A high-performance, low-power linear algebra core

Proceedings of the International Conference on Application-Specific Systems, Architectures and Processors

Volumn , Issue , 2011, Pages 35-42

  Pedram, Ardavan ^a   Gerstlauer, Andreas ^a   Geijn, Robert A Van De ^b  

^a The University of Texas at Austin   (United States)

^b University of Texas at Austin   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

45NM TECHNOLOGY; CURRENT COMPONENT; CUSTOM HARDWARES; FEASIBILITY STUDIES; LOW POWER; MATRIX COMPUTATION; ORDERS OF MAGNITUDE; REDUCING POWER; TECHNOLOGY SCALING;

ALGEBRA; COMPUTER ARCHITECTURE; EFFICIENCY;

MATRIX ALGEBRA;

EID: 80055100054     PISSN: 10636862     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASAP.2011.6043234     Document Type: Conference Paper

References (46)

1. R. Hameed et al., "Understanding sources of inefficiency in general-purpose chips," ISCA, 2010.
2. N. Zhang and R. W. Broderson, "The cost of flexibility in systems on a chip design for signal processing applications," University of California, Berkeley, Tech. Rep., 2002.
3. Z. Yu et al., "Asap: An asynchronous array of simple processors," Solid-State Circuits, IEEE Journal of, vol. 43, no. 3, pp. 695-705, march 2008.
4. J. Dongarra et al., "A set of level 3 basic linear algebra subprograms," ACM Trans. Math. Soft., vol. 16, no. 1, 1990.
5. K. Goto and R. van de Geijn, "Anatomy of a high-performance matrix multiplication," ACM Trans. Math. Soft., vol. 34, no. 3, p. 12, May 2008.
6. K. Goto and R. van de Geijn, "High-performance implementation of the level-3 BLAS," ACM Trans. Math. Softw., vol. 35, no. 1, pp. 1-14, 2008.
7. "Intel Math Kernel Library," Intel, User's Guide 314774-009US, 2009.
8. R. C. Whaley and J. J. Dongarra, "Automatically tuned linear algebra software," in SC, 1998.
9. K. Fatahalian et al., "Understanding the efficiency of GPU algorithms for matrix-matrix multiplication," ACM SIGGRAPH/EUROGRAPHICS, 2004.
10. V. Allada et al., "Performance analysis of memory transfers and GEMM subroutines on NVIDIA Tesla GPU cluster," CLUSTER'09, 2009.
11. V. Volkov and J. Demmel, "Benchmarking GPUs to tune dense linear algebra," SC, 2008.
12. R. Nath et al., "An improved MAGMA GEMM for Fermi GPUs," LAPACK WN #227, Tech. Rep., 2010.
13. T. Lippert et al., "Hyper-systolic matrix multiplication," Parallel Computing, 2001.
14. K. Sano et al., "Fpga-array with bandwidth-reduction mechanism for scalable and power-efficient numerical simulations based on finite difference methods," ACM Trans. Reconfigurable Technol. Syst., vol. 3, pp. 21:1-21:35, November 2010.
15. C. Takahashi et al., "Design and power performance evaluation of on-chip memory processor with arithmetic accelerators," IWIA, 2008.
16. J. Kelm et al., "Rigel: an architecture and scalable programming interface for a 1000-core accelerator," ISCA, 2009.
17. S. Vangal et al., "An 80-tile sub-100-W TeraFLOPS processor in 65-nm CMOS," IEEE J. of Solid-State Circuits, vol. 43, no. 1, 2008.
18. "CSX700 Floating Point Processor," ClearSpeed Technology Ltd, Datasheet 06-PD-1425 Rev 1, 2011.
19. P. Zicari et al., "A matrix product accelerator for field programmable systems on chip," Microprocessors and Microsystems 32, 2008.
20. L. Zhuo and V. Prasanna, "Scalable and modular algorithms for floatingpoint matrix multiplication on reconfigurable computing systems," IEEE Trans. on Parallel and Distributed Systems, vol. 18, no. 4, 2007.
