Kia Bazargan
ABSTRACT
Advances in the FPGA technology, both in terms of device capacity and architecture, have resulted in introduction of reconfigurable computing machines, where the hardware adapts itself to the running application to gain speedup. To keep up with the ever-growing performance expectations of such systems, designers need new methodologies and tools for developing reconfigurable computing systems (RCS). This paper addresses the need for fast compilation and physical design phase to be used in application development / debugging / testing cycle for RCS. We present a high-level synthesis approach that is integrated with placement, making the compilation cycle much faster. On the average, our tool generates the VHDL code (and the corresponding placement information) from the data flow graph of a program in less than a minute. By compromising 30% in the clock frequency of the circuit, we can achieve about 10 times speedup in the Xilinx placement phase, and 2.5 times overall speedup in the Xilinx place-and-route phase, a reasonable trade-off when developing RCS applications.
- 1.K. Bazargan. "Designing CAD Tools for Reconfigurable Computing". PhD thesis, Department of Electrical and Computer Engineering, Northwestern University, 2000. Google Scholar
Digital Library
- 2.K. Bazargan and M. Sarrafzadeh. "Fast Online Placement for Reconfigurable Computing Systems". Symposium on FPGAs for Custom Computing Machines, pp. 300-302, 1999. Google ScholarDigital Library
- 3.T. J. Callahan, P. Chong, A. DeHon, and J. Wawrzynek. "Fast Module Mapping and Placement for Datapaths in FPGAs". Symposium on Field Programmable Gate Arrays, 1998. Google ScholarDigital Library
- 4.A. DeHon and J. Wawrzynek. "Embedded Tutorial: Reconfigurable Computing: What, Why, and Implications for Design Automation". Design Automation Conference, pp. 610-615, 1999. Google ScholarDigital Library
- 5.S. Hauck,"The Roles of FPGAs in Reprogrammable Systems", Proceedings of the IEEE, 86(4):615-638,1998.Google ScholarCross Ref
- 6.T. Maruyama and T. Hoshino. "A C to HDL Compiler for Pipeline Processing on FPGAs". Symposium on FPGAs for Custom Computing Machines, 2000. Google ScholarDigital Library
- 7.M. Weinhardt. "Compilation and Pipeline Synthesis for Reconfigurable Architectures". Reconfigurable Architectures Workshop (RAW), 1997.Google Scholar
- 8.Z. A. Ye, N. Shenoy, and P. Baneijee. "A C compiler for a processor with a reconfigurable functional unit". Symposium on Field-Programmable Gate Arrays, pp. 95-100, 2000. Google ScholarDigital Library
Index Terms
- Integrating scheduling and physical design into a coherent compilation cycle for reconfigurable computing architectures
Recommendations
Pipeline Reconfigurable DSP for Dynamically Reconfigurable Architectures
Dynamically reconfigurable architectures, such as NATURE, achieve high logic density and low reconfiguration latency compared to traditional field-programmable gate arrays. Unlike fine-grained NATURE, reconfigurable DSP block incorporated NATURE ...
Recurrence cycle aware modulo scheduling for coarse-grained reconfigurable architectures
LCTES '09: Proceedings of the 2009 ACM SIGPLAN/SIGBED conference on Languages, compilers, and tools for embedded systemsIn high-end embedded systems, coarse-grained reconfigurable architectures (CGRA) continue to replace traditional ASIC designs. CGRAs offer high performance at a low power consumption, yet provide flexibility through programmability. In this paper we ...
Recurrence cycle aware modulo scheduling for coarse-grained reconfigurable architectures
LCTES '09In high-end embedded systems, coarse-grained reconfigurable architectures (CGRA) continue to replace traditional ASIC designs. CGRAs offer high performance at a low power consumption, yet provide flexibility through programmability. In this paper we ...
Comments