FI20215475A1 - Förfarande för ökning av energieffektivitet genom att utnyttja feltoleranta algoritmer för digitala system med underspänning - Google Patents

Förfarande för ökning av energieffektivitet genom att utnyttja feltoleranta algoritmer för digitala system med underspänning Download PDF

Info

Publication number
FI20215475A1
FI20215475A1 FI20215475A FI20215475A FI20215475A1 FI 20215475 A1 FI20215475 A1 FI 20215475A1 FI 20215475 A FI20215475 A FI 20215475A FI 20215475 A FI20215475 A FI 20215475A FI 20215475 A1 FI20215475 A1 FI 20215475A1
Authority
FI
Finland
Prior art keywords
matrix
voltage
matrix accelerator
processing system
accelerator
Prior art date
Application number
FI20215475A
Other languages
English (en)
Finnish (fi)
Other versions
FI130137B (sv
Inventor
Mehdi Safarpour
Olli Silvén
Original Assignee
Univ Of Oulu
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Univ Of Oulu filed Critical Univ Of Oulu
Priority to FI20215475A priority Critical patent/FI130137B/sv
Priority to PCT/FI2022/050258 priority patent/WO2022223881A1/en
Publication of FI20215475A1 publication Critical patent/FI20215475A1/sv
Application granted granted Critical
Publication of FI130137B publication Critical patent/FI130137B/sv

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
    • G06F11/0766—Error or fault reporting or storing
    • G06F11/0772—Means for error signaling, e.g. using interrupts, exception flags, dedicated error registers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234—Power saving characterised by the action undertaken
    • G06F1/3296—Power saving characterised by the action undertaken by lowering the supply or operating voltage
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/28—Supervision thereof, e.g. detecting power-supply failure by out of limits supervision
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234—Power saving characterised by the action undertaken
    • G06F1/324—Power saving characterised by the action undertaken by lowering clock frequency
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/004—Error avoidance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03K—PULSE TECHNIQUE
    • H03K19/00—Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits
    • H03K19/0008—Arrangements for reducing power consumption
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03K—PULSE TECHNIQUE
    • H03K19/00—Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits
    • H03K19/003—Modifications for increasing the reliability for protection
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03K—PULSE TECHNIQUE
    • H03K3/00—Circuits for generating electric pulses; Monostable, bistable or multistable circuits
    • H03K3/02—Generators characterised by the type of circuit or by the means used for producing pulses
    • H03K3/027—Generators characterised by the type of circuit or by the means used for producing pulses by the use of logic circuits, with internal or external positive feedback
    • H03K3/037—Bistable circuits
    • H03K3/0375—Bistable circuits provided with means for increasing reliability; for protection; for ensuring a predetermined initial state when the supply voltage has been applied; for storing the actual state when the supply voltage fails

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Quality & Reliability (AREA)
  • Biomedical Technology (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Neurology (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Medicines Containing Plant Substances (AREA)
  • Power Sources (AREA)
FI20215475A 2021-04-22 2021-04-22 Förfarande för ökning av energieffektivitet genom att utnyttja feltoleranta algoritmer för digitala system med underspänning FI130137B (sv)

Priority Applications (2)

Application Number Priority Date Filing Date Title
FI20215475A FI130137B (sv) 2021-04-22 2021-04-22 Förfarande för ökning av energieffektivitet genom att utnyttja feltoleranta algoritmer för digitala system med underspänning
PCT/FI2022/050258 WO2022223881A1 (en) 2021-04-22 2022-04-20 A method for increase of energy efficiency through leveraging fault tolerant algorithms into undervolted digital systems

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
FI20215475A FI130137B (sv) 2021-04-22 2021-04-22 Förfarande för ökning av energieffektivitet genom att utnyttja feltoleranta algoritmer för digitala system med underspänning

Publications (2)

Publication Number Publication Date
FI20215475A1 true FI20215475A1 (sv) 2022-10-23
FI130137B FI130137B (sv) 2023-03-09