21. G. Kuzmanov and W. van Oijen, "Floating-point matrix multiplication in a polymorphic processor," ICFPT, pp. 249 - 252, 2007.
22. B. A. Hendrickson and D. E. Womble, "The Torus-Wrap mapping for dense matrix calculations on massively parallel computers," SIAM J. Sci. Stat. Comput., vol. 15, no. 5, 1994.
23. J. Choi et al., "ScaLAPACK: A scalable linear algebra library for distributed memory concurrent computers," in Proc. of the 4th Symp. on the Frontiers of Massively Parallel Computation. IEEE, 1992.
24. S. Vangal et al., "A 6.2-GFlops floating-point multiply-accumulator with conditional normalization," IEEE J. of Solid-State Circuits, vol. 41, no. 10, 2006.
25. A. Pedram et al., "Towards a high-performance, low-power linear algebra processor," Computer Engineering Research Center, The University of Texas at Austin, Tech. Rep. UT-CERC-10-03, September 2010.
26. E. Quinnell et al., "Floating-point fused multiply-add architectures," ACSSC, pp. 331 - 337, 2007.
27. S. Jain et al., "A 90mW/GFlop 3.4GHz reconfigurable fused/continuous multiply-accumulator for floating-point and integer operands in 65nm," VLSID, 2010.
28. D. Tan et al., "Low-power multiple-precision iterative floating-point multiplier with SIMD support," IEEE Trans. on Computers, vol. 58, no. 2, 2009.
29. S. Galal and M. Horowitz, "Energy-efficient floating point unit design," IEEE Trans. on Computers, vol. PP, no. 99, 2010.
30. T. Shyamkumar et al., "CACTI:5.0 an integrated cache timing, power, and area model," HP Laboratories Palo Alto, Technical Report HPL- 2007-167, 2007.
31. P. Wolkotte, "Energy model of networks-on-chip and a bus," System-on- Chip, pp. 82 - 85, 2005.
32. K. Lahiri and A. Raghunathan, "Power analysis of system-level on-chip communication architectures," CODES+ISSS, 2004.
33. S. Li et al., "Mcpat: An integrated power, area, and timing modeling framework for multicore and manycore architectures," MICRO, 2009.
34. D. Brooks et al., "Wattch: a framework for architectural-level power analysis and optimizations," ISCA, pp. 83 - 94, 2000.
35. S. Hong and H. Kim, "An integrated GPU power and performance model," ISCA, Jun 2010.
36. H. Wong et al., "Demystifying GPU microarchitecture through microbenchmarking," ISPASS, pp. 235 - 246, 2010.
37. "Samsung DDR3 SDRAM: High-Performance, Energy-Efficient Memory for Todays Green Computing Platforms," SAMSUNG Green Memory, Tech. Rep., March 2009.
38. "Fermi computer architecture white paper," NVIDIA, Technical Report, 2009.
39. D. Kanter, "Inside Fermi: Nvidia's HPC push," Real World Technologies, Tech. Rep., September 2009.
40. V George et al., "Penryn: 45-nm next generation Intel® core™ 2 processor," A-SSCC, Jan 2008.
41. M. Parker, "High-performance floating-point implementation using FPGAs," in MILCOM, 2009.
42. S. Williams et al., "The potential of the Cell processor for scientific computing," in CF, 2006.
43. F. Lauginiger et al., "Performance of a multicore matrix multiplication library," STMCS, Jan 2007.
44. B. Kagstrom et al., "GEMM-based level 3 BLAS: High performance model implementations and performance evaluation benchmark," ACM Trans. Math. Soft, vol. 24, no. 3, 1998.
45. E. Anderson et al., LAPACK Users' guide (third ed.). Philadelphia, PA, USA: SIAM, 1999.
46. F. Van Zee, libflame: The Complete Reference. www.lulu.com, 2009.