Rapid application specific floating-point unit generation with bit-alignment

ABSTRACT

While ASIPs have allowed designers to create processors with custom instructions to target specific applications, floatingpoint units are still instantiated as fixed general-purpose units, which wastes area if not fully utilized. Therefore, there is a need for custom FPUs for embedded systems. The creation of a custom FPU requires the selection of a subset of the full floating-point instruction set and the implementation of this subset in hardware, such that the runtime of the application is minimized. To minimize area, it is desirable to merge the datapaths for each of the floating-point operations, so that redundant hardware is minimized. Floating-point datapaths are complex and contain components with varying bit-widths, so sharing components of different bit-widths is necessary. However, this introduces the problem of bit-alignment, which involves determining how smaller resources should be aligned within larger resources when merged. This is a problem that has been largely neglected in previous work.

Thus, this paper presents a novel algorithm for solving the bit-alignment problem, which neatly integrates into the datapath merging process. By solving this bit-alignment problem, automatic datapath merging can be made available for FPU generation. To explore the trade-offs between area and performance, a rapid design space exploration was performed to determine which FP operations should be implemented in hardware rather than emulated. Our results show that more floating-point hardware does not necessarily equate to lower run-time if the additional hardware increases delay. We found that bit-alignment reduced area by an average of 22.5% in our benchmarks, compared to an average of 14.1% without bit-alignment.

REFERENCES

• 1: Xtensa Processor. Tensilica Inc. http://www.tensilica.com.
• 2: ARCtangent. ARC International. http://www.arc.com.
• 3: ASIP Meister. ASIP Solutions. http://www.asip-solutions.com.
• 4: Werner Geurts , Francky Catthoor , Hugo de Man, Quadratic zero-one programming based synthesis of application specific data paths, Proceedings of the 1993 IEEE/ACM international conference on Computer-aided design, p.522-525, November 07-11, 1993, Santa Clara, California, United States
• 5: Junhyung Um , Jae-hoon Kim , Taewhan Kim, Layout-driven resource sharing in high-level synthesis, Proceedings of the 2002 IEEE/ACM international conference on Computer-aided design, p.614-618, November 10-14, 2002, San Jose, California [doi>10.1145/774572.774663]
• 6: Chia-Jeng Tseng and D. P. Siewiorek. Automated Synthesis of Data Paths in Digital Systems. In IEEE Trans. Computer-Aided Design Integr. Circuits Syst., volume 5, pages 379--395, July 1986.
• 7: Charles Y. Hitchcock, III , Donald E. Thomas, A method of automatic data path synthesis, Proceedings of the 20th conference on Design automation, p.484-489, June 27-29, 1983, Miami Beach, Florida, United States
• 8: Oliver Bringmann , Wolfgang Rosenstiel, Resource sharing in hierarchical synthesis, Proceedings of the 1997 IEEE/ACM international conference on Computer-aided design, p.318-325, November 09-13, 1997, San Jose, California, United States
• 9: S. Raje , R. A. Bergamaschi, Generalized resource sharing, Proceedings of the 1997 IEEE/ACM international conference on Computer-aided design, p.326-332, November 09-13, 1997, San Jose, California, United States
• 10: E. M. Witte , A. Chattopadhyay , O. Schliebusch , D. Kammler, Applying Resource Sharing Algorithms to ADL-driven Automatic ASIP Implementation, Proceedings of the 2005 International Conference on Computer Design, p.193-199, October 02-05, 2005 [doi>10.1109/ICCD.2005.25]
• 11: N. Moreano, E. Borin, C. Souza, and G. Araujo. Efficient Datapath Merging for Partially Reconfigurable Architectures. In IEEE Trans. Computer-Aided Design Integr. Circuits Syst., volume 24, pages 969--980, July 2005.
• 12: Philip Brisk , Adam Kaplan , Majid Sarrafzadeh, Area-efficient instruction set synthesis for reconfigurable system-on-chip designs, Proceedings of the 41st annual conference on Design automation, June 07-11, 2004, San Diego, CA, USA [doi>10.1145/996566.996679]
• 13: K. Schoofs, G. Goossens, and HG Man. Bit-Alignment in Hardware Allocation for Multiplexed DSP Architectures. In European Conference on Design Automation, pages 289--293, Feb 1993.
• 14: Yee Jern Chong , Sri Parameswaran, Automatic application specific floating-point unit generation, Proceedings of the conference on Design, automation and test in Europe, April 16-20, 2007, Nice, France
• 15: M. R. Garey and D. S. Johnson. Computers and Intractability. W. H. Freeman and Company, 1979.
• 16: Cliquer. http://users.tkk.fi/~pat/cliquer.html.
• 17: SimpleScalar Tool Set. http://www.simplescalar.com.
• 18: Jorgen Peddersen , Seng Lin Shee , Andhi Janapsatya , Sri Parameswaran, Rapid Embedded Hardware/Software System Generation, Proceedings of the 18th International Conference on VLSI Design held jointly with 4th International Conference on Embedded Systems Design, p.111-116, January 03-07, 2005 [doi>10.1109/ICVD.2005.145]
• 19: IEEE standard for binary floating-point arithmetic, 1985.
• 20: David A. Patterson , John Hennessy, Computer Organization and Design, Morgan Kaufmann Publishers Inc., San Francisco, CA, 2004
• 21: Chunho Lee , Miodrag Potkonjak , William H. Mangione-Smith, MediaBench: a tool for evaluating and synthesizing multimedia and communicatons systems, Proceedings of the 30th annual ACM/IEEE international symposium on Microarchitecture, p.330-335, December 01-03, 1997, Research Triangle Park, North Carolina, United States
• 22: Synopsys Tool Set. http://www.synopsys.com.
• 23: SoftFloat. http://www.jhauser.us/arithmetic/SoftFloat.html.

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.3 SPECIAL-PURPOSE AND APPLICATION-BASED SYSTEMS

General Terms:
Algorithms, Design, Experimentation, Performance

Keywords:
bit-alignment, datapath merging, floating-point