Is there a Future for Differentiating ICs for High- End Televisions - - PowerPoint PPT Presentation

▶
is there a future for differentiating ics for high end
SMART_READER_LITE
LIVE PREVIEW

Is there a Future for Differentiating ICs for High- End Televisions - - PowerPoint PPT Presentation

Aug 26, 2022 160 likes •503 views

Is there a Future for Differentiating ICs for High- End Televisions ? MPSoC04 9 July 2004 Rafael Peset Llopis Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis 1 Outline High-end televisions Picture Quality

slide-1
SLIDE 1

1 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Is there a Future for Differentiating ICs for High- End Televisions ?

MPSoC’04 9 July 2004 Rafael Peset Llopis

slide-2
SLIDE 2

2 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Outline

  • High-end televisions
  • Picture Quality Roadmap
  • Current approach
  • Technology Roadmap
  • Solution?
  • Conclusions
slide-3
SLIDE 3

3 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Television Market

Three market segments:

– High 1M Philips sets 1500-10000 $ – Mid 3M Philips sets 500-1500 $ – Low 9M Philips sets < 500 $

Philips Consumer Electronics

– #2 worldwide – #1 Europe

Market players:

– Leaders; present in high-end – Followers

slide-4
SLIDE 4

4 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Philips Consumer Electronics

127 cm

High-End Television

slide-5
SLIDE 5

5 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

High-End Television

High-end market segment:

– Entry point innovation – Large margins – Branding – Differentiation is key

Current differentiation on picture quality SD/HD source => HD display (Europe/USA)

– Spatial up-conversion – Temporal up-conversion – Image enhancements

slide-6
SLIDE 6

6 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Outline

  • High-end televisions
  • Picture Quality Roadmap
  • Current approach
  • Technology Roadmap
  • Solution?
  • Conclusions
slide-7
SLIDE 7

7 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Picture Quality Roadmap

Digital image processing improvements like:

– Sub pixel based luminance transient improvement – Dynamic contrast – Digital natural motion – Color dependent sharpness – Green enhancement – Blue stretch – Skin tone correction – 3-dimensional digital noise reduction – scaling

Three EISA awards!!

slide-8
SLIDE 8

8 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Statistics: 401135 gates 32 mm2 278.4 kbit RAM 64 MHz 3 DAC’s PLL 0.18u; 4 metal layers 590 mW

Picture Quality Roadmap

slide-9
SLIDE 9

9 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

36,1% 32,8% 33,1% 38,2% 46,8% 48,5% 49,1%

0% 10% 20% 30% 40% 50% 60%

FEB02- MAR02 APR02- MAY02 JUN02- JUL02 AUG02- SEP02 OCT02- NOV02 DEC02- JAN03 FEB03- MAR03

PHILIPS GRP SONY GRUNDIG PANASONIC LOEWE

THOMSON GRP

Picture Quality Roadmap

slide-10
SLIDE 10

10 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Picture Quality Roadmap

So far so good… How is it implemented?

slide-11
SLIDE 11

11 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

High End Mid End Low End

Picture Quality Roadmap

Generation N Generation N+1

2

C B A

PS PS PS

D C B

PS PS PS

slide-12
SLIDE 12

12 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Picture Quality Roadmap

So far so good… How is it implemented?

– Common TV platform provided by Philips Semiconductors – Differentiation with additional key ICs – Migration to future common TV platform

Lead time of differentiating functionality in market!

slide-13
SLIDE 13

13 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Picture Quality Roadmap

2500% 1250% 500% 150% 100% #Mgates

  • excl. mem

2000% 1000% 500% 170% 100% #Mgates

  • incl. mem

350+ 250 133 64 64 frequency (MHz) 65 90 120 180 180 technology (nm) 1200% 600% 320% 140% 100% resources (manyears) 2010 2007 2005 2003 2001 year G5 G4 G3 G2 G1

65 90 120 180 180 1200% 600% 320% 140% 100% 2500% 1250% 500% 150% 100% 2000% 1000% 500% 170% 100%

slide-14
SLIDE 14

14 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Picture Quality Roadmap

So there is the pain!!

– Exploding engineering costs – Exploding complexity – Exploding mask costs (~1M $ for 0.065u)!!

