Efficient BISR Techniques for Word-Oriented Embedded Memories with Hierarchical Redundancy

Computer and Information Science, 5th IEEE/ACIS International Conference on 01/2006; DOI: 10.1109/ICIS-COMSAR.2006.32


In this paper, BISR (built-in self-repair) techniques with hierarchical redundancy architecture are proposed for word-oriented embedded memories. Our BISR circuit consists of a built-in self-test (BIST) module and a built-in redundancy-analysis (BIRA) module. Spare words, spare rows, and spare columns are added into the memory cores as redundancy. However, the spare rows and spare columns are virtually divided into spare row blocks and spare column group blocks. The address reconfiguration is performed at row block or column group block level instead of the traditional row or column level. An extended essential spare pivoting (EESP) algorithm is proposed for redundancy analysis based on the proposed redundancy organization. A practical 16K .. 32 SRAM with BISR circuitry is designed and implemented. Experimental results show that we can obtain a higher repair rate with negligible area overhead (2.56%) of the BISR circuit for a 1024K .. 2048-bit SRAM chip.

10 Reads
  • Source
    • "In [3] [4] [5] both redundant rows and columns are incorporated into the recollection array. In [6] spare words, rows, and columns are incorporated into the word-oriented recollection cores as redundancy. All these redundancy mechanisms bring penalty of area and intricacy to embedded recollections design. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Abstract: Built-In Self-Repair (BISR) with Redundancy is an effective yield enhancement strategy for embedded memories. This paper proposes an efficient BISR strategy which consists of a Built-In Self-Test (BIST) module, a Built-In Address -Analysis (BIAA) module and a Multiplexer (MUX) module. The BISR is designed flexible that it can provide four operation modes to SRAM users. Each fault address can be saved only once is the feature of the proposed BISR strategy. In BIAA module, fault addresses and redundant ones form a one-to-one mapping to achieve a high repair speed. Besides, instead of adding spare words, rows, columns or blocks in the SRAMs, users can select normal words as redundancy. The selectable redundancy brings no penalty of area and complexity and is suitable for compiler design. A practical 4K × 32 SRAM IP with BISR circuitry is designed and implemented based on a 55nm CMOS process Experimental results show that the BISR occupies 20% area and can work at up to 150MHz.
    International Journal For Technological Research In Engineering, hyderabad; 11/2015
  • Source
    • "However different redundancy organization will lead to different area cost and repair rate. Since most of the memory faults are single cells, spare words [6] are very efficient in reducing area. "
    [Show abstract] [Hide abstract]
    ABSTRACT: As RAM is major component in present day SOC, by improving the yield of RAM improves the yield of SOC. So the repairable memories play a vital role in improving the yield of chip. This paper presents the efficient Reconfigurable Built-in Self Repair (Re BISR) circuit along with 2D redundancies (spare row/column) and spare cells. Since most of faults are single cell fault, the area of spare is effectively utilized by replacing defected cell with spare cell. This in turn increases repair rate. The proposed repair circuit is Reconfigurable for less area, used to repair multiple memories with different in size and redundancy. The experimental results show that proposed ReBISR circuit reduces the area and increases the yield of the memory.
    International Journal of Computer Applications 06/2011; 24(8). DOI:10.5120/2971-3995
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: With the growth of memory capacity and density, test cost and yield improvement are becoming more important. In the case of embedded memories for systems-on-a-chip (SOC), built-in redundancy analysis (BIRA) is widely used as a solution to solve quality and yield issues by replacing faulty cells with extra good cells. However, previous BIRA approaches focused mainly on embedded memories rather than commodity memories. Many BIRA approaches require extra hardware overhead to achieve the optimal repair rate, which means that 100% of solution detection is guaranteed for intrinsically repairable dies, or they suffer a loss of repair rate to minimize the hardware overhead. In order to achieve both low area overhead and optimal repair rate, a novel BIRA approach is proposed and it builds a line-based searching tree. The proposed BIRA minimizes the storage capacity requirements to store faulty address information by dropping all unnecessary faulty addresses for inherently repairable die. The proposed BIRA analyzes redundancies quickly and efficiently with optimal repair rate by using a selected fail count comparison algorithm. Experimental results show that the proposed BIRA achieves optimal repair rate, fast analysis speed, and nearly optimal repair solutions with a relatively small area overhead.
    IEEE Transactions on Very Large Scale Integration (VLSI) Systems 12/2009; 17(12):1665-1678. DOI:10.1109/TVLSI.2008.2005988 · 1.36 Impact Factor
Show more

Similar Publications