Low overhead soft error detection and correction scheme for reconfigurable pipelined data paths

In this paper, we describe a novel scheme for radiation hardening of high performance pipelined architectures and data paths. The proposed technique uses a local ground bus decoupled from the global ground using an additional pull down device, to detect a transient error. Combining the detector output with duplicated pipeline registers enables an instruction execution through the data path to be repeated as soon as the error is detected. The detector outputs from various stages in a pipelined data path are manipulated to maintain correctness of data in the event of a transient error detection and corresponding instruction roll back. The proposed technique is extremely effective for errors of different pulse widths and comes without the extra cost of error checking codes, watch dog processors and logic core duplication as used by other techniques in literature. Our scheme provides 100% radiation hardening over all process corners with only 9.7% and 21.73% area and power overhead respectively with the delay overhead being masked out by the pipeline stages used in modern high performance data path architectures.

[1]  Edward J. McCluskey,et al.  Concurrent Error Detection Using Watchdog Processors - A Survey , 1988, IEEE Trans. Computers.

[2]  R.C. Baumann,et al.  Radiation-induced soft errors in advanced semiconductor technologies , 2005, IEEE Transactions on Device and Materials Reliability.

[3]  Kartik Mohanram,et al.  Gate sizing to radiation harden combinational logic , 2006, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[4]  Martin Margala,et al.  MORA - An Architecture and Programming Model for a Resource Efficient Coarse Grained Reconfigurable Processor , 2009, 2009 NASA/ESA Conference on Adaptive Hardware and Systems.

[5]  Marc Tremblay,et al.  The implementation and application of micro rollback in fault-tolerant VLSI systems , 1988, [1988] The Eighteenth International Symposium on Fault-Tolerant Computing. Digest of Papers.

[6]  Edward J. McCluskey,et al.  Dependable adaptive computing systems-the ROAR project , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[7]  Jill J. Hallenbeck,et al.  Modulo 3 Residue Checker: New Results on Performance and Cost , 1988, IEEE Trans. Computers.

[8]  Sunil P. Khatri,et al.  A Delay-efficient Radiation-hard Digital Design Approach Using CWSP Elements , 2008, 2008 Design, Automation and Test in Europe.

[9]  Fernanda Gusmão de Lima Kastensmidt,et al.  Using Bulk Built-in Current Sensors to Detect Soft Errors , 2006, IEEE Micro.

[10]  Ming Zhang,et al.  A CMOS design style for logic circuit hardening , 2005, 2005 IEEE International Reliability Physics Symposium, 2005. Proceedings. 43rd Annual..

[11]  M. Nicolaidis,et al.  Evaluation of a soft error tolerance technique based on time and/or space redundancy , 2000, Proceedings 13th Symposium on Integrated Circuits and Systems Design (Cat. No.PR00843).

[12]  Michael C. Huang,et al.  Variation-tolerant hierarchical voltage monitoring circuit for soft error detection , 2009, 2009 10th International Symposium on Quality Electronic Design.