A VPM (Virtual Pipelined Memory) architecture for a fast row-cycle DRAM

We propose a Virtual Pipelined Memory (VPM) architecture for fast row-cycle by using a top-down design approach. A pipeline structure in the row path and integration of multiple SRAM buffers enable fast row-cycle. VPM shows higher performance than that of SDRAM by about 40% and that of VCM by about 20%. VPM maintains backward compatibility with a conventional SDRAM interface and consumes low power by adopting partial cell core activation.

[1]  Hyoungsik Nam,et al.  A 64-Mbit, 640-MByte/s bidirectional data strobed, double-data-rate SDRAM with a 40-mW DLL for a 256-MByte memory system , 1998, IEEE J. Solid State Circuits.

[2]  Richard Crisp,et al.  Direct RAMbus technology: the new main memory standard , 1997, IEEE Micro.

[3]  Hirotaka Tamura,et al.  10-ns row cycle DRAM using temporal data storage buffer architecture , 1998, 1998 Symposium on VLSI Circuits. Digest of Technical Papers (Cat. No.98CH36215).

[4]  K. Fujishima,et al.  A circuit design of intelligent CDRAM with automatic write back capability , 1990, Digest of Technical Papers., 1990 Symposium on VLSI Circuits.

[5]  Hiroyuki Kobayashi,et al.  Fast cycle RAM (FCRAM); a 20-ns random row access, pipe-lined operating DRAM , 1998, 1998 Symposium on VLSI Circuits. Digest of Technical Papers (Cat. No.98CH36215).