Some implementations of segment sequential functions

Abstract

Since conventional computers are straining to handle the increased size and sophistication of non-numeric processing (data management, information retrieval, artificial intelligence), a new class of non-numeric architectures is evolving. The segment sequential architecture is one of these. Further development of this architecture requires new techniques for multiple cell operation and intercell communication to handle control and search operations. This paper describes such techniques for instruction fetching, operand recall, string, set and tree context searching, and pointer transfer. It is expected that combinations of these techniques will appear in future architectures that are needed for non-numeric processing.

Implementing a relational database by means of specialzed hardware

“…Moreover, the search hardware can support concurrent tasks on the multiplexed output of up to 12 disk channels. This contrasts with the logic per track designs of Parker [13], RAP [12], CASSM [3,10,14,151, and RARES [9], which generally have only limited selection capability per scan but possibly greater parallelism. This paper considers two extended versions of the CAFS hardware.…”

“…Figure 1 is based on the diagram in Mitchell et al [5,111 and gives the outline architecture of the content addressable file store (CAFS). The selector (18) is used to set up the key registers (3)(4)(5) with just the key value pairs taken from the selector (18). The tuple (2) from a file on disk pack (1) enters each key register and sets a latch if the value in a tuple is "greater than," "equal to," or "less than" the value in the key register.…”

“…This paper considers two extended versions of the CAFS hardware. E. Babb the CASSM system [3] and is similar to an earlier idea patented by the author in 1974 [ 11. A more detailed comparison with the CASSM system will be given later.…”

“…This is done by associating an index with each member of the list of parts. Thus transistor is labeled 1, diode 2, etc., to give a list of part-index pairs [(Transistor, 1) (Diode, 2) (Resistor, 3)]. Any subset of this original list can now be uniquely coded by a three-element bit array.…”

“…Uni.t (33) selects a disk drive (1) and allocates channels. Tuples (2) are then sent to the key registers (3)(4)(5)(6)(7)(8), bit address filter (21), and retrieval unit (14). The bit address filter extracts the index value I from a coupling index such as IrAm.…”