Accelerating divergent applications on SIMD architectures using neural networks

2014 32nd IEEE International Conference on Computer Design, ICCD 2014

Volumn , Issue , 2014, Pages 317-323

  Grigorian, Beayna ^a   Reinman, Glenn ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Approximate Computing; Branch Divergence; Hardware Acceleration; Neural Networks; SIMD

Indexed keywords

APPLICATION PROGRAMS; CODES (SYMBOLS); ENERGY CONSERVATION; NETWORK ARCHITECTURE;

APPROXIMATE COMPUTING; BRANCH DIVERGENCE; HARDWARE ACCELERATION; NETWORK-BASED SOLUTIONS; NEURAL NETWORKS (NNS); PERFORMANCE DEGRADATION; SIMD; SINGLE-INSTRUCTION MULTIPLE-DATA ARCHITECTURES;

NEURAL NETWORKS;

EID: 84919678129     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICCD.2014.6974700     Document Type: Conference Paper

References (30)

1. C. Lomont, "Introduction to Intel Advanced Vector Extensions, " in ASCI "11, pp. 132-137.
2. E. Lindholm et al., "NVIDIA Tesla: A Unified Graphics and Computing Architecture, " IEEE Micro '08, vol. 28, no. 2, pp. 39-55.
3. J. E. Smith et al., "Vector Instruction Set Support for Conditional Operations, " in ISCA '00, pp. 260-269.
4. G. Diamos et al., "SIMD Re-Convergence at Thread Frontiers, " in MICRO '11, pp. 477-488.
5. W. W. L. Fung et al., "Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow, " in MICRO '07, pp. 407-420.
6. H. Wu et al., "Characterization and Transformation of Unstructured Control Flow in Bulk Synchronous GPU Applications, " IJHPCA '12, vol. 26, no. 2, pp. 170-185.
7. V. Narasiman et al., "Improving GPU Performance via Large Warps and Two-Level Warp Scheduling, " in MICRO '11, pp. 308-317.
8. W. W. L. Fung and T. M. Aamodt, "Thread Block Compaction for Efficient SIMT Control Flow, " in HPCA '11, pp. 25-36.
9. S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed. Prentice Hall PTR, 1998.
10. H. Esmaeilzadeh et al., "Neural Acceleration for General-Purpose Approximate Programs, " in MICRO '12, pp. 449-460.
11. S. Che et al., "A Performance Study of General-Purpose Applications on Graphics Processors Using CUDA, " JPDC '08, vol. 68, no. 10, pp. 1370-1380.
12. J. Cong et al., "Architecture Support for Accelerator-Rich CMPs, " in DAC '12, pp. 843-849.
13. J. Cong et al., "CHARM: A Composable Heterogeneous Accelerator-Rich Microprocessor, " in ISLPED '12, pp. 379-384.
14. H. Cho et al., "ERSA: Error Resilient System Architecture for Probabilistic Applications, " TCAD '12, vol. 31, no. 4, pp. 546-558.
15. S. Sidiroglou-Douskos et al., "Managing Performance vs. Accuracy Trade-Offs with Loop Perforation, " in SIGSOFT/FSE '11, pp. 124-134.
16. A. Sampson et al., "EnerJ: Approximate Data Types for Safe and General Low-Power Computation, " in PLDI '11, pp. 164-174.
17. M. Carbin, S. Misailovic, and M. C. Rinard, "Verifying Quantitative Reliability for Programs That Execute on Unreliable Hardware, " in OOPSLA, 2013, pp. 33-52.
18. D. Quinlan, "Rose: Compiler support for object-oriented frameworks, " Parallel Processing Letters '00, vol. 10, pp. 215-226.
19. D. E. Rumelhart et al., "Learning Representations by Back-Propagating Errors, " Nature '86, vol. 323, no. 6088, pp. 533-536.
20. K. Hornik, "Approximation Capabilities of Multilayer Feedforward Networks, " Neural Networks '91, vol. 4, no. 2, pp. 251-257.
21. C. Bienia et al., "The PARSEC Benchmark Suite: Characterization and Architectural Implications, " in PACT '08, pp. 72-81.
22. J. M. Ortega et al., Iterative Solution of Nonlinear Equations in Several Variables. Academic Press, 1970.
23. J. Sanders and E. Kandrot, CUDA by Example: An Introduction to General-Purpose GPU Programming. Addison-Wesley Pro., 2010.
24. S. Nissen, "Implementation of a Fast Artificial Neural Network Library (FANN), " DIKU, Report, 2003.
25. CUDA 5.5 Production Release, " http://developer.nvidia.com/ cuda-downloads, Nvidia.
26. Kill A Watt, " http://www.p3international.com/products/p4400.html, P3 International.
27. J. Sartori and R. Kumar, "Branch and Data Herding: Reducing Control and Memory Divergence for Error-Tolerant GPU Applications, " IEEE TMM, vol. 15, no. 2, pp. 279-290, Feb 2013.
28. B. Grigorian and G. Reinman, "Improving Coverage and Reliability in Approximate Computing Using Application-Specific, Light-Weight Checks, " in WACAS '14.
29. J. Meng et al., "Dynamic Warp Subdivision for Integrated Branch and Memory Divergence Tolerance, " in ISCA '10, pp. 235-246.
30. T. Chen et al., "BenchNN: On the Broad Potential Application Scope of Hardware Neural Network Accelerators, " in IISWC '12, pp. 36-45.