Augmented von Neumann Processors

1
Augmented von Neumann Processors
Binu K. Mathew, Al Davis School of
Computing University of Utah
2
Guide to the future!
"What is it?" asked Arthur. "The Hitchhiker's
Guide to the Galaxy. It's a sort of electronic
book a million "pages could be summoned at a
moment's notice... A screen, about three
inches by four, lit up and characters began to
flicker across the surface. The words Vogon
Constructor Fleets flared in green across the
screen. At the same time, the book began to
speak the entry as well in a still quiet measured
voice.This is what the book said. - Douglas
Adams, The Hitch Hikers Guide to the Galaxy
3
Future Applications

• Projected performance requirement 10 GOPS
• Continuous speech recognition
• Handwriting and gesture recognition
• Computer Vision
• Heuristic searches in multimedia databases
• Video conferencing
• Power consumption of typical processors
• Intel Strong ARM SA110 _at_ 233 MHz 1 W (Max)
• Intel embedded Pentium _at_ 233 MHz 7.9W 17W
• AMD Athlon _at_ 800 MHz 45.5 W (Max core power)
• Can conventional archs provide required
  performance?
• At a low enough power budget ?

4
Primitives for Future Applications

• Hidden Markov Model Solvers Speech Recognition,
  Handwriting and gesture recognition
• FFT Audio processing
• DCT Image compression
• Block Data Difference Compression, motion
  detection
• Pattern matching Database searches, feature
  recognition
• Generalized filters Image and audio processing,
  array transformations
• Encryption/Decryption, block data transfer,
  heuristic processing of bulk data
• Reduction operators, block math units Image
  statistics, Finite element analysis, Logic
  simulation, Neural nets

5
Augmented von Neumann Processors

• Multiple threads of execution, task level
  parallelism
• Domain-specific coprocessors provide high
  performance at low power

Language model from memory
6
Conclusion

• Power
• Pihl et als HMM coprocessor consumes 853mW _at_
  154 MHz in a 5V, 0.8? technology
• 41mW estimated power _at_ 1GHz on a 1.2V. 0.1 ?
  process
• Indication that domain specific coprocessors win!
  
• Area
• AMD K-7 die area is 184mm2 in a 0.25 ? process
• Same K-7 is estimated to be 4.7-12.5 of the die
  area of a microprocessor of 2005 in a 0.1 ?
  process
• Total area of all our coprocessors is less than
  184 mm2
• Domain specific coprocessors win again!
• Challenges
• Identify core primitives, generalize
• Power efficient implementation
• Provide plumbing between units and overall
  framework