Family

ID=81850667

Family Applications (1)

Application Number Title Priority Date Filing Date
FI20215475A FI130137B (sv) 2021-04-22 2021-04-22 Förfarande för ökning av energieffektivitet genom att utnyttja feltoleranta algoritmer för digitala system med underspänning

Country Status (2)

Country Link
FI (1) FI130137B (sv)
WO (1) WO2022223881A1 (sv)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11710030B2 (en) * 2018-08-31 2023-07-25 Texas Instmments Incorporated Fault detectable and tolerant neural network

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE1774906A1 (de) 1967-10-30 1971-11-04 Olivetti & Co Spa Dezimalrechenmaschine
US7278080B2 (en) 2003-03-20 2007-10-02 Arm Limited Error detection and recovery within processing stages of an integrated circuit
CN101369241A (zh) 2007-09-21 2009-02-18 中国科学院计算技术研究所 一种机群容错系统、装置及方法
US20120221884A1 (en) 2011-02-28 2012-08-30 Carter Nicholas P Error management across hardware and software layers
US10908668B2 (en) * 2017-12-29 2021-02-02 Intel Corporation Voltage droop mitigation technology in array processor cores
CN108733628B (zh) 2018-05-23 2020-01-03 河海大学常州校区 一种并行矩阵乘算法的加固方法
CN110932713B (zh) * 2019-11-11 2023-05-16 东南大学 用于卷积神经网络硬件加速器的时序弹性电路

Also Published As

Publication number Publication date
FI130137B (sv) 2023-03-09
WO2022223881A1 (en) 2022-10-27

Similar Documents

Publication Publication Date Title
Mittal A survey on modeling and improving reliability of DNN algorithms and accelerators
Venkataramani et al. Substitute-and-simplify: A unified design paradigm for approximate and quality configurable circuits
Wu et al. An efficient method for calculating the error statistics of block-based approximate adders
EP3035254A1 (en) Method of managing the operation of an electronic system with a guaranteed lifetime
Safarpour et al. Algorithm level error detection in low voltage systolic array
Wang et al. Resilience-aware frequency tuning for neural-network-based approximate computing chips
Damsgaard et al. Approximation opportunities in edge computing hardware: A systematic literature review
Chen et al. Two approximate voting schemes for reliable computing
FI130137B (sv) Förfarande för ökning av energieffektivitet genom att utnyttja feltoleranta algoritmer för digitala system med underspänning
Taheri et al. Deepaxe: A framework for exploration of approximation and reliability trade-offs in dnn accelerators
Salamin et al. Reliability-aware quantization for anti-aging NPUs
Jiao et al. Tevot: Timing error modeling of functional units under dynamic voltage and temperature variations
Ozen et al. Architecting decentralization and customizability in dnn accelerators for hardware defect adaptation
Huang et al. Sensor-based approximate adder design for accelerating error-tolerant and deep-learning applications
Chen et al. Design and evaluation of confidence-driven error-resilient systems
Kong et al. M2STaR: A Multi-Mode Spatio-Temporal Redundancy Design for Fault-Tolerant Coarse-Grained Reconfigurable Architectures
Huang et al. A determinate radiation hardened technique for safety-critical CMOS designs
Deepanjali et al. Self healing controllers to mitigate SEU in the control path of FPGA based system: A complete intrinsic evolutionary approach
Liu et al. Runtime long-term reliability management using stochastic computing in deep neural networks
Marty et al. Algorithm level timing speculation for convolutional neural network accelerators
Tsounis et al. A methodology for fault-tolerant pareto-optimal approximate designs of fpga-based accelerators
Santiago et al. Characterizing approximate adders and multipliers for mitigating aging and temperature degradations
Ikezoe et al. Recovering faulty non-volatile flip flops for coarse-grained reconfigurable architectures
Abdallah et al. Timing error statistics for energy-efficient robust DSP systems
Juliato et al. SEU-resistant SHA-256 design for security in satellites