BRAINIAC: Bringing reliable accuracy into neurally-implemented approximate computing

2015 IEEE 21st International Symposium on High Performance Computer Architecture, HPCA 2015

Volumn , Issue , 2015, Pages 615-626

  Grigorian, Beayna ^a   Farahpour, Nazanin ^a   Reinman, Glenn ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ACCELERATION; COMPLEX NETWORKS; NETWORK ARCHITECTURE; REAL TIME SYSTEMS;

APPLICATION SPECIFIC; APPROXIMATE COMPUTING; COMPUTER ARCHITECTS; HETEROGENEOUS PLATFORMS; HIGH PERFORMANCE COMPUTING (HPC); LARGE AMOUNTS OF DATA; REAL TIME CONSTRAINTS; SINGLE-INSTRUCTION MULTIPLE-DATA ARCHITECTURES;

COMPUTER ARCHITECTURE;

EID: 84934325706     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/HPCA.2015.7056067     Document Type: Conference Paper

References (89)

1. R. S. Amant et al., "General-Purpose Code Acceleration with Limited-Precision Analog Computation," in ISCA '14, pp. 505-516.
2. "AMD FireStream GPU Compute Accelerators," http://www. amd. com/us/products/workstation/graphics/legacy/Pages/ firestream. aspx, AMD.
3. W. Baek et al., "Green: A Framework for Supporting Energy-Conscious Programming using Controlled Approximation," in PLDI '10, pp. 198-209.
4. B. Belhadj et al., "Continuous Real-World Inputs Can Open Up Alternative Accelerator Designs," in ISCA '13, pp. 1-12.
5. C. Bienia et al., "The PARSEC Benchmark Suite: Characterization and Architectural Implications," in PACT '08, pp. 72-81.
6. D. Bouris et al., "Fast and Efficient FPGA-Based Feature Detection Employing the SURF Algorithm," in FCCM '10, pp. 3-10.
7. "Box2D: A 2D Physics Engine for Games," http://box2d. org, Box2D.
8. M. Carbin et al., "Verifying Quantitative Reliability for Programs That Execute on Unreliable Hardware," in OOPSLA '13, pp. 33-52.
9. L. N. Chakrapani et al., "Ultra-Efficient (Embedded) SOC Architectures Based on Probabilistic CMOS (PCMOS) Technology," in DATE '06, pp. 1-6.
10. T. Chen et al., "BenchNN: On the Broad Potential Application Scope of Hardware Neural Network Accelerators," in IISWC '12, pp. 36-45.
11. H. Cho et al., "ERSA: Error Resilient System Architecture for Probabilistic Applications," TCAD '12, vol. 31, no. 4, pp. 546-558.
12. M. R. Choudhury et al., "Approximate Logic Circuits for Low Overhead, Non-Intrusive Concurrent Error Detection," in DATE '08, pp. 903-908.
13. N. Clark et al., "VEAL: Virtualized Execution Accelerator for Loops," in ISCA '08, pp. 389-400.
14. J. Cong et al., "Architecture Support for Accelerator-Rich CMPs," in DAC '12, pp. 843-849.
15. J. Cong et al., "CHARM: A Composable Heterogeneous Accelerator-Rich Microprocessor," in ISLPED '12, pp. 379-384.
16. J. Cong et al., "Accelerating Vision and Navigation Applications on a Customizable Platform," in ASAP '11, pp. 25-32.
17. J. Cong et al., "FPGA-Based Hardware Acceleration of Lithographic Aerial Image Simulation," TRETS '09, vol. 2, no. 3, pp. 17:1-17:29.
18. "The Hybrid-Core Series," http://www. conveycomputer. com/products/ hcseries, Convey Computer.
19. G. Danese et al., "A Parallel Neural Processor for Real-Time Applications," Micro '02, vol. 22, no. 3, pp. 20-31.
20. M. de Kruijf et al., "Relax: An Architectural Framework for Software Recovery of Hardware Faults," in ISCA '10, pp. 497-508.
21. P. Dubey, "A Platform 2015 Workload Model: Recognition, Mining and Synthesis Moves Computers to the Era of Tera," Intel Corporation, White Paper, 2007.
22. D. Ernst et al., "Razor: A Low-Power Pipeline Based on Circuit-Level Timing Speculation," in MICRO '03, pp. 7-18.
23. H. Esmaeilzadeh et al., "Architecture Support for Disciplined Approximate Programming," in ASPLOS '12, pp. 301-312.
24. H. Esmaeilzadeh et al., "Neural Acceleration for General-Purpose Approximate Programs," in MICRO '12, pp. 449-460.
25. S. Feng et al., "Shoestring: Probabilistic Soft Error Reliability on the Cheap," in ASPLOS '10, pp. 385-396.
