High-level synthesis using computation-unit integrated memories

ABSTRACT

High-level synthesis (HLS) of memory-intensive applications has featured several innovations in terms of enhancements made to the basic memory organization and data layout. However, increasing performance and energy demands faced by application-specific integrated circuits (ASIC) are forcing designers to alter the fundamental architectural template of the HLS output, namely, a controller-datapath associated with a memory subsystem (monolithic, banked, etc.). We propose an architectural template for the HLS output that consists of a controller-datapath circuit associated with a memory subsystem into which computation units have been integrated. The enhanced memory subsystem is called computation-unit integrated memory (CIM). A CIM offers higher memory bandwidth (relative to what is offered through the system bus) to computation units present locally within it and reduces the overall communication between the memory subsystem and the controller-datapath, thus providing a template highly suitable for deriving efficient implementations of memory-intensive applications. This work addresses the challenge of providing an automatic synthesis framework for a CIM-based architecture. Our framework can analyze the various trade-offs involved in selecting suitable operations in a behavior for execution using a CIM and generate a high-performance, low-overhead implementation. Experiments with several behaviors indicate that an average performance improvement of 1.88/spl times/ (a maximum of 2.63/spl times/) is possible with very low area overheads. The energy-delay product improves by an average of 2.1/spl times/ (maximum of 3.4/spl times/).