Current design approach is unsustainable

– Innovation will stop

RIP

slide-15
SLIDE 15

15 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Outline

  • High-end televisions
  • Picture Quality Roadmap
  • Current approach
  • Technology Roadmap
  • Solution?
  • Conclusions
slide-16
SLIDE 16

16 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Huge computational requirements

– HD @ 100fps = 200M pixels/s – 1 pixel per clock – 100-400 GOPS – Regular & control dominated pixel processing

Communication requirements:

– Streaming data – Latency tolerant (beware audio/video & football)

Power dissipation bounded (no fans) Many different use cases (diversity) Stability

Requirements

(no + + )

Ctrl Alt Del

slide-17
SLIDE 17

17 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Current Approach

Computation:

– RTL VHDL blocks – Heavy pipelining

Communication:

– FIFO buffers – Handshaking – Bypasses – Centralized memory

Chain of video processing functions:

slide-18
SLIDE 18

18 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Current Approach

Many different use cases:

– Source (size, frame rate, TV, movie) – Display (size, type)

Superset approach:

– Large volume – High complexity – Verification issue !!!!

slide-19
SLIDE 19

19 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Outline

  • High-end televisions
  • Picture Quality Roadmap
  • Current approach
  • Technology Roadmap
  • Solution?
  • Conclusions
slide-20
SLIDE 20

20 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Technology Evolution

0. 001 0. 01 0. 1 1 10 100 1000 10000 100000 Jan- 90 Jan- 95 Jan- 00 Jan- 05 Jan- 10 Year G OPS ASI C t r end ASI C al t er a t r end FPGA DSP RI SC i nt el t r end MPU

ASICs are overkill Embedded cores provides less performance than stand-alone cores

slide-21
SLIDE 21

21 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

0. 001 0. 01 0. 1 1 10 100 1000 Jan- 90 Jan- 95 Jan- 00 Jan- 05 Jan- 10 Year G OPS/ W

ASI C t r end ASI C al t er a t r end FPGA DSP RI SC i nt el t r end MPU

Technology Evolution

FPGAs have improved in power efficiency Embedded cores are more power efficient than stand-alone cores 80x 3x

slide-22
SLIDE 22

22 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

0. 00001 0. 0001 0. 001 0. 01 0. 1 1 10 100 1000 Jan- 90 Jan- 95 Jan- 00 Jan- 05 Jan- 10 Year G OPS/ m m 2

ASI C t r end ASI C al t er a t r end FPGA DSP RI SC i nt el t r end MPU

Technology Evolution

20x 40x

Embedded cores are more area efficient than stand-alone cores

slide-23
SLIDE 23

23 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Technology Evolution

Observations:

– FPGAs and processors providing sufficient performance – Huge area and power expenses – Hybrids seem likely

slide-24
SLIDE 24

24 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Outline

  • High-end televisions
  • Picture Quality Roadmap
  • Current approach
  • Technology Roadmap
  • Solution?
  • Conclusions
slide-25
SLIDE 25

25 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Solution?

Subset with flexibility approach: Key:

– Composability – Flexibility – Scalability

slide-26
SLIDE 26

26 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Solution?

Exploding complexity and engineering costs:

Next step in design paradigm

Transistors => standard cells => synthesis => ?

Subset with flexibility approach IP reuse Composability

Exploding mask costs:

Even larger volumes Share silicon over more products Flexibility/scalability

slide-27
SLIDE 27

27 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Computation:

Embedded processors? Dedicated HW blocks? Flexible (eFPGA) HW blocks?

Communication:

Point to point? Busses? Network on Chip?

Solution?

A B D E G H C F I

slide-28
SLIDE 28

28 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Embedded Processors:

(Tunable) RISC / CISC VLIW / ULIW SIMD / vector Is SW cheaper than HW?

Dedicated HW blocks:

Behavioral synthesis

Flexible HW blocks:

Behavioral Synthesis Several e-FPGA blocks Fixed blocks with e-FPGA parts

Computation

1 pel/clk 20x area

slide-29
SLIDE 29

29 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Point to point:

Inflexible Not scalable

Busses:

Not scalable

Network on Chip:

Flexible and scalable

Key aspects:

– Cost / area – Required degree of flexibility (diversity) – Composability

Communication

slide-30
SLIDE 30

30 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Outline

  • High-end televisions
  • Picture Quality Roadmap
  • Current approach
  • Technology Roadmap
  • Solution?
  • Conclusions
slide-31
SLIDE 31

31 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis

Conclusions Questions/Challenges

Computation:

– Optimal mix ASIC / e-FPGA / programmable cores – What should be flexible, what not – Programming model

Communication:

– Composability – Flexibility / scalability

Both:

– Power / area efficiency – Engineering efficiency

Total cost (engineering hours + masks + silicon area)

slide-32
SLIDE 32

32 Philips Consumer Electronics, IC-laboratory, Rafael Peset Llopis