26. H. Franke et al., "Introduction to the Wire-Speed Processor and Architecture," IBM J. of R&D '10, vol. 54, no. 1, pp. 3:1-3:11.
27. K. Fukushima, "A Neural Network for Visual Pattern Recognition," Computer '88, vol. 21, no. 3, pp. 65-75.
28. K. Fukushima, "Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position," Biological Cybernetics '80, vol. 36, no. 4, pp. 193-202.
29. P. D. Gader et al., "Handwritten Word Recognition with Character and Inter-Character Neural Networks," TSMC '97, vol. 27, no. 1, pp. 158-164.
30. V. Govindaraju et al., "Dynamically Specialized Datapaths for Energy Efficient Computing," in HPCA '11, pp. 503-514.
31. B. Grigorian et al., "Accelerating Divergent Applications on SIMD Architectures Using Neural Networks," in ICCD '14, pp. 317-323.
32. B. Grigorian et al., "Dynamically Adaptive and Reliable Approximate Computing Using Light-Weight Error Analysis," in AHS '14, pp. 248-255.
33. M. Gschwind, "Chip Multiprocessing and the Cell Broadband Engine," in CF '06, pp. 1-8.
34. V. Gupta et al., "Low-Power Digital Signal Processing Using Approximate Adders," TCAD '13, vol. 32, no. 1, pp. 124-137.
35. S. K. S. Hari et al., "Low-Cost Program-Level Detectors for Reducing Silent Data Corruptions," in DSN '12, pp. 1-12.
36. A. Hashmi et al., "Automatic Abstraction and Fault Tolerance in Cortical Microachitectures," in ISCA '11, pp. 1-10.
37. A. Hashmi et al., "A Case for Neuromorphic ISAs," in ASPLOS '11, pp. 145-158.
38. J. R. Hauser et al., "Garp: A MIPS Processor with a Reconfigurable Coprocessor," in FCCM '97, pp. 12-21.
39. R. Hegde et al., "Soft Digital Signal Processing," TVLSI '01, vol. 9, no. 6, pp. 813-823.
40. H. Hoffmann et al., "Dynamic Knobs for Responsive Power-Aware Computing," in ASPLOS '11, pp. 199-212.
41. M. Holler et al., "An Electrically Trainable Artificial Neural Network (ETANN) with 10240 'Floating Gate' Synapses," in IJCNN '89, pp. 191-196.
42. "CACTI 5. 3," http://quid. hpl. hp. com:9081/cacti, HP Labs.
43. J. Huang et al., "A Methodology for Energy-Quality Tradeoff Using Imprecise Hardware," in DAC '12, pp. 504-509.
44. H. Jang et al., "Neural Network Implementation Using CUDA and OpenMP," in DICTA '08, pp. 155-161.
45. T. Johnson et al., "An 8-core, 64-thread, 64-bit Power Efficient SPARC SoC (Niagara2)," in ISPD '07, pp. 2-2.
46. A. B. Kahng et al., "ORION 2. 0: A Fast and Accurate NoC Power and Area Model for Early-Stage Design Space Exploration," in DATE '09, pp. 423-428.
47. K. Kamijo et al., "Stock Price Pattern Recognition-A Recurrent Neural Network Approach," in IJCNN '90, pp. 215-221.
48. S. Lawrence et al., "Face Recognition: A Convolutional Neural-Network Approach," TNN '97, vol. 8, no. 1, pp. 98-113.
49. Y. Lee et al., "Exploring the Tradeoffs Between Programmability and Efficiency in Data-Parallel Accelerators," in ISCA '11, pp. 129-140.
50. S. Li et al., "McPAT: An Integrated Power, Area, and Timing Modeling Framework for Multicore and Manycore Architectures," in MICRO '09, pp. 469-480.
51. X. Li et al., "Application-Level Correctness and its Impact on Fault Tolerance," in HPCA '07, pp. 181-192.
52. E. Lindholm et al., "NVIDIA Tesla: A Unified Graphics and Computing Architecture," Micro '08, vol. 28, no. 2, pp. 39-55.
53. C. Lomont, "Introduction to Intel Advanced Vector Extensions," in ASCI '11, pp. 132-137.
54. S.-L. Lu, "Speeding Up Processing with Approximation Circuits," Computer '04, vol. 37, no. 3, pp. 67-73.
55. M. J. Lyons et al., "The Accelerator Store: A Shared Memory Framework for Accelerator-Based Systems," TACO '12, vol. 8, no. 4, pp. 48:1-48:22.
56. P. S. Magnusson et al., "Simics: A Full System Simulation Platform," Computer '02, vol. 35, no. 2, pp. 50-58.
57. M. M. K. Martin et al., "Multifacet's General Execution-Driven Multiprocessor Simulator Toolset," SIGARCH Comp. Archit. News '05, vol. 33, no. 4, pp. 92-99.
