A barrel shift microsystem for parallel processing

ABSTRACT

A flow-through interconnection network microsystem is described. It is part of a parallel SIMD graphics architecture called Cube in which the network interconnects between n pairs of processors and memories. No two accesses involve the same memory or processor and their is an uniform communication distance among the processors. The interconnection network is based on a modular and VLSI implemented Barrel Switch (BS) unit, which provides modularity and flexibility of the entire network. A rotate distance of up to 16 processor-memory pairs is performed in a flow-through manner in a single machine cycle. Structurally, the BS is organised in a simple and repetitive pattern of junction elements and connection paths, extendable in its overall length and its data width, and suited for VLSI implementation.

REFERENCES

• 1: R. Bakalash. Cube - The 3-D Frame-Buffer Architecture. Ph.D. Thesis, Ben-Gurion University, Beer-Sheva, Israel. April 1988.
• 2: Ralph Duncan, A Survey of Parallel Computer Architectures, Computer, v.23 n.2, p.5-16, February 1990 [doi>10.1109/2.44904]
• 3: S. M. Kang. Domino-CMOS Barrel Switch for 32-Bit VLSI Processors, IEEE Circuits and Devices Magazine, May 1987, pp.3-8.
• 4: A. Kaufman. Voxel Based Architectures for 3-D Graphics, Proc. of the IFIP Information Processing 86, Dublin, Irland (September 1986), 361-366.
• 5: Arie Kaufman , Reuven Bakalash, Memory and Processing Architecture for 3D Voxel-Based Imagery, IEEE Computer Graphics and Applications, v.8 n.6, p.10-23, November 1988 [doi>10.1109/38.20314]
• 6: Harold S. Stone, High-performance computer architecture, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1987