog Digital
Copper Optical, Wireless
Biomedical
Analog Digital
Wet labs Bioinformatics
Film/video
Analog Digital
Isolated Connected
Consumer
Analog Digital
Isolated Connected
Tethered Untethered
Computers
Desktop Embedded

2 November 2017 Nick Tredennick