58. J. Misra et al., "Artificial Neural Networks in Hardware: A Survey of Two Decades of Progress," Neurocomputing '10, vol. 74, no. 1, pp. 239-255.
59. "Nallatech: Intel Xeon FSB-FPGA Accelerator Module," http://www. nallatech. com/Intel-Xeon-FSB-Socket-Fillers/fsbdevelopment-systems. html, Nallatech.
60. S. Narayanan et al., "Scalable Stochastic Processors," in DATE '10, pp. 335-338.
61. S. H. Nawab et al., "Approximate Signal Processing," J. VLSI Sig. Proc. '97, vol. 15, no. 1-2, pp. 177-200.
62. S. Nissen, "Implementation of a Fast Artificial Neural Network Library (FANN)," University of Copenhagen (DIKU), Report, 2003.
63. K.-S. Oh et al., "GPU Implementation of Neural Networks," Pattern Recognition '04, vol. 37, no. 6, pp. 1311-1314.
64. J. M. Ortega et al., Iterative Solution of Nonlinear Equations in Several Variables. Academic Press '70.
65. R. Parisi et al., "Car Plate Recognition by Neural Networks and Image Processing," in ISCAS '98, vol. 3, pp. 195-198.
66. H. Park et al., "Polymorphic Pipeline Array: A Flexible Multicore Accelerator with Virtualized Execution for Mobile Multimedia Application," in MICRO '09, pp. 370-380.
67. K. W. Przytula et al., Parallel Digital Implementations of Neural Networks, 1st ed. Prentice Hall, Inc., 1993.
68. W. Qian et al., "An Architecture for Fault-Tolerant Computation with Stochastic Logic," TC '11, vol. 60, no. 1, pp. 93-105.
69. A. Ramirez et al., "The SARC Architecture," Micro '10, vol. 30, no. 5, pp. 16-29.
70. M. Samadi et al., "SAGE: Self-tuning Approximation for Graphics Engines," in MICRO '13, pp. 13-24.
71. A. Sampson et al., "EnerJ: Approximate Data Types for Safe and General Low-Power Computation," in PLDI '11, pp. 164-174.
72. J. Schemmel et al., "Wafer-Scale Integration of Analog Neural Networks," in IJCNN '08, pp. 431-438.
73. L. Seiler et al., "Larrabee: A Many-Core x86 Architecture for Visual Computing," TOG '08, vol. 27, no. 3, pp. 18:1-18:15.
74. S. Sidiroglou-Douskos et al., "Managing Performance vs. Accuracy Trade-Offs with Loop Perforation," in ESEC-FSE '11, pp. 124-134.
75. N. Srinivasa et al., "Neuromorphic Adaptive Plastic Scalable Electronics: Analog Learning Systems," Pulse '12, vol. 3, no. 1, pp. 51-56.
76. P. Stillwell et al., "HiPPAI: High Performance Portable Accelerator Interface for SoCs," in HiPC '09, pp. 109-118.
77. "Synopsys Design Compiler," http://www. synopsys. com/Tools/Pages/ default. aspx, Synopsys.
78. O. Temam, "A Defect-Tolerant Accelerator for Emerging High-Performance Applications," in ISCA '12, pp. 356-367.
79. G. V. Varatkar et al., "Energy-Efficient Motion Estimation Using Error-Tolerance," in ISLPED '06, pp. 113-118.
80. S. K. Venkata et al., "SD-VBS: The San Diego Vision Benchmark Suite," in IISWC '09, pp. 55-64.
81. S. Venkataramani et al., "SALSA: Systematic Logic Synthesis of Approximate Circuits," in DAC '12, pp. 796-801.
82. S. Venkataramani et al., "Quality Programmable Vector Processors for Approximate Computing," in MICRO '13, pp. 1-12.
83. G. Venkatesh et al., "QsCores: Trading Dark Silicon for Scalable Energy Efficiency with Quasi-Specific Cores," in MICRO '11, pp. 163-174.
84. L.-C. T. Wang et al., "A Combined Optimization Method for Solving the Inverse Kinematics Problem of Mechanical Manipulators," TRA '91, vol. 7, no. 4, pp. 489-499.
85. P. H. Wang et al., "EXOCHI: Architecture and Programming Environment for a Heterogeneous Multi-core Multithreaded System," in PLDI '07, pp. 156-166.
86. "Xilinx," http://www. xilinx. com, Xilinx.
87. T. Yeh et al., "The Art of Deception: Adaptive Precision Reduction for Area Efficient Physics Acceleration," in MICRO '07, pp. 394-406.
88. G. P. Zhang, "Neural Networks for Classification: A Survey," TSMC '00, vol. 30, no. 4, pp. 451-462.
89. J. Zhu et al., "FPGA Implementations of Neural Networks-A Survey of a Decade of Progress," in FPL '03, pp. 1062-1066.