REFERENCES

• 1: P. W. Diodato , Y.-H. Wong , C.-T Liu , K.-H. Lee , R. Dail , W. S. Lindenberger , A. C.. .. Dumbri , M. V. Depaolis , J. T. Clemens , W. W. Troutman , K. Noda , J. M. Drynan , M. Nakamae, Merged Dram-Logic In The Year 2001, Proceedings of the 1998 IEEE International Workshop on Memory Technology, Design and Testing, p.24, August 24-25, 1998
• 2: [2] H. Horikawa and H. Aslam, Merged-logic-type embedded DRAM suits high-performance SoCs, EE Times, Mar. 2003.
• 3: Christoforos E. Kozyrakis , Stylianos Perissakis , David Patterson , Thomas Anderson , Krste Asanovic , Neal Cardwell , Richard Fromm , Jason Golbus , Benjamin Gribstad , Kimberly Keeton , Randi Thomas , Noah Treuhaft , Katherine Yelick, Scalable Processors in the Billion-Transistor Era: IRAM, Computer, v.30 n.9, p.75-78, September 1997 [doi>10.1109/2.612252]
• 4: Ken Mai , Tim Paaske , Nuwan Jayasena , Ron Ho , William J. Dally , Mark Horowitz, Smart Memories: a modular reconfigurable architecture, Proceedings of the 27th annual international symposium on Computer architecture, p.161-171, June 2000, Vancouver, British Columbia, Canada
• 5: FlexRAM: Toward an Advanced Intelligent Memory System, Proceedings of the 1999 IEEE International Conference on Computer Design, p.192, October 10-13, 1999
• 6: Mark Oskin , Frederic T. Chong , Timothy Sherwood, Active pages: a computation model for intelligent memory, Proceedings of the 25th annual international symposium on Computer architecture, p.192-203, June 27-July 02, 1998, Barcelona, Spain
• 7: Mary Hall , Peter Kogge , Jeff Koller , Pedro Diniz , Jacqueline Chame , Jeff Draper , Jeff LaCoss , John Granacki , Jay Brockman , Apoorv Srivastava , William Athas , Vincent Freeh , Jaewook Shin , Joonseok Park, Mapping irregular applications to DIVA, a PIM-based data-intensive architecture, Proceedings of the 1999 ACM/IEEE conference on Supercomputing (CDROM), p.57-es, November 14-19, 1999, Portland, Oregon, United States [doi>10.1145/331532.331589]
• 8: Maya Gokhale , Bill Holmes , Ken Iobst, Processing in Memory: The Terasys Massively Parallel PIM Array, Computer, v.28 n.4, p.23-31, April 1995 [doi>10.1109/2.375174]
• 9: Prabhat Jain , G. Edward Suh , Srinivas Devadas, Embedded intelligent SRAM, Proceedings of the 40th conference on Design automation, June 02-06, 2003, Anaheim, CA, USA [doi>10.1145/775832.776051]
• 10: Michael Joseph Wolfe , Carter Shanklin , Leda Ortega, High Performance Compilers for Parallel Computing, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1995
• 11: Rajeev Barua , Walter Lee , Saman Amarasinghe , Anant Agarawal, Compiler Support for Scalable and Efficient Memory Systems, IEEE Transactions on Computers, v.50 n.11, p.1234-1247, November 2001 [doi>10.1109/12.966497]
• 12: Mary W. Hall , Jennifer M. Anderson , Saman P. Amarasinghe , Brian R. Murphy , Shih-Wei Liao , Edouard Bugnion , Monica S. Lam, Maximizing Multiprocessor Performance with the SUIF Compiler, Computer, v.29 n.12, p.84-89, December 1996 [doi>10.1109/2.546613]
• 13: J. Carter , W. Hsieh , L. Stoller , M. Swanson , L. Zhang , E. Brunvand , A. Davis , C.-C. Kuo , R. Kuramkote , M. Parker , L. Schaelicke , T. Tateyama, Impulse: Building a Smarter Memory Controller, Proceedings of the 5th International Symposium on High Performance Computer Architecture, p.70, January 09-12, 1999
• 14: Yan Solihin , Jaejin Lee , Josep Torrellas, Automatic Code Mapping on an Intelligent Memory Architecture, IEEE Transactions on Computers, v.50 n.11, p.1248-1266, November 2001 [doi>10.1109/12.966498]
• 15: Francky Catthoor , Koen Danckaert , Sven Wuytack , Nikil D. Dutt, Code Transformations for Data Transfer and Storage Exploration Preprocessing in Multimedia Processors, IEEE Design & Test, v.18 n.3, p.70-82, May 2001 [doi>10.1109/54.922804]
• 16: [16] R. Cloutier and D. Thomas, "The combination of scheduling, allocation, and mapping in a single algorithm," in Proc. Int. Symp. Microarchitecture, Dec. 1996, pp. 126-137.
• 17: N. D. Holmes , D. D. Gajski, Architectural exploration for datapaths with memory hierarchy, Proceedings of the 1995 European conference on Design and Test, p.340, March 06-09, 1995
• 18: Peter Marwedel, The MIMOLA design system: Detailed description of the software system, Proceedings of the 16th Conference on Design automation, p.59-63, June 25-27, 1979, San Diego, CA, United States
• 19: Herman Schmit , Donald E. Thomas, Synthesis of application-specific memory designs, IEEE Transactions on Very Large Scale Integration (VLSI) Systems, v.5 n.1, p.101-111, March 1997 [doi>10.1109/92.555990]
• 20: Kamal S. Khouri , Ganesh Lakshminarayana , Niraj K. Jha, Memory binding for performance optimization of control-flow intensive behaviors, Proceedings of the 1999 IEEE/ACM international conference on Computer-aided design, p.482-488, November 07-11, 1999, San Jose, California, United States
• 21: Jaewon Seo , Taewhan Kim , Preeti R. Panda, An integrated algorithm for memory allocation and assignment in high-level synthesis, Proceedings of the 39th conference on Design automation, June 10-14, 2002, New Orleans, Louisiana, USA [doi>10.1145/513918.514072]
• 22: Pradip K. Jha , Nikil D. Dutt, High-level library mapping for memories, ACM Transactions on Design Automation of Electronic Systems (TODAES), v.5 n.3, p.566-603, July 2000 [doi>10.1145/348019.348297]
• 23: [23] O. Sentieys, D. Chillet, J. P. Diguet, and J. L. Phillipe, "Memory module selection for high-level synthesis," in Proc. VLSI Signal Processing IX, Oct. 1996, pp. 273-282.
• 24: L. Benini , L. Macchiarulo , A. Macii , E. Macii , M. Poncino, From architecture to layout: partitioned memory synthesis for embedded systems-on-chip, Proceedings of the 38th conference on Design automation, p.784-789, June 2001, Las Vegas, Nevada, United States [doi>10.1145/378239.379066]
• 25: Peter Slock , Sven Wuytack , Francky Catthoor , Gjalt de Jong, Fast and extensive system-level memory exploration for ATM applications, Proceedings of the 10th international symposium on System synthesis, p.74-81, September 17-19, 1997, Antwerp, Belgium
• 26: Ying Zhao , Sharad Malik, Exact memory size estimation for array computations, IEEE Transactions on Very Large Scale Integration (VLSI) Systems, v.8 n.5, p.517-521, Oct., 2000 [doi>10.1109/92.894155]
• 27: [27] P. G. Kjeldsberg, F. Catthoor, and E. J. Aas, "Data dependency size estimation for use in memory optimization," IEEE Trans. Computer-Aided Design, vol. 22, no. 7, pp. 908-921, July 2003.
• 28: Chao Huang , Srivaths Ravi , Anand Raghunathan , Niraj K. Jha, Synthesis of Heterogeneous Distributed Architectures for Memory-Intensive Applications, Proceedings of the 2003 IEEE/ACM international conference on Computer-aided design, p.46, November 09-13, 2003 [doi>10.1109/ICCAD.2003.134]
• 29: Robert Sedgewick, Algorithms in C: Parts 1-4, Fundamentals, Data Structures, Sorting, and Searching, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1997
• 30: [30] TSMC 0.13µm Process (CL013G) High-Speed Single-Port Synchronous SRAM (SRAM-SP-HS) Generator User Manual, http://www.artisan.com.
• 31: Kazutoshi Wakabayashi, C-based synthesis experiences with a behavior synthesizer, “cyber”, Proceedings of the conference on Design, automation and test in Europe, p.83-es, January 1999, Munich, Germany [doi>10.1145/307418.307530]
• 32: [32] SYNOPSIS Design Compiler, VSS and Cyclone User Manual, http://www.synopsys.com.
• 33: [33] Sequence Design Power Tools 2000.4 User's Guide, http://www.sequencedesign.com.
• 34: [34] Cadence Openbook SE 5.3. IC 4.4.3 and LVD 3.0, http://www.cadence.com.
• 35: David E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1989