A 0.18 /spl mu/m implementation of a floating-point unit for a processing-in-memory system

The Data-Intensive Architecture (DIVA) system incorporates Processing-In-Memory (PIM) chips as smart-memory coprocessors to a microprocessor. This architecture exploits inherent memory bandwidth both on chip and across the system to target several classes of bandwidth-limited applications. A key capability of this architecture is the support of parallel single-precision floating-point operations. Each PIM chip includes eight single-precision FPUs, each of which supports eight basic instructions and IEEE-754 compliant rounding and exceptions. Through block sharing and a hardware-efficient division algorithm, the resulting FPU is well-balanced between area and performance. This paper focuses on the novel divide algorithm implemented and documents the fabrication and testing of a prototype FPU based on standard cell methodology in TSMC 0.18 /spl mu/m CMOS technology.

[1]  Michael J. Flynn,et al.  High-performance floating point divide , 2001, Proceedings Euromicro Symposium on Digital Systems Design.

[2]  Jeffrey T. Draper,et al.  Implementation of a 32-bit RISC processor for the data-intensive architecture processing-in-memory chip , 2002, Proceedings IEEE International Conference on Application- Specific Systems, Architectures, and Processors.

[3]  Michael J. Flynn,et al.  High-performance arithmetic for division and the elementary functions , 2002 .

[4]  Ansi Ieee,et al.  IEEE Standard for Binary Floating Point Arithmetic , 1985 .

[5]  Chun Chen,et al.  The architecture of the DIVA processing-in-memory chip , 2002, ICS '02.

[6]  Chang Woo Kang,et al.  Implementation of a 256-bit wideword processor for the data-intensive architecture (DIVA) processing-in-memory (PIM) chip , 2002, Proceedings of the 28th European Solid-State Circuits Conference.

[7]  Guido D. Salvucci,et al.  Ieee standard for binary floating-point arithmetic , 1985 .

[8]  Taek-Jun Kwon,et al.  An area-efficient standard-cell floating-point unit design for a processing-in-memory system , 2003, ESSCIRC 2004 - 29th European Solid-State Circuits Conference (IEEE Cat. No.03EX705).

[9]  Miriam Leeser,et al.  Division and square root: choosing the right implementation , 1997, IEEE